adlc-toolkit
CLAUDE.md174 starsChanged 17 days agoMITView on GitHub
@../AGENTS.md - This file lives here, not at the repo root, because the repo is also the plugin: a root CLAUDE.md fails claude plugin validate .claude-plugin/plugin.json --strict. adlc harness render --harness claude writes one when none exists, so delete what it writes here; the manifest-parity lint refuses it. - .claude/settings.json is rendered by adlc harness render --harness claude from the ADLC toolkit's templates/permissions.yml and templates/hooks.yml. Commit it: it is shared by the team. Personal overrides go in .claude/settings.local.json. - Claude…
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Commit it: it is shared by the team.
≈ “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
@../AGENTS.md
Claude Code
- This file lives here, not at the repo root, because the repo is also the plugin:
a root
CLAUDE.mdfailsclaude plugin validate .claude-plugin/plugin.json --strict.adlc harness render --harness claudewrites one when none exists, so delete what it writes here; themanifest-paritylint refuses it. .claude/settings.jsonis rendered byadlc harness render --harness claudefrom the ADLC toolkit'stemplates/permissions.ymlandtemplates/hooks.yml. Commit it: it is shared by the team. Personal overrides go in.claude/settings.local.json.- Claude Code applies the committed allowlist only in a trusted workspace: accept the trust dialog once per checkout.
- Its deny tier is Claude Code's
asklist, so a person confirms each one-way move in session. The allowlist is a convenience, not a safety gate.
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.

