agent-superpowers / rules
Cursor rule1 starsChanged 15 days agoMITView on GitHub
Disciplined autonomous engineering framework: TDD bug reproduction, git worktree sandboxing, adversarial fuzzing, and AST context compression.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,144 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository36 other files it gives its agents.
- arch-archaeologistSkill
- graphifySkill
- hindsight-architectSkill
- ghost-runnerSkill
- figma-designerSkill
- frontend-sentinelSkill
- hallmarkSkill
- landing-page-designSkill
- review-frontend-productionSkill
- hindsight-coding-agentSkill
- memory-nexusSkill
- video-shotcraftSkill
- caveman-compressSkill
- cavemanSkill
- prompt-optimizerSkill
- token-squeezerSkill
- using-superpowersSkill
- api-synthesizerSkill
- blackbox-clonerSkill
- agent-reachSkill
- firecrawl-buildSkill
- firecrawl-build-interactSkill
- firecrawl-build-onboardingSkill
- firecrawl-build-scrapeSkill
- firecrawl-build-searchSkill
- scrapling-officialSkill
- adversarial-duelistSkill
- testsprite-ciSkill
- testsprite-verifySkill
- caveman-commitSkill
- feature-brainstormerSkill
- git-worktree-sandboxSkill
- ponytail-auditSkill
- ponytail-debtSkill
- ponytail-reviewSkill
- ponytailSkill
The file
We split this agent-superpowers.mdc into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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 13
Never guess or speculate on bug fixes without evidence.
- Distinctive: line 15
If deterministic reproduction is not possible, document the evidence and add a regression test for the affected invariant.
- Distinctive: line 20
Before creating the worktree, inspect git status and preserve or explicitly carry all uncommitted and untracked changes.
- Distinctive: line 25
Test explicitly for null-bytes, zero-divisions, payload boundary limits, and unexpected types before committing.
- Distinctive: line 28
When loading large multi-file architectures into active context, compress AST structures to preserve token budget.
- Distinctive: line 32
If user requirements are ambiguous, clarify boundary conditions, edge cases, and scope constraints before implementation.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
--- description: "Disciplined autonomous engineering framework: TDD bug reproduction, git worktree sandboxing, adversarial fuzzing, and AST context compression." globs: **/* alwaysApply: false --- # Agent Superpowers: Autonomous Engineering System A disciplined, deterministic engineering protocol enforcing rigour before code execution. ## Core Directives 1. **Bug Reproduction First (Ghost Runner)** - Never guess or speculate on bug fixes without evidence. - Author a minimal reproduction test (MRE) that fails on the current codebase when deterministic reproduction is possible. - If deterministic reproduction is not possible, document the evidence and add a regression test for the affected invariant. - Apply the minimal code fix and confirm the test PASSES (GREEN). 2. **Branch Isolation (Git Worktree Sandbox)** - For complex, multi-file refactoring or experimental tasks, isolate work in an ephemeral git worktree branch. - Before creating the worktree, inspect `git status` and preserve or explicitly carry all uncommitted and untracked changes. - Protect the main working tree from unverified state corruption. 3. **Adversarial Verification (Adversarial Duelist)** - Subject critical business logic and input boundaries to red-team fuzzing. - Test explicitly for null-bytes, zero-divisions, payload boundary limits, and unexpected types before committing. 4. **Context Hygiene (Token Squeezer)** - When loading large multi-file architectures into active context, compress AST structures to preserve token budget. - Strip internal implementations while preserving typed function signatures, exports, and docstrings. 5. **Clarify Before Code (Feature Brainstormer)** - If user requirements are ambiguous, clarify boundary conditions, edge cases, and scope constraints before implementation.
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.