optimus-claude
CLAUDE.md75 starsChanged 2 months agoMITView on GitHub
GitHub: https://github.com/oprogramadorreal/optimus-claude A Claude Code plugin whose source is markdown: SKILL.md files are instructions a model executes, not documentation about code that runs. Edit them as prompts, not as prose. Test command: bash scripts/validate.sh && bash scripts/test-hooks.sh && python -m pytest test/ Load the doc that matches the change — not all of them.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brainstormSkill
- code-reviewSkill
- commitSkill
- deepSkill
- dreamSkill
- gauntletSkill
- handoffSkill
- how-to-runSkill
- initSkill
- jiraSkill
- paper-initSkill
- permissionsSkill
- promptSkill
- prSkill
- refactorSkill
- resetSkill
- tddSkill
- unit-testSkill
- worktreeSkill
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 23
Never leave a ref field in marketplace.json on the master branch
- Very specific: line 24
Every PR to master bumps the version in .claude-plugin/plugin.json and .codex-plugin/plugin.json and updates the README.md version badge to …
- Very specific: line 25
Only /optimus:init writes .claude/.optimus-version in user projects — other skills that install template files must NOT update this file …
≈ “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
optimus-claude
GitHub: https://github.com/oprogramadorreal/optimus-claude
A Claude Code plugin whose source is markdown: SKILL.md files are instructions a model executes, not documentation about code that runs. Edit them as prompts, not as prose.
Test command: bash scripts/validate.sh && bash scripts/test-hooks.sh && python -m pytest test/
Where to look
Load the doc that matches the change — not all of them.
| Changing | Read first |
A skill, agent, or shared reference (skills/, agents/, references/) | .claude/docs/skill-writing-guidelines.md |
Scripts or hooks (scripts/, hooks/) | .claude/docs/coding-guidelines.md |
Tests, or anything under scripts/harness_common/ | .claude/docs/testing.md |
| Deep-loop invariants, harness JSON contracts, agent and reference tiers, Claude/Codex host wiring | .claude/docs/architecture.md |
| Contribution workflow, skill anatomy, feature-branch testing, version bumping | CONTRIBUTING.md |
Key rules
- Never leave a
reffield inmarketplace.jsonon the master branch - Every PR to master bumps the version in
.claude-plugin/plugin.jsonand.codex-plugin/plugin.jsonand updates theREADME.mdversion badge to match —validate.shfails the PR otherwise - Only
/optimus:initwrites.claude/.optimus-versionin user projects — other skills that install template files must NOT update this file (it tracks init's full template audit, not individual file freshness)
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.