wiki
Skill0 starsChanged 19 days agoApache-2.0View on GitHub
Keep the Agent Co-op wiki in step with changes a person can see or do. Use when a change touches commands, chat phrases, install, the board, settings, permissions, safety, agents, errors, or troubleshooting.
43 other projects use a version of this.
Adopted by
Most recently taken up by
- tboome33/obsidian-mcp-routertheir own version, first seen Nov 15, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 9, 2026
- skillberry-ai/cap-evolvetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- SethGammon/Citadeltheir own version, first seen Nov 4, 2026
- Lixiuxiu559/AgentForgetheir own version, first seen Nov 1, 2026
Used with
Projects with it also use ai-slop-cleaner, ralplan and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Jurel89Skillai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Also in 4 projects that use this
ibahgatSkillralplan
Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.
Also in 4 projects that use this
Yeachan-HeoSkillultragoal
Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
Also in 3 projects that use this
woosikkimSkilldeepinit
Generate hierarchical AGENTS.md codebase maps for agent context
Also in 3 projects that use this
ibahgatSkillhud
Control omi visual HUD profile and keep status output readable in normal, compact, or hidden mode.
Also in 3 projects that use this
klauswgSkilldeep-interview
在明确批准执行之前,通过数学化歧义门控进行苏格拉底式深度访谈
Also in 4 projects that use this
Other versions43 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 43
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- AgriciDaniel/claude-obsidian★ 16ksame name
- SethGammon/Citadel★ 927same name
- saltmd/salt.md★ 178same name
- ekadetov/llm-wiki★ 108same name
- saksham10arora-dotcom/everything-claude-codex★ 96same name
- skillberry-ai/cap-evolve★ 70same name
- WALKERKILLER/Look-Tongji-Notes★ 53same name
33 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- compatibilitySkill
- agent-coopSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 37 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Update it when a change touches anything a person sees or does:
- Distinctive: line 53
Add a row when you add a page.
- Very specific: line 59
Check each command, flag, path, phrase, exit code, and message against the source.
- Distinctive: line 61
If something is not confirmed, say that, and say what to check.
- Very specific: line 69
Do not edit Chat-phrases.md or Command-reference.md by hand.
- Distinctive: line 79
Do this only after the main pull request is merged, so the wiki never describes work that did not land.
- Very specific: line 83
Add a line Wiki: <pages changed>, or No wiki change: <reason>.
- Distinctive: line 89
Every change must work on Windows, macOS, and Linux.
“Common” is measured: kept by at least 6 in 10 of the 37 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Wiki
The guide people read is the GitHub wiki, in the agent-coop.wiki folder next to this repo. Its branch is master. The main repo stays the source for anything an agent follows.
1. Decide if the wiki needs an update
Update it when a change touches anything a person sees or does:
- commands, flags, or output
- chat phrases
- skill or rule text
- install, update, or uninstall steps
- board files
- settings
- permissions
- safety rules
- supported agents
- error messages
- the troubleshooting cases
2. Find the pages
| Source | Wiki pages |
src/agentcoop/cli.py | Command reference, Exit codes |
src/agentcoop/data/phrases.json, src/agentcoop/templates/ | Chat phrases |
src/agentcoop/watch.py | Keeping agents checking, Exit codes |
src/agentcoop/update.py, docs/agent-update.md, docs/update.md | Updating, Install a specific version |
src/agentcoop/updatecheck.py | Updating, STATUS.md and the viewer |
src/agentcoop/migrate.py, COMPATIBILITY.md | Compatibility, Updating |
src/agentcoop/uninstall.py, docs/agent-uninstall.md | Uninstall |
src/agentcoop/install.py, docs/agent-setup.md | Install on Windows, Install on macOS, Install on Linux, Your first project |
src/agentcoop/confirm.py | Permissions |
src/agentcoop/safety.py, docs/security.md | Safety and privacy |
src/agentcoop/projects.py, src/agentcoop/schema.py | Projects, Settings files |
src/agentcoop/context.py, src/agentcoop/progress.py | Context and progress, Done means verified |
src/agentcoop/taskreview.py, src/agentcoop/donereport.py | Done means verified, Roles, Working with several helpers |
src/agentcoop/rounds.py, docs/schedule.md | Background runs, Keeping agents checking |
src/agentcoop/ui.py, src/agentcoop/statusfile.py | STATUS.md and the viewer |
src/agentcoop/tools.py, AGENTS-SUPPORT.md, docs/tools/ | Cursor, Claude Code, Codex and the ChatGPT desktop app, Gemini CLI, Local models, Planned agents, Claude desktop app |
src/agentcoop/desktop.py, src/agentcoop/outbox.py | Claude desktop app, Troubleshooting |
src/agentcoop/paths.py, SPEC.md | How it works, Board layout, Message format |
src/agentcoop/gitshim.py, src/agentcoop/worktree.py | Background runs |
src/agentcoop/session.py | Troubleshooting, Environment variables |
src/agentcoop/runner.py, docs/runner.md | Local models |
docs/troubleshooting.md | Troubleshooting |
Add a row when you add a page.
3. Edit them
Write for a person. Lead with what to say in chat. Put terminal commands in a details block. Sentence case. No em dashes or en dashes. Start each page with one or two sentences. Mark a new feature with Added in <version>, using the version the change will ship in. Do not write that a version is the latest. Link to the releases page.
Check each command, flag, path, phrase, exit code, and message against the source. Run command examples on a temporary board (AGENTCOOP_BOARD and HOME set to a temp folder) and paste the real output, trimmed.
If something is not confirmed, say that, and say what to check.
4. Regenerate
python3 scripts/gen_wiki.py --wiki ../agent-coop.wikiDo not edit Chat-phrases.md or Command-reference.md by hand.
5. Check links
python3 scripts/check_wiki_links.py ../agent-coop.wiki6. Commit and push the wiki
Do this only after the main pull request is merged, so the wiki never describes work that did not land. The commit message names that pull request number.
7. Say it in the pull request
Add a line Wiki: <pages changed>, or No wiki change: <reason>.
8. Never put on the wiki
Secrets, internal hostnames or IP addresses, personal project details, or a guess presented as a fact.
Every change must work on Windows, macOS, and Linux. Test on all three in CI, and list any skips in the PR.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

