We split this AGENTS.md into the rules it gives an agent

8 rules. About 0 are common, 2 are distinctive, and 6 are very specific to this project.

• ≈0

  Common · estimate

  Many files like this have a rule of this kind.

• ≈2

  Distinctive · estimate

  This author's own choices. Worth a look.

• 6

  Very specific

  Tied to their project's names, files or tools. Probably skip.

• Common
• Distinctive
• Very specific

1. Very specific:

   Read WRITING-GUIDE.md before authoring or editing a skill or agent.

   line 5
2. Distinctive:

   Write skill files and other instructions for reliable AI execution: make each instruction clear, coherent, explicit, and actionable without …

   line 6
3. Distinctive:

   Before reporting an instruction-text edit complete, invoke these skills (the lenses) in order:

   line 7
4. Very specific:

   When updating a shared schema in references/, sync all consumers per WRITING-GUIDE.md.

   line 15
5. Very specific:

   When a skill/agent/command is added, removed, or renamed, sync both the README.md list and .claude-plugin/plugin.json's skills array to …

   line 16
6. Very specific:

   When a skill/agent/command's purpose changes, update its README.md description.

   line 17
7. Very specific:

   Run scripts/validate-skills.sh once when I ask to commit.

   line 21
8. Very specific:

   After a commit that adds or updates a skill/agent/command, offer to install the changed ones based on the instructions below:

   line 22

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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.