Release notes
What changed in each release since 2.0, newest first, with what to do on every machine that shares your config root, and how to move from dotagents. How to install a new release is in Upgrade.
To 3.1
Nothing to migrate by hand. A workspace session that is already open keeps its old panes until you close it; run the workspace command again to get the new layout.
- New:
tackroom dash, a live screen for a terminal pane. It is a terminal view again, aftertackroom tuiwas removed in 3.0, and it works differently.tuiwas read-only, with four tabs that loaded once.dashis one screen that refreshes itself (the sync state every 30 seconds, the crons every 5 minutes, and onr), draws itself again at once when the pane is resized, and acts: Enter runs the selected launchd job now,ppauses or resumes it, andssyncs, each after a y/n question. It shows the overall state, the failing jobs and those whose last run failed first, by the same job health as the web view, and what is wrong with a harness that drifted. It needs a terminal; elsewhere usetackroom statusandtackroom cron collect --table. See terminals.md. - Changed:
tackroom rex,tackroom tmux,tackroom zellijandtackroom ternopen two panes instead of three:tackroom dashacross the full width on top, with 70% of the height, and the shell below it, which has the focus. Thetackroom statusandtackroom cron collect --tablepanes are replaced by the dash. In Tern the shell is the upper pane and the two share the height, because Tern splits only right and down and has no size option. In Rex the dash pane is labelleddash, and the panes no longer wait for Enter to run their command again. - Changed:
tackroom tuistill fails as an unknown command, and now namestackroom dash. - New: Overview in
tackroom viewhas a rail under its headline where every enabled harness hangs a nameplate: straight when in sync, crooked from one hook when it needs a sync, on the floor when it fails, empty hooks when it is not installed. The plates swing when the pointer nudges them, after a sync and when a state changes, and stay still with reduced motion. See view.md.
To 3.0.2
Nothing to migrate by hand. If you read tackroom status or tackroom cron collect --table in a script, note the changes below; status --json and cron collect without --table are unchanged.
- Changed:
tackroom statusis one screen by default. It prints a title with the overall state, the repo link, the sources and the lock check, then one table with a row per harness. A harness gets a block under the table only when it needs attention: its config could not be read, it drifted, or it lists something to act on. What to do comes last, and a synced setup prints nothing after the table, so the last line is no longerEverything is synced.. The title sayssyncedorneeds attention. In a window too narrow for the bordered table, the table loses its borders, then the columns no harness uses, then becomes one line per harness, and the sources lose their URLs where those would wrap.tackroom status --verboseprints the block of every harness, with the full lists and native paths, asstatusdid before. - Changed:
tackroom cron collect --tablefits the terminal. On a terminal wider than the table it prints as before. On a narrower one both tables lose their borders, and the jobs table then loses columns (problems,runs,source,schedule), then shortens theidand thelast rununtil it fits. Lines under Outputs and Problems wrap between words. The access table cuts itsdetailthe same way. A longidis cut in the middle, so the end that tells launchd labels apart stays. A last run that failed showsexit Nin red. Into a pipe or a file the output keeps every column. The access table now comes first, then the jobs, then Outputs and Problems, so the jobs and problems are the last lines on screen. - Changed:
tackroom tmux,tackroom zellijandtackroom rexputtackroom statusabove the shell on the left, with 70% of that half, andtackroom cron collect --tableat full height on the right. The shell had the whole left half and the two command panes a quarter of the window each.tackroom ternputs the shell above the status pane, in equal halves, because Tern splits only right and down. A session that already exists keeps its old layout: close it and run the command again to get the new one. See terminals.md. - Changed: in the Rex workspace the status and crons panes are labelled
statusandcrons, and Enter in either pane runs its command again, so the pane refreshes without reopening the workspace.
To 3.0.1
Nothing to migrate by hand, with two things to know. If you use the Herdr panel, copy the mods from herdr/tackroom/mods/ again. A sync run with a second config file next to tackroom.yaml, such as a web view started with --config, now stops with an error unless that file lists the pinned skill sources as tackroom.yaml does.
- Changed: the web view has a new look. In a window 1100 px wide or more, the Overview puts what is failing or needs attention in the main column and everything else in a rail on the right. Issues and cron jobs are cards with a status icon, section headings carry a count, and on a desktop with a mouse the buttons are 36 px tall instead of 44. Nothing was renamed or moved to another page, and the buttons do what they did.
