superpowers-plus
CLAUDE.md8 starsChanged 6 months agoMITView on GitHub
See AGENTS.md for all AI guidance. All infrastructure code, tooling, gates, hooks, and workflows in this repository are designed and optimized for AI coding agents, not humans. Humans interact with this repo only to approve and monitor; agents execute. Consequences: - Do not add interactive prompts, manual checkpoints, or pauses for human confirmation to any tool or workflow. Every step must be executable autonomously from start to finish. - Do not add human-legibility conveniences (colorized spinners, interactive menus, PAGER output)…
In this repository129 other files it gives its agents.
- AGENTS.mdAGENTS.md
- guidance/AGENTS.mdAGENTS.md
- guidance/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- blast-radius-checkSkill
- brainstormingSkill
- branch-flow-gateSkill
- branch-sync-gateSkill
- codebase-reconSkill
- codeowners-drift-auditSkill
- code-review-batterySkill
- cognitive-complexity-refactoringSkill
- debateSkill
- debug-conductorSkill
- dispatching-parallel-agentsSkill
- domain-buildSkill
- evidence-adjudicatorSkill
- executing-plansSkill
- external-cli-auditSkill
- feature-developmentSkill
- field-rename-verificationSkill
- finishing-a-development-branchSkill
- git-branch-conventionsSkill
- gitlab-cliSkill
- hotfix-charterSkill
- implementation-trackerSkill
- incident-revert-reviewSkill
- infra-config-investigatorSkill
- investigation-stateSkill
- kernel-splitSkill
- llm-behavior-investigatorSkill
- llm-skill-reviewSkill
- merge-authorization-gateSkill
- micro-harsh-reviewSkill
- output-verificationSkill
- pre-commit-gateSkill
- progressive-code-review-gateSkill
- progressive-harsh-reviewSkill
- providing-code-reviewSkill
- pr-triage-gateSkill
- push-authorization-gateSkill
- receiving-code-reviewSkill
- reproduction-experiment-investigatorSkill
- requesting-code-reviewSkill
- requirements-validation-pmSkill
- requirements-validationSkill
- scope-tripwireSkill
- session-handoffSkill
- skills-hierarchy-tuningSkill
- sp-bughuntSkill
- state-consistency-investigatorSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- timeline-trace-investigatorSkill
- token-estimationSkill
- unified-commit-gateSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- The first 60 shown.
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
All infrastructure code, tooling, gates, hooks, and workflows in this repository are designed and optimized for AI coding agents, not …
- Distinctive: line 28
If you find yourself writing a step that says "then the human should...", stop — that step belongs in the tool itself or the tool is …
≈ “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
Claude Code Instructions
See AGENTS.md for all AI guidance.
Agent-first design principle (non-negotiable)
All infrastructure code, tooling, gates, hooks, and workflows in this repository are designed and optimized for AI coding agents, not humans. Humans interact with this repo only to approve and monitor; agents execute.
Consequences:
- Do not add interactive prompts, manual checkpoints, or pauses for human confirmation to any tool or workflow. Every step must be executable autonomously from start to finish.
- Do not add human-legibility conveniences (colorized spinners, interactive menus, PAGER output) that break non-interactive shells or pipe consumption.
- When a tool or workflow requires a decision, encode the decision logic directly in the script rather than delegating to a human prompt. If the decision cannot be automated, the tool should fail clearly and exit non-zero with a machine-readable error, not wait.
- Quality gates exist to run autonomously. A gate that requires human review before it can be checked does not belong here.
- ship.sh is the canonical end-to-end agent workflow. Any friction it exposes is a bug in the infrastructure, not a feature.
If you find yourself writing a step that says "then the human should...", stop — that step belongs in the tool itself or the tool is incomplete.
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.