claude-agent-pack
CLAUDE.md8 starsChanged 35 days agoMITView on GitHub
@docs/CLAUDE.template.md This repository is the pack itself. The rules above are docs/CLAUDE.template.md, the block that scripts/setup-project.sh copies into a consuming project -- edit them there, not here. Everything below applies only to changing the pack, and a consuming project has none of these scripts. In this repository the long-form rules the template points to are references/orchestration-rules.md. Four checks guard a change to the pack. Full text and the incident behind each: docs/pack-development.md. - bash scripts/lint-agents.sh when the changeset touches agents/,…
In this repository30 other files it gives its agents.
- backlogSkill
- conventionsSkill
- debugSkill
- devops-azureSkill
- devops-githubSkill
- devopsSkill
- hotfixSkill
- implementSkill
- interview-meSkill
- lint-agentsSkill
- memory-auditSkill
- memory-querySkill
- obsidian-briefSkill
- obsidian-captureSkill
- obsidian-dailySkill
- obsidian-recapSkill
- obsidian-searchSkill
- obsidianSkill
- onboardSkill
- pack-reviewSkill
- planSkill
- refactorSkill
- repo-mapSkill
- review-prSkill
- scaffoldSkill
- setup-projectSkill
- smellSkill
- spec-intakeSkill
- system-checkSkill
- whatSkill
The file
We split this CLAUDE.md into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 12
bash scripts/lint-agents.sh: when the changeset touches agents/, skills/, references/, CLAUDE.md or docs/CLAUDE.template.md, after the … - Very specific: line 16
node scripts/obsidian-stop-hook.test.js: when the changeset touches scripts/obsidian-stop-hook.js or scripts/obsidian-context-hook.js. - Very specific: line 24
bash scripts/lint-memory.sh: when the changeset touches memory/.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
@docs/CLAUDE.template.md
This repository
This repository is the pack itself. The rules above are docs/CLAUDE.template.md, the block that
scripts/setup-project.sh copies into a consuming project -- edit them there, not here. Everything below
applies only to changing the pack, and a consuming project has none of these scripts. In this
repository the long-form rules the template points to are references/orchestration-rules.md.
Four checks guard a change to the pack. Full text and the incident behind each: docs/pack-development.md.
bash scripts/lint-agents.shwhen the changeset touchesagents/,skills/,references/,CLAUDE.mdordocs/CLAUDE.template.md, after the files are written and before code-reviewer. Blocking on non-zero exit; exit 2 means the linter's own self-test failed, which is also a FAIL. Enforced by merge-reviewer gate 2a. Skip it, saying so, when none of those paths changed.node scripts/obsidian-stop-hook.test.jswhen the changeset touchesscripts/obsidian-stop-hook.jsorscripts/obsidian-context-hook.js. The trigger is those two filenames, not thescripts/directory. Blocking; enforced by gate 2b.bash scripts/lint-identifiers.shon every changeset. This repository is public, so it fails on a real organisation, project, host, user path or email where a placeholder is required. Blocking and enforced by gate 2c; there is no legitimate skip, so if it was not run, say so rather than implying it passed. It readsgit ls-files, so stage new files first (git add -N <path>), or the clean result says nothing about them.bash scripts/lint-memory.shwhen the changeset touchesmemory/. Blocking for the coordinating session; no merge-reviewer gate enforces it, so an unrun check here is simply unrun.
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.