- Fixed: the audit missed a command split over lines in a script. A download whose
| shsat on the next line, after a backslash or after a pipe at the end of the line, did not block. A line that ends with a backslash or a pipe is now also read together with the line after it, socurl ... \followed by| shis CRITICAL like the one-line form. Markdown is unchanged. Nothing is retroactive: a pin already in the lock keeps syncing (skills.md). - Fixed: the audit blocked a skill whose text only names the pattern. "Prefer a package manager over
curl | sh" was a CRITICALremote-execfinding, so a new pin of that skill did not sync until you accepted it.curl | shandwget | shwith nothing between the command and the pipe are no longer a finding, in the gate and in thetackroom doctorwarning: they name the pattern and download something only where a config file such as~/.curlrcsupplies the URL. A download with a URL, an option or a variable before the pipe is CRITICAL as before. (skills.md). - Fixed: in the web view, Run now, Pause and Resume looked dead for a long time. While one job's action ran, every job's buttons were greyed out, and an action first waited for any crons collect in progress, which lasts as long as the slowest host takes to answer over SSH. An action now starts at once. Only the job it acts on has its buttons off, and the button you clicked reads Starting…, Pausing…, Resuming… or Saving…; every other job stays clickable. An action or a host probe that runs past its timeout now returns when the timeout ends, not when the command it started exits.
- Fixed: the Crons tab of the Herdr panel and of the web view left a job whose last run failed out of the line under the headline, so "2 of 18 jobs failing" was followed by counts that added up to 17. The line now starts with it ("1 last run failed, 12 healthy, 2 paused, 1 not run yet"). In the panel, a last run such as "16 min ago" no longer wraps onto a second line in the per-machine list. The web view's fix comes with the release; if you use the Herdr panel, copy the mods from
herdr/tackroom/mods/again. - Fixed: a config that named Qwen Code
qwen, as the other harnesses are named by their short names, was read as an unknown custom harness. It got skills only, andconfig inventory, the web view and the Herdr panel showedqwenin lowercase and said it takes no roles; MCP servers, hooks, roles and the root file never reached it.qwenis now read asqwen-code, asclaude-codeis read asclaude, inagents:, in--agentsand in theagents:lists of MCP servers, hooks and skill sources, andstatusandconfig inventoryreport it asqwen-code. The next sync adds what Qwen Code gets:skills.directoriesin~/.qwen/settings.json, your MCP servers and hooks, the roles in~/.qwen/agentsand~/.qwen/QWEN.md. It deletes nothing: the skills link an earlier sync made in~/.qwen/skillsstays, andstatuscounts it as external.tackroom.yamlis not rewritten, though a command that edits it, such asmcp add, saves the name asqwen-code. A config that lists bothqwenandqwen-codenow stops withconfig agent qwen-code is duplicated, asclaudewithclaude-codedoes; delete one of the two entries (harnesses.md). - Fixed: when an outside skill source no longer had a folder listed in its
skill_dirs, for example because upstream deleted it,syncandpullstopped withskill directory "..." not found in cloned external source ...and nothing else synced, for any source or harness.skill updatefailed the same way, or, for a source withoutmaterialize: true, pinned the commit without the folder, so every sync after it failed. Now that source alone is blocked: sync keeps its pin and its skill copies, prints a warning and syncs everything else, andskill updatekeeps its previous pin and updates the other sources.status,sync --dry-runandconfig inventorylist it as blocked with the folder and the commit, anddoctorwarns. To clear it, remove or rename the folder inskill_dirsintackroom.yaml(skills.md). The web view and the Herdr panel show such a source with its reason and that fix, not as an audit finding to accept; if you use the Herdr panel, copy the mods fromherdr/tackroom/mods/again. - Fixed:
skill update <name>dropped fromtackroom.lockthe pin and the materialized skills of every other source whoseurlorbranchintackroom.yamlno longer matched its lock entry, and the next sync then failed withcollides with unrelated canonical skill. The entry now stays until a sync or an update of that source replaces it. If a lock already lost pins this way, restore it from git (git checkout <commit> -- tackroom.lockin the config root) and runtackroom sync. - Fixed: a sync run with a second config file in the config root, for example from a web view started with
--config ~/.agents/crons.yaml, emptiedtackroom.lockand deleted the materialized skill copies inskills/whenever that file did not list the outside skill sources, and still reported success. Every config file in a folder shares the lock andskills/. Nowsync,pull,sync --dry-run,skill sources addand the web view's Sync stop before they touch the lock,skills/or a harness when the file is nottackroom.yaml, atackroom.yamlsits next to it and it leaves out a source the lock pins, or lists it with another url, branch ormaterialize; the error names the sources.pullchecks after itsgit pull, so an incoming commit that fixes the file lets it sync. If it already happened, restoretackroom.lockandskills/from git (git checkout <commit> -- tackroom.lock skillsin the config root), then runtackroom syncwithout--configor with--configpointing attackroom.yaml.
