comp
AGENTS.md2k starsChanged 5 months agoAGPL-3.0View on GitHub
We are migrating away from Next.js server actions toward calling the NestJS API directly. Every customer-facing endpoint in apps/api/src/ flows into three systems: the OpenAPI spec (packages/docs/openapi.json), the MCP server…
We split this AGENTS.md into the rules it gives an agent
26 rules. About 0 are common, 8 are distinctive, and 18 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
18
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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.
Trending
Steady talk.thin dataabout the whole repository
Who's talking about trycompai/comp
- @tom-doerr.bsky.social“https://github.com/trycompai/comp”Bluesky · Jul 30, 2025 · 1 likes
- basitalisandhu/agent-identity-governance-skills“Add agent-audit-log-integrity (0.3.0)”GitHub · Oct 20, 2026
- basitalisandhu/compliance-evidence-skills“Add evidence-collection-plan (0.6.0)”GitHub · Oct 20, 2026
- better-auth/better-auth“fix(types): make plugin declarations portable”GitHub · Aug 13, 2026
- Next-Degree/dilligent“rebrand: Comp AI → Dilligent / Pickle branding migration”GitHub · Aug 10, 2026
The biggest 5 of 6 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 6
Talked about on GitHub and Bluesky (6 times).
On GitHub · 4
- Oct 20, 2026Add agent-audit-log-integrity (0.3.0) — basitalisandhu/agent-identity-governance-skills0 reactions
- Oct 20, 2026Add evidence-collection-plan (0.6.0) — basitalisandhu/compliance-evidence-skills0 reactions
- Aug 13, 2026fix(types): make plugin declarations portable — better-auth/better-auth0 reactions · 6 comments
- Aug 10, 2026rebrand: Comp AI → Dilligent / Pickle branding migration — Next-Degree/dilligent0 reactions · 2 comments
On Bluesky · 2
- Jul 30, 2025https://github.com/trycompai/comp — @tom-doerr.bsky.social1 likes and repost
- Mar 4, 2026github.com/trycompai/comp ? what a time to be alive! — @rager.tech0 likes and reposts · 1 reply
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 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 repository69 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/api-endpoint-contract.mdcCursor rule
- .cursor/rules/code.mdcCursor rule
- .cursor/rules/cursor-usage.mdcCursor rule
- .cursor/rules/data.mdcCursor rule
- .cursor/rules/essentials.mdcCursor rule
- .cursor/rules/forms.mdcCursor rule
- .cursor/rules/infra.mdcCursor rule
- .cursor/rules/prisma.mdcCursor rule
- .cursor/rules/prompt-engineering.mdcCursor rule
- .cursor/rules/trigger.advanced-tasks.mdcCursor rule
- .cursor/rules/trigger.basic.mdcCursor rule
- .cursor/rules/trigger.config.mdcCursor rule
- .cursor/rules/trigger.realtime.mdcCursor rule
- .cursor/rules/trigger.scheduled-tasks.mdcCursor rule
- .cursor/rules/ui.mdcCursor rule
- audit-design-systemSkill
- audit-hooksSkill
- audit-rbacSkill
- audit-testsSkill
- better-auth-best-practicesSkill
- billingSkill
- codeSkill
- cursor-usageSkill
- dataSkill
- diagnose-generation-failureSkill
- essentialsSkill
- formsSkill
- generate-mcp-serverSkill
- infraSkill
- manage-openapi-overlaysSkill
- new-feature-setupSkill
- prismaSkill
- production-readinessSkill
- prompt-engineeringSkill
- speakeasy-contextSkill
- stale-worktree-cleanupSkill
- trigger-advanced-tasksSkill
- trigger-basicSkill
- trigger-configSkill
- trigger-realtimeSkill
- trigger-scheduled-tasksSkill
- uiSkill
- api-endpoint-contractSkill
- audit-design-systemSkill
- audit-hooksSkill
- audit-rbacSkill
- audit-testsSkill
- check-results-serviceSkill
- cleanupSkill
- codeSkill
- cursor-usageSkill
- dataSkill
- essentialsSkill
- formsSkill
- infraSkill
- new-feature-setupSkill
- prismaSkill
- production-readinessSkill
- prompt-engineeringSkill
- The first 60 shown.
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.

