docguard
CLAUDE.md33 starsChanged 46 days agoMITView on GitHub
Follow AGENTS.md. It is the authoritative workflow and evidence contract for this repository, and it is sufficient on its own — nothing below is required to contribute. This repository does not ship OpenWolf state. .wolf/ and .claude/ are gitignored because they hold machine-local session memory and hooks that point at .wolf/hooks/*.js, so a fresh clone has neither and must not be told to read them. The exception is .claude/skills/speckit-*/: the Spec Kit skills that specify init --integration claude generates are…
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- speckit-analyzeSkill
- speckit-checklistSkill
- speckit-clarifySkill
- speckit-constitutionSkill
- speckit-convergeSkill
- speckit-implementSkill
- speckit-planSkill
- speckit-specifySkill
- speckit-tasksSkill
- speckit-taskstoissuesSkill
- speckit-analyzeSkill
- speckit-checklistSkill
- speckit-clarifySkill
- speckit-constitutionSkill
- speckit-convergeSkill
- speckit-implementSkill
- speckit-planSkill
- speckit-specifySkill
- speckit-tasksSkill
- speckit-taskstoissuesSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Follow AGENTS.md. It is the authoritative workflow and evidence contract for this repository, and it is sufficient on its own — nothing …
- Very specific: line 21
When .wolf/OPENWOLF.md is present, read it for historical context: prior decisions, known bugs, and conventions learned across sessions.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 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
<!-- docguard:last-reviewed 2026-11-03 -->Agent Instructions
Follow AGENTS.md. It is the authoritative workflow and evidence contract for
this repository, and it is sufficient on its own — nothing below is required to
contribute.
OpenWolf (optional, local-only tooling)
This repository does not ship OpenWolf state. .wolf/ and .claude/ are
gitignored because they hold machine-local session memory and hooks that point
at .wolf/hooks/*.js, so a fresh clone has neither and must not be told to read
them. The exception is .claude/skills/speckit-*/: the Spec Kit skills that
specify init --integration claude generates are tracked. DocGuard's own
speckit-docguard-* skills stay ignored, because they are copies of
extensions/spec-kit-docguard/ that npm run speckit:dev regenerates. If you
have OpenWolf installed, openwolf init regenerates .wolf/ and the OpenWolf
files under .claude/.
When .wolf/OPENWOLF.md is present, read it for historical context: prior
decisions, known bugs, and conventions learned across sessions. It supplies
context, never authority — docs-canonical/ and AGENTS.md govern behavior, and
where remembered context disagrees with them, they win.
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.