To 3.0
- New:
tackroom tmuxandtackroom zellij. Each opens a session namedtackroomin the config root with a shell,tackroom statusandtackroom cron collect --table, and takes--config PATHand--dry-run, astackroom ternandtackroom rexdo. A second run shows the existing session. See terminals.md and terminals.md - Removed: the bundled memory system. tackroom no longer ships memory tiers, the scripts under
memory/or theremandknowledge-synctools, andsyncno longer builds Go tools undermemory/tools/. A memory file now reaches your harnesses as a file listed underinstructions:(memory.md). - Changed:
setup --memoryis still accepted and does nothing.--memory basicor--memory memsearchprints one line saying so, and setup goes on.tackroom memsearch,setup memsearchandstatus memsearchare gone, and so are the memsearch lines instatusanddoctor.setupno longer adds or rewrites memory hooks, intackroom.yamlor in a harness's own config. The sync it runs removes a harness registration only when the memory script it runs is retired, as described below. - What an existing config keeps: its memory hooks stay in
tackroom.yamland sync as ordinary hooks. While a hook entry points at a script undermemory/hooks/, enabled or not, every file undermemory/stays, and the first sync stops tracking them in.tackroom-starter.jsonwith one note; after that they are yours to delete. With no such hook entry at that first sync, it removes the scripts you never edited and lists the ones you did once. Any sync then also removes a hook registration in a harness's own config that still runs a removed or missing memory script, such as a Pi or OMP module or a Factoryhooks.jsonentry left from a memory hook you deleted fromtackroom.yaml; it backs each one up first, as for any removed hook. A harness turned off withenabled: falseis not synced, so its registrations stay:tackroom hook remove --dry-run --agents <name> memory/hookslists them, and the same command without--dry-runremoves them.memory/tools/, builtremandknowledge-syncbinaries andmemsearch.confare left alone. Details are in memory.md. remandknowledge-syncnow live in the rem repository.- Changed: the 72-hour wait for a new pin of an outside skill source, or a new npm or PyPI version, is now called a cooldown, and the 72 hours are the minimum release age. The rule itself is unchanged. Output that said
held,hold endsorheld 41h of 72hnow sayscooldown,cooldown endsandcooldown 41h of 72h;statusandsync --dry-runlist such items under "in cooldown or blocked (skipped by sync)".--allow-freshand--reasonkeep their names and still skip the cooldown. - Changed:
tackroom.lockrecords cooldowns undercooldowns:, each withcooldown_until, instead ofholds:andhold_until. Nothing to do by hand: the old keys are still read with the same meaning, so an item in cooldown stays in cooldown, and the next command that writes the lock rewrites them as the new keys. In a lock with both keys, an entry undercooldowns:wins over one underholds:for the same item and ref, and aholds:entry with no match is kept. tackroom 2.x does not readcooldowns:: a 2.x machine that rewrites a shared lock drops it, and with it any recorded--allow-freshdecision, which leaves the item in cooldown. Upgrade every machine that shares the lock. - Removed: the
heldfield ofsync --dry-run --json, which breaks scripts that read it. The same list, every item sync skips, is nowskipped, and an item in cooldown there has"kind": "cooldown"instead of"kind": "held"; a blocked item keeps"kind": "blocked". The lock rows of the web view's/api/inventoryuse"state": "cooldown"instead of"state": "held". There is no alias for the old names. - Changed: the Herdr panel reads
skippedand is updated in this release; copy the mods fromherdr/tackroom/mods/again. It still readsheldfrom an older tackroom. - Removed:
tackroom tui, deprecated since 2.x. It now fails as an unknown command and names the replacement:tackroom view, ortackroom status,tackroom cron collect --tableandtackroom doctorin a terminal. - New:
status --jsonandsync --jsonlist the items sync skips underskipped, assync --dry-run --jsondoes;[]when there are none. - New:
--allow-fresh=<item>prints a warning on stderr for each name that matches nothing in cooldown, with the items that are, and exits 0 as before. - Fixed:
tackroom statusno longer says "none configured" for the external skill lock when every source is in cooldown or blocked; it shows the counts. - Fixed:
sync --dry-runplans the skills a materialized source would add, including one released with--allow-fresh. Before, it saidplanned noneand the sync then added them. - Fixed:
sync --jsonprinted a line from git ahead of the JSON document when a source was blocked. git's output now goes to stderr. - Fixed:
syncno longer printsmaterialized <from> -> <to>when the copy did not change. - Fixed:
syncreported a memory script you had edited on every run. It lists the script once, stops tracking it and leaves the file alone. - Fixed: a command that edits
tackroom.yamlortackroom.local.yaml(skill sources add,mcp addandremove,config set,setup, the web view) changes only the lines of the entry it touches. Blank lines, comments, an empty list such ashooks: [], CRLF line endings and a missing final newline are kept, and untouched entries no longer gainagents: []. Before, every such write reformatted the whole file. - Changed: a first
tackroom setupwrites the startertackroom.yamlas it ships, with the detected agents filled in: it keepshooks: []and its blank lines, and no longer addsmcp_servers: []. - New: a security fix skips the cooldown. When
syncfinds an exact npm or PyPI version in cooldown, it asks OSV whether a published advisory names that version as its fix; if one does, sync takes the version at once, printscooldown skipped for <item> (<ref>): security fix: GHSA-...and records it intackroom.lockas--allow-freshwould, with the advisory ids as the reason. If OSV cannot be reached, the cooldown applies as before.statusandsync --dry-runmake no lookup, and git skill sources are not covered (skills.md). - New:
trusted_packagesintackroom.yamlortackroom.local.yamllists the packages, asnpm:<name>orpypi:<name>, whose new versions skip the cooldown. Without the key the list isnpm:@openai/codex,npm:@anthropic-ai/claude-codeandnpm:@earendil-works/pi-coding-agent; a key you write replaces it, sotrusted_packages: []gates every package. Before,@openai/codexwas exempt in code and nothing else could be. - Changed: the audit no longer blocks Markdown text that only describes a risk. A CRITICAL pattern counts one level lower, and so does not block, when it sits in double quotation marks or follows never, do not, don't, avoid, instead of, for example, such as, flag, detect or warn in the same clause.
