gates
Skill16 starsChanged 17 days agoMITView on GitHub
What each gate level (strict, standard, light) switches on and off, and what never relaxes at any level. Use when setup asks the founder to choose a level, when the level changes, and whenever an agent is unsure whether a step is required.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- akshaypimprikar/pragmatheir own version, first seen Nov 11, 2026
- FiredMosquito831/my-writing-companiontheir own version, first seen Nov 1, 2026
- CorvusWing/CorvusWingtheir own version, first seen Oct 25, 2026
- harshanandak/forge-legacytheir own version, first seen Oct 17, 2026
- zajca/pohunektheir own version, first seen Oct 13, 2026
- The-40-Thieves/obsidian-tctheir own version, first seen Oct 8, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- Nebulock-Inc/agentic-threat-hunting-framework★ 420same name
- The-40-Thieves/obsidian-tc★ 13same name
- zajca/pohunek★ 9same name
- akshaypimprikar/pragma★ 4same name
- harshanandak/forge-legacy★ 4same name
- FiredMosquito831/my-writing-companion★ 2same name
- CorvusWing/CorvusWing★ 1same name
- Leostruka/devin-bundle★ 0same name
- ninoverse/claude-mit-go-template★ 0same name
- ninoverse/claude-mit-rust-agent-template★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository120 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agent-agentic-workflow.mdcCursor rule
- .cursor/rules/agent-android-dev.mdcCursor rule
- .cursor/rules/agent-architect.mdcCursor rule
- .cursor/rules/agent-backend-dev.mdcCursor rule
- .cursor/rules/agent-dashboard.mdcCursor rule
- .cursor/rules/agent-debugger.mdcCursor rule
- .cursor/rules/agent-desktop-dev.mdcCursor rule
- .cursor/rules/agent-devops.mdcCursor rule
- .cursor/rules/agent-explainer-writer.mdcCursor rule
- .cursor/rules/agent-feasibility.mdcCursor rule
- .cursor/rules/agent-growth.mdcCursor rule
- .cursor/rules/agent-ios-dev.mdcCursor rule
- .cursor/rules/agent-legal.mdcCursor rule
- .cursor/rules/agent-optimizer.mdcCursor rule
- .cursor/rules/agent-orchestrator.mdcCursor rule
- .cursor/rules/agent-platform-architect.mdcCursor rule
- .cursor/rules/agent-platform-designer.mdcCursor rule
- .cursor/rules/agent-product-designer.mdcCursor rule
- .cursor/rules/agent-qa.mdcCursor rule
- .cursor/rules/agent-researcher.mdcCursor rule
- .cursor/rules/agent-reviewer.mdcCursor rule
- .cursor/rules/agent-rollback.mdcCursor rule
- .cursor/rules/agent-security.mdcCursor rule
- .cursor/rules/agent-setup.mdcCursor rule
- .cursor/rules/agent-social-media.mdcCursor rule
- .cursor/rules/agent-web-dev.mdcCursor rule
- .cursor/rules/skill-bug-fix.mdcCursor rule
- .cursor/rules/skill-commit.mdcCursor rule
- .cursor/rules/skill-context-budget.mdcCursor rule
- .cursor/rules/skill-cost-audit.mdcCursor rule
- .cursor/rules/skill-decision-log.mdcCursor rule
- .cursor/rules/skill-experiment.mdcCursor rule
- .cursor/rules/skill-founder-voice.mdcCursor rule
- .cursor/rules/skill-frontend-design.mdcCursor rule
- .cursor/rules/skill-gates.mdcCursor rule
- .cursor/rules/skill-grilling.mdcCursor rule
- .cursor/rules/skill-handoff.mdcCursor rule
- .cursor/rules/skill-human-design.mdcCursor rule
- .cursor/rules/skill-human-steps.mdcCursor rule
- .cursor/rules/skill-karpathy-guidelines.mdcCursor rule
- .cursor/rules/skill-known-reds.mdcCursor rule
- .cursor/rules/skill-legal-review.mdcCursor rule
- .cursor/rules/skill-new-feature.mdcCursor rule
- .cursor/rules/skill-observability.mdcCursor rule
- .cursor/rules/skill-ordered-steps.mdcCursor rule
- .cursor/rules/skill-performance.mdcCursor rule
- .cursor/rules/skill-readiness-gate.mdcCursor rule
- .cursor/rules/skill-release.mdcCursor rule
- .cursor/rules/skill-requirement-first.mdcCursor rule
- .cursor/rules/skill-safe-data-write.mdcCursor rule
- .cursor/rules/skill-setup.mdcCursor rule
- .cursor/rules/skill-single-source.mdcCursor rule
- .cursor/rules/skill-spec-audit.mdcCursor rule
- .cursor/rules/skill-tailoring.mdcCursor rule
- .cursor/rules/skill-twin-check.mdcCursor rule
- .cursor/rules/skill-verified-claims.mdcCursor rule
- .cursor/rules/skill-verify-green.mdcCursor rule
- bug-fixSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
2
Distinctive
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 19
No unconfirmed assumptions (rule 10), and every rejected idea is recorded (rule 12).
- Distinctive: line 33
Light is for throwaway prototypes only: no real users, no real personal data, no payments.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Generated by tools/sync_adapters.py from skills/gates/SKILL.md. Edit the source, not this file. -->Gate levels
project.toml [gates] level is one of three values. Explain them to the founder in these
words, not in your own; a level is what this file says it is.
Never relaxed, at any level
- Outward steps (deploy, merge, push, publish, send, pay, delete, real data writes) wait for the
founder's go, one step at a time (
skills/ordered-steps/). - Data writes prove themselves and can be undone (
skills/safe-data-write/). - The commit-msg hook refuses banned characters (
skills/commit/). - No unconfirmed assumptions (rule 10), and every rejected idea is recorded (rule 12).
- Free tiers are strict, with tested caps before release.
What changes
| strict | standard | light | |
| Requirement row before a change | always, new or cited | always for features; a copy or style fix cites the row of the screen it touches | one row per prototype area, cited in every commit; detail optional |
| Grilling and readiness gate | every feature | every feature | none |
Spec audit (skills/spec-audit/) | every feature | features touching existing code | none |
| Security and legal review | every feature touching data, money, AI output or claims | only where the feature's spec flags them | before any real user or real data |
| Full sweep | before every hand-off and every commit | before every commit | before every commit |
| QA report | every change | every feature | before any real user |
Light is for throwaway prototypes only: no real users, no real personal data, no payments. Moving from light to anything else means writing the missing requirement rows first.
Recommending
Setup always recommends strict and says what it buys, using the table above. If the founder
chooses another level, record the level, the reason and when to revisit it in
p1-closed-decisions.md, and the declined recommendation in p1-rejected.md.
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.

