text-flags
CLAUDE.md0 starsChanged 38 days agoMITView on GitHub
In this repositoryOne other file it gives its agents.
- textSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Every rule in -p traces to Anthropic's prompting docs, the best practices page and the Opus 5.5 and Sonnet 5.5 pages.
- Very specific: line 19
Add the changes to CHANGELOG.md.
≈ “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
text-flags
Rules
- A single-plugin repo. Plugin and marketplace sit at the root (
source: "./"), the marketplace carries the plugin's name, and the skill lives inskills/. - The plugin is named
text-flagsand its skill staystext. A generic plugin name triggers a review hold in the plugin directory, and/textkeeps working. -lnever writes in a consulting register.- Every rule in
-ptraces to Anthropic's prompting docs, the best practices page and the Opus 5.5 and Sonnet 5.5 pages. Add none without such a source.
Checks
claude plugin validate --strict .checks the marketplace andclaude plugin validate --strict .claude-plugin/plugin.jsonthe plugin. Fix every warning.npx skills add . --listconfirms that other agents find the skill.- The Validate workflow runs the same three on every push to
mainand every pull request.
Release
- Bump
versionin.claude-plugin/plugin.json, or installed copies never update. - Add the changes to
CHANGELOG.md. - Push and wait for the Validate workflow to pass.
- Tag
vX.Y.Zand create a GitHub release.
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.