doctor auditstill lists it as HIGH. A script that pipes a download into a shell blocks as before (skills.md). - New:
tackroom skill sources addaccepts a repository that is itself one skill, withSKILL.mdat its root. It is recorded asskill_dirs: [.]and named by thename:in that file, else by the source name. - Changed:
skill sources add --allskips a skill name that two folders both hold, prints one line per skipped name and adds the rest. Before, it refused the whole repository. - Changed: a source you wrote by hand with
skill_dirs: [.]on a repository with a rootSKILL.mdis now named by thename:in that file. If that differs from the source name, the next sync installs the skill under the new name and removes the old copy. - Changed: the first line of the README and the landing page now leads with what does not port between agents: MCP servers, hooks and subagents.
- Fixed: the audit treated every triple-quoted Python string as a docstring and counted a match inside it one level lower, so a script could hold
curl ... | shin a string, run it withsubprocess, and still be pinned. Only a real docstring, the first statement of a module, class or function, is lowered now. A pin already in the lock keeps syncing, since the gate checks only a new or changed pin;tackroom doctor auditlists such a match as CRITICAL. A new or changed pin that does this is blocked until you accept or remove it. - New: Gemini CLI is supported again (key
gemini, detected bygeminionPATH), with the adapter 2.7 had: skills read from~/.agents/skills, stdio and remote MCP servers and hooks in~/.gemini/settings.json, roles in~/.gemini/agents, and the root file~/.gemini/GEMINI.md, shared with Antigravity CLI. A config that still namesgemini, which 2.8 ignored, syncs to it again with no edit, including a server, hook or source MCP whoseagents:list names onlygemini. See harnesses.md. - New: a job under
crons.jobstakes an optionaloutput, the path or glob where its results land.cron addandcron edittake--output PATH, and--output ""removes it.cron collectJSON carriesoutputandoutput_expanded(expanded only for a job on this machine),--tablelists them under "Outputs", and the web view shows them in the job's details (crons.md). - Changed: building from source needs Go 1.26.7 or newer; it needed Go 1.25. Release binaries are still built with Go 1.27.
- Changed:
tackroom viewstarts the view in the background when none runs, opens it and returns at once. That view exits after 30 minutes without requests; an open page keeps it up.--foregroundserves in the terminal as before. A launchd job or systemd unit that runstackroom viewkeeps working: under a service manager, detected fromXPC_SERVICE_NAMEorINVOCATION_IDwhen stdout is not a terminal, plainviewserves in the foreground.--foregroundis the explicit form. A view an older tackroom started from a terminal restarts onto this release as a background view. See view.md. - New:
tackroom view --jsonprintsurl,addr,pid,startedandidle_timeoutas one JSON object. Scripts and plugins call it instead of readingview.addrandview.token, which stay.tackroom view --stopstops the running view. A running view records its process inview.pidand a background one writesview.log. - New:
ui.view.addr,ui.view.idle_timeoutandui.view.open_browserintackroom.yamlortackroom.local.yaml(Settings).config validaterefuses a non-loopback address and an idle timeout that is not0or at least2m, so the page's request once a minute always keeps an open view up. - Changed: the web view and the Herdr panel lead with one answer, counted from the sync state, the machines and the crons: "2 failing, 1 needs attention", "All clear", or "Checking…" while one is still loading. Under it come what fails and what needs attention, each with its fix or its actions, and everything else on one line per kind; both group the same rows the same way, so a pending sync is one row and items in cooldown fold into everything else. The web view has a sidebar from 900px wide, and a top bar, a bottom dock and sheets for Sync, a job and its log on a phone; Skills, Roles and MCP & hooks are lists instead of matrices. Copy the mods from
herdr/tackroom/mods/again to get the panel's. See view.md. - Changed: a
uiblock intackroom.local.yamlreplaces only theuikeys it sets. Before, it replaced the whole shareduiblock, so a localui:withoutlinksdropped the shared links. - Changed: the Herdr panel's Web button, the Tern crons block's Web button and Rex's Open tackroom View on Crons run
tackroom view --json, so they start the view when none runs. Copy the Herdr mod, the Tern plugin andrex/tackroom.luaagain. With an older tackroom the Herdr button opens a running view as before, and the Tern and Rex ones say "Web needs a newer tackroom". - Changed:
--secure-cookieimplies--foreground, and a view that restarts itself after an upgrade serves in place with--foreground, so a view behindtailscale servekeeps running. A background view takesPATHfrom your login shell, so it finds the same harnesses as a terminal; the caller's own variables win. Undernohup, a foreground view no longer exits on SIGHUP. - Fixed: a view that restarts itself after an upgrade adds
--no-opento its arguments only when it is not there yet. Before, each restart added another one. - Known limit: for an outside skill source the cooldown counts from the commit's committer date, which whoever makes the commit sets, so a backdated commit is not held. npm and PyPI versions go by the registry's publish time. skills.md lists what else the cooldown does not cover.
- Known limit: the audit is a pattern check per line, not a parser or a sandbox, so a skill written to evade it can hide a command from it. One case: Python 3.12 and later let an f-string hold a nested string that uses the f-string's own delimiter, such as
f"""{'''"""'''}"""; the audit then loses track of where the f-string ends, so a line inside it that starts with#counts as a comment (skills.md). - Going back:
npm install -g tackroom@2.8.0installs the previous release; the Homebrew tap carries only the latest one. 2.8.0 loads atackroom.yamlandtackroom.lockwritten by 3.0, but it reads cooldown entries only under their old names,holds:andhold_until, and the memory scripts 3.0 removed do not come back.
To 2.8
- New: Devin (key
devin, detected bydevinonPATH), which covers Devin CLI and the Devin Local agent in Devin Desktop. It gets skills (read from~/.agents/skills, mirrored into~/.config/devin/skillsonly when the config root is elsewhere), stdio and remote MCP servers in~/.config/devin/mcp_config.json, and a root file at~/.config/devin/AGENTS.md. tackroom writes it no roles and no hooks. Devin loads the role files in~/.agents/agents/itself when that is the config root, with their tool names as written, and it loads Claude Code's hooks by default, so a copy from tackroom would run twice. Devin also reads~/.claude/CLAUDE.mdby default. With aninstructions:list intackroom.yaml, a machine with both loads it as a second rule unless you setread_config_from.claudetofalsein~/.config/devin/config.json; without one, Devin loads the root file once. Checked against Devin CLI 3000.12.57 without signing in. See Devin.
To 2.7.1
Nothing to migrate by hand: tackroom.yaml and tackroom.lock keep their formats.
-
Fixed:
tackroom setupon a config root that already hastackroom.yaml(a rerun, or a clone on another machine) no longer brings back starter files you deleted, such as a starter role, thetackroomskill orplugin.json. Starter files now go only into a config root with notackroom.yaml. A memory tier that is on, including onesetup --memory basicturns on, still gets its missing files undermemory/. A config root holding only atackroom.yamlyou wrote by hand no longer gets the starter roles and skill fromsetup. -
Fixed:
setupno longer rewritestackroom.yamlwhen its content does not change. Before, every run reformatted it (blank lines dropped), which left a change in a cloned config repository and could stopgit pull --ff-onlythere. -
Fixed:
sync, and the syncsetupruns, no longer add aholds:entry totackroom.lockfor an npm or PyPI version that was already older than 72 hours when first looked up. On a new machine every pinned Pi package or MCP server version was new, so its first sync changed the lock. Entries already in the lock are handled as before; one an earlier release wrote with ahold_untilin the past and noallowedcan be deleted and committed once every machine runs this release. -
Changed: Pi packages are looked up only on a machine where Pi is detected. A machine without Pi makes no registry lookup for them and records no hold; a decision already in the lock still applies there.
-
Changed: release binaries are built with Go 1.27. They were built with Go 1.25, which no longer gets security fixes:
govulncheckreports 14 standard-library vulnerabilities in the 2.7.0 binary and none in a 1.27.4 build. Building from source still needs Go 1.25 or newer. -
Fixed:
skill sources add --latestholds a head younger than 72 hours instead of pinning and syncing it. The lock records the hold and no pin, and nothing reaches an agent until the hold ends or you release it.addnow takes--allow-freshand--reason, asskill updatedoes. -
Fixed:
skill sources addruns the audit gate. A source with an unaccepted CRITICAL finding is neither pinned nor linked until you accept it withtackroom doctor audit accept. -
Fixed:
skill updateof one source no longer pins other sources that are held or blocked. -
Fixed: a release recorded for a held commit applies to that commit. A branch head that moved afterwards gets its own hold.
-
Fixed:
status,sync,sync --dry-runand the view list a hold or block created byskill update, with an override that works:tackroom skill update <name> --allow-fresh=<item>. -
Changed:
tackroom doctor auditlabels its first count as heuristic findings.
To 2.7
Nothing to migrate by hand: tackroom.yaml and tackroom.lock keep their formats.
- New:
tackroom setup --overlay NAMEcopiesoverlays/NAME.yaml, a completetackroom.local.yamlcommitted in the config repository, into place before the first sync, for machines of one kind such as cloud VMs:tackroom setup --from <repository url> --overlay cloud --no-cron. A differenttackroom.local.yamlis never overwritten; setup lists it as needing your attention and exits 1. An unknown name stops setup before it syncs anything. See Machine overlays. - New:
tackroom hosts fix [HOST...]runs the fixtackroom hostsnames (tackroom setup,pullorsyncon that machine, over SSH) and prints the machine's new row;--dry-runonly prints it. A fix that commits and pushes is still printed for you to run.tackroom hosts setup user@hostsets up another machine from this one withtackroom setup --from, and--installinstalls tackroom there first.hosts --jsonaddsfix_runnableto each host. - Changed: for a machine that has tackroom but no config,
tackroom hostsnow namestackroom hosts setup HOSTas the fix, not a baretackroom setupthere, which would start an unrelated config. - New: the Claude Code pane syncs and edits, as the Herdr panel does. When something waits, Sync shows the plan, with what it removes or overwrites, before it applies it, and applies only that plan. Harnesses, MCP servers and hooks have Turn on and Turn off, MCP servers and hooks add or remove a harness, and with more than one machine in
crons.hostsa Machines section shows each one's health. It needs tackroom 2.6 or newer as the plugin'stackroomprogram; with an older one the pane stays as before and says to update tackroom. Update the Claude Code plugin to get it.
To 2.6
Nothing to migrate by hand: tackroom.yaml and tackroom.lock keep their formats. One thing changes on its own: a hook you turned off in the config is now removed from the agents on the next sync (below).
- New: the Herdr panel syncs and edits. Overview has a Sync button that shows the plan, with what it removes or overwrites, before it applies it. Harnesses, MCP servers and hooks have Turn on and Turn off, and MCP servers and hooks add or remove an agent, as the web view's switches and cells do. Copy the two mods from
herdr/tackroom/mods/again to get it. With an older tackroom the panel stays read-only. - Fixed: the Herdr panel could stay on "Loading…" (the crons panel on "Collecting…") for good when Herdr created it hidden, as it does at start: its first loads never returned. They now start a moment later.
- New:
tackroom config set <section/name/field> <value>changes one field, as the web view's switches do, for exampletackroom config set mcp_servers/exa/enabled false. An entry defined intackroom.local.yamlis changed there. The path must name a field that section's entries have; a misspelled field, a shorter path ornullis refused. - New:
sync --dry-run --jsonaddsplan,destructiveandplan_digest, andtackroom sync --plan-digest DIGESTsyncs only while the plan is still the one with that digest andtackroom.yamlandtackroom.local.yamlare unchanged.destructivelists every removal (skills, roles, MCP servers, hooks, plugins, Pi packages, starter files) and every role overwrite. - Fixed: turning a hook off, or removing an agent from it, now removes it from that agent on the next sync. Before,
syncreported "up to date" and the command stayed registered untiltackroom hook remove. The native file is backed up first, sotackroom restore latestputs it back.statuslists such a hook ashooks stale, and--jsonasagents[].hooks.stale. This applies to hookstackroom.yamlstill declares; a registration of a hook you deleted from the config is left alone, as before. - Changed: the web view's Sync now also asks you to tick hook and Pi package removals.
To 2.5.1
Nothing to migrate by hand: tackroom.yaml and tackroom.lock keep their formats.
- Fixed: a role with
tools: []was written with notoolskey, so Claude Code, GitHub Copilot CLI, Gemini CLI, Kimi Code, OMP and Pi gave it every tool. They now get no tools, and the next sync, including the periodictackroom pull, rewrites those copies.tools: ""now also means no tools. Codex, Cursor, Factory Droid, OpenCode, Qwen Code and Grok Build cannot express it and keep the harness default; see Tools. - The Herdr panel moved to
herdr/tackroom/, a package Herdr's mod gallery can list, with a recipe that adds the button and the panel to the layout you use. Thetackroomlayout inherdr/layouts/is gone; if you copied it, it keeps working. To update the panel, copy the two mods fromherdr/tackroom/mods/, or paste the gallery line in herdr.md to your agent. Where the notes below say to copyherdr/mods/tackroom, copyherdr/tackroom/mods/tackroominstead.
To 2.5
tackroom.yaml and tackroom.lock keep their formats. Scripts that run tackroom setup --yes keep working.
tackroom setupno longer asks anything. It does whatsetup --yesdid: imports everything your agents have (copies; a differing native file is backed up before it is replaced), installs the periodic job, and ends with a short summary instead of the full sync report. Unlike--yes, it initializes git only on a first setup (notackroom.yamlyet), so a config you kept out of git stays that way; it never changes the memory tier of an existingtackroom.yamlwithout--memory(basicon a new one); and it exits 1 whenever the summary lists something that needs you, possibly after the sync, commit and job are already done. To review imports and confirm each step as before, runtackroom setup --review;--verboseprints the full report.--yesis still accepted and does nothing, so scripts keep working.- New:
tackroom setup --from <git url>sets up another machine in one command. It clones your config repository into the config root, or pulls it when it is already a clone of that URL, then sets up from it. A config root with other content is refused and left as it is. See Multi-machine. - Changed: a native role is shared, and later replaced, only when the role tackroom writes keeps every field and the instructions of the native file. A role with a field tackroom cannot write (such as
permissionModeorsandbox_mode), with different copies in different agents, or that is a link to a file elsewhere stays each agent's own, and setup adds no starter role of that name, so a fresh setup ends synced. Where the config already has a role of that name, the native file is left in place and listed with how to fix it, and only that file: the rest of that agent still syncs (before, one such file kept the whole agent from syncing).sync --replace-conflictsreplaces the roles that pass this check, which it did not do before. A role imported without frontmatter no longer gets an invented model, effort or a description holding a machine path. - If 2.4 left role conflicts on a machine (
statusorsynclisted a role as "exists but is not tackroom-managed", and that agent got nothing), the first sync after upgrading, including the unattended periodictackroom pull, now syncs that agent. It backs up and links that agent's skill folders andCLAUDE.md-style instructions files that are identical to the shared copy, and writes the shared roles into it, including roles a 2.4 setup imported from another agent without the fields tackroom cannot write (such assandbox_modeorpermissionMode) or, for a Codex role with"""instructions, with the raw TOML as its instructions. The conflicting role files themselves stay in place. Right after upgrading, before the next periodic run, runtackroom sync --dry-runto see what it would change. To keep a role as one agent's own, rename that agent's file so its name differs from the shared role's. To stop sharing a role, delete~/.agents/agents/<name>.mdand remove the copies tackroom already wrote into the other agents' folders (they start with aGenerated by tackroomline); sync does not remove them. - Fixed: importing a Codex role whose
developer_instructionsis a"""multi-line string no longer copies the raw TOML into the instructions. - Fixed: rerunning
setupno longer removes the memory hooks from each agent's config only for the sync to add them back. - Changed:
sync(and sosetup) backs up a native file or skill folder that is identical to the shared copy before linking it, as it already did for different ones, sotackroom restore latestputs back everything a run replaced. - Fixed: with many agents, the web view's Skills, Roles and MCP & hooks tables showed no names. The name column now keeps its width and the table scrolls sideways inside its card.
setuplists instructions files it merged from several agents intoAGENTS.mdas needing your attention, andsetup --dry-runnow says what the run would do: whose copy it keeps and which roles stay each agent's own.
To 2.4
Nothing to migrate by hand: tackroom.yaml and tackroom.lock keep their formats. If your periodic sync job dates from before 2.0, run tackroom cron once (below).
- New:
tackroom hostsshows tackroom on every machine incrons.hosts: its version, whether it is set up and synced, and its config commit against this machine's, with the command that fixes what is wrong. With more than one host, the view's Overview and the Herdr panel's Overview show the same as a Machines block. Copyherdr/mods/tackroomagain to get it in the panel. See commands.md. - Fixed:
tackroom setupstopped withconfig hook memory-session-start targets unknown agent "claude"whentackroom.local.yamllisted an agent, for example one turned off on that machine. It also stopped on any machine with Grok Build installed, reading~/.grok/config.tomlas JSON. Both now set up; a harness config tackroom cannot read is reported as a warning and its MCP servers are left out of the import. - If you first installed the periodic sync job with a tackroom before 2.0, run
tackroom crononce. That job sources~/.profilefirst, and when the file is missing (common with zsh) or fails,/bin/shstops before tackroom runs: the job never synced and its log stayed empty.tackroom statusandtackroom doctornow name this case. - Deprecated:
tackroom tui. It still runs, with a notice, and will be removed in 3.0. Usetackroom view(on a desktop, a phone or in a side panel) or the Herdr panel; in a terminal,tackroom status,tackroom cron collect --tableandtackroom doctorprint the same facts.
To 2.3
Nothing to migrate by hand: tackroom.yaml and tackroom.lock keep their formats.
tackroom viewworks on a phone and in a narrow side panel: larger text and tap targets, matrices that stack into rows, a web app manifest so it can go on a home screen, and a page that asks for the token when a phone opens it without one. See On a phone.- The view's Overview lists outside sources as pinned, held or blocked, with the reason and the command that overrides it. The view now applies the freshness hold and the audit gate the way
tackroom statusdoes, so it no longer offers a sync for a skill that sync would skip. - New:
tackroom config inventoryprints the view's inventory as JSON. - The Herdr panel is now a
tackroompanel with Overview, Skills, Roles, MCP & hooks and Crons tabs. Copyherdr/mods/tackroomand thetackroomlayout again to get it; the oldcrons.svgicon is replaced bytackroom.svg. See terminals.md.
To 2.2
Nothing to migrate by hand: tackroom.yaml and tackroom.lock keep their formats. One thing moves on its own, for Codex users with plugin sources (below).
- New: Codex settings. Keys under
settings:on thecodexagent are written into~/.codex/config.toml; every other key in that file is kept. See Per-harness settings. - New:
tackroom cron add,cron editandcron removefor jobs tackroom owns on this machine, with the same actions in the web view and the Herdr panel. See crons.md. tackroom viewuses the Graphite theme and now has a light theme that follows the OS setting.
Codex now installs an agent-plugins-spec source with mcp: true as a native plugin, through codex plugin. tackroom.yaml and tackroom.lock keep their formats. See Codex plugins.
- If a source with
mcp: truealready synced into Codex, the nexttackroom syncmoves it. It removes that source's skill links from~/.codex/skillsand the[mcp_servers]rows tackroom wrote for it, backs up~/.codex/config.toml, and installs<name>@tackroomwithcodex plugin add. Codex then also gets the plugin'sstreamable-httpservers. - A source that sets
skills:,skill_dir:orskill_dirs:, that sets nomcp: true, or that lists Codex inexclude_agentsor leaves it out ofmcp_agentskeeps its links and rows. codexmust be onPATH. A failedcodex plugincall is reported for the Codex plugin surface only; the other surfaces still apply.- To keep one source out of Codex, set
enabled = falseunder[plugins."<name>@tackroom"]in~/.codex/config.toml, or addcodexto itsexclude_agents.
To 2.1
Nothing to migrate: tackroom.yaml and tackroom.lock keep their formats.
- A download piped into a shell (
curl ... | sh,wget ... | bash,base64 -d ... | sh) in an external skill is now a CRITICAL audit finding. A new or changed pin with that pattern is skipped until you accept it withtackroom doctor audit accept. Pins already in the lock keep syncing, and your own skills are reported, never blocked. - The Hermes memory bridge is gone. The next
tackroom syncdeletesmemory/hooks/sync.sh,sync-memory-to-vault.sh,sync-vault-to-memory.shandmemory/lib/sync.pyfrom your config root if you never edited them. Edited copies are reported and left alone.tackroom setupremoves the old sync hook commands from native configs. tackroom doctorno longer fails because an external skill is held or blocked. It passes, counts them and says what to do next.- Install with Homebrew or npm. The install script is no longer offered.
- New:
tackroom tui, a read-only terminal view. It was removed in 3.0.
To 2.0
tackroom 2.0 removes the Hermes and OpenClaw harnesses (with their hooks, MCP adapters, setup defaults and doctor checks), the hermes and openbot cron sources, the tackroom skill promote command, the macOS app, the HarnessKit coexistence notes, and the legacy tackroom view --port/--host/--no-token/--name flags.
tackroom.lockgains two keys:accepted:(audit decisions) andholds:(freshness holds). An older tackroom that rewrites the shared lock drops both, so upgrade every machine that shares the config root before syncing.setupnow installs the periodic sync job (tackroom pull) by default, every 15 minutes. It was opt-in at 30 minutes.--no-cronskips it.- If you use Hermes or OpenClaw, tackroom leaves their native files in place and stops managing them. Delete them yourself if you no longer need them.
The claude key
In tackroom.yaml and --agents, Claude Code is claude, since 1.2.0. The former name claude-code is still accepted. A tackroom older than 1.2.0 does not know claude, so upgrade every machine that shares the config.
From dotagents
tackroom 1.0 is the dotagents CLI under a new name. An existing config root needs its files renamed once; tackroom refuses to run while dotagents.yaml, dotagents.local.yaml or .dotagents-starter.json still exist without their new names.
dotagents cron --remove # only if you installed the cron entry
cd ~/.agents
git mv dotagents.yaml tackroom.yaml
git mv dotagents.lock tackroom.lock
git mv .dotagents-starter.json .tackroom-starter.json
mv dotagents.local.yaml tackroom.local.yaml # only if you have one
Then:
- In
.gitignore, replacedotagents.local.yamlwithtackroom.local.yamlso machine-local overrides stay out of git. - Move
skills/dotagentstoskills/tackroom. If you never edited it, copy theskills/tackroomfolder from the tackroom repository over it; otherwise replacedotagentswithtackroominside it. - Install tackroom, run
tackroom sync, thentackroom cronif you use it, and remove the olddotagentsbinary.
Role files that dotagents rendered into harness folders are adopted and rewritten on the first sync.