failproofai
AGENTS.md8.2k starsChanged 7 months agoLicence not identifiedView on GitHub
This file is read by AI coding agents (Codex, Claude Code, etc.). It duplicates the most critical rules from CLAUDE.md in a format optimised for agent consumption. If that prints…
- Installs packages
1 other project uses a version of this.
Trending
Quiet since May.about the whole repository
Most recently taken up by
- FailproofAI/failproofaiword for word, first seen Apr 8, 2026
Who's talking about exospherehost/failproofai
- A Hacker News story“PocketOS lost their prod DB in 9s. The rules to prevent it were in the prompt”Hacker News · Apr 29, 2026 · 2 points
- hesreallyhim/awesome-claude-code“[Resource]: failproof ai”GitHub · May 20, 2026
- FailproofAI/failproofai“[luv-339] fix: drop startup ASCII wordmark; align version with link lines”GitHub · May 10, 2026
- FailproofAI/failproofai“[luv-320] docs: swap README hero gif to readme-arch-hq”GitHub · May 8, 2026
- FailproofAI/claude-hackernews“[claude-hackernews] Reply draft: Coord Show HN, claim-vs-invariant orthogonality (id=48063563)”GitHub · May 8, 2026
The biggest 5 of 28 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 28
Talked about on GitHub and Hacker News (28 times).
On GitHub · 27
- May 20, 2026[Resource]: failproof ai — hesreallyhim/awesome-claude-code0 reactions · 1 comment
- May 10, 2026[luv-339] fix: drop startup ASCII wordmark; align version with link lines — FailproofAI/failproofai0 reactions · 1 comment
- May 8, 2026[luv-320] docs: swap README hero gif to readme-arch-hq — FailproofAI/failproofai0 reactions · 1 comment
- May 8, 2026[claude-hackernews] Reply draft: Coord Show HN, claim-vs-invariant orthogonality (id=48063563) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 8, 2026[claude-hackernews] Reply draft: Agentctl Show HN, replay-against-old-traces vs real-time hooks (id=48057567) — FailproofAI/claude-hackernews0 reactions · 1 comment
22 more on GitHub
- May 8, 2026[luv-308] fix: stream messages so large Sonnet docs dodge Bedrock's 300s InvokeModel wall — FailproofAI/failproofai0 reactions · 1 comment
- May 4, 2026[claude-hackernews] Reply draft: Kirikiri Show HN, mobile supervision asymmetry vs hook layer (id=47996198) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 4, 2026[claude-hackernews] Reply draft: Stop Treating Agent Sandboxes as Cattle, intent-vs-infra layer (id=48004872) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 4, 2026[claude-hackernews] Reply draft: TrainForgeTester Show HN, scenario-tests vs in-loop hook seam (id=48000135) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 4, 2026[claude-hackernews] Reply draft: AI CAD Harness Show HN, bounded-mutation in agentic feature-tree edits (id=47977694) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 4, 2026[claude-hackernews] Reply draft: Lilith-zero Show HN, transport vs hook layer (id=47875939) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 4, 2026[claude-hackernews] Reply draft: Cohorte governance stack, YAML vs code-as-policy (id=47860859) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 4, 2026[claude-hackernews] Reply draft: BetterClaw Show HN, workflow-shape vs invariant-shape (id=47973502) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 4, 2026[claude-hackernews] Reply draft: $38k Bedrock runaway, LLM-call vs tool-call layer (id=47933355) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 3, 2026[claude-hackernews] Reply draft: Snyk agent-scan Show HN, static-catalog vs runtime-call seam (id=47999709) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 3, 2026[claude-hackernews] Reply draft: Spec27 Show HN, spec-tests vs in-loop hook seam (id=47959984) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 3, 2026[claude-hackernews] Reply draft: Trent Show HN, static-review vs runtime-action layer (id=47962091) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 3, 2026[claude-hackernews] Reply draft: Smithy-ai Show HN, instruct() as third option (id=47999589) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 3, 2026[claude-hackernews] Reply draft: trust-boundaries, operator-side PreToolUse policy (id=47963671) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 3, 2026[claude-hackernews] Reply draft: VentureBeat credentials-exploit, deny-rule truncation (id=47986839) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 3, 2026[claude-hackernews] Reply draft: OMAR Show HN, policy-as-code at swarm scale (id=47978340) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 3, 2026[claude-hackernews] Reply draft: Pu.sh harness, hook layer outside the harness (id=47968112) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 2, 2026[claude-hackernews] Reply draft: harness-outside-sandbox, PreToolUse firewall layer (id=47990675) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 2, 2026[claude-hackernews] Reply draft: rogue Cursor agent, prod-token grep (id=47924586) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 1, 2026[claude-hackernews] Reply draft: AgentPort vs runtime-hook layer (id=47950752) — FailproofAI/claude-hackernews0 reactions · 1 comment
- May 1, 2026[claude-hackernews] Reply draft: hooks vs CLAUDE.md drift (id=47936579) — FailproofAI/claude-hackernews0 reactions · 1 comment
- Apr 30, 2026[CLAUDE ROUTINE]: CX enhancement — add docs & issue-tracker links to the dashboard error fallback so users have a clear next step when something breaks — FailproofAI/failproofai0 reactions
On Hacker News · 1
- Apr 29, 2026PocketOS lost their prod DB in 9s. The rules to prevent it were in the prompt2 points · 1 comment
Other versions1 project uses a version of this.
Word for word · 1
- FailproofAI/failproofai★ 8.2k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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.
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 31,774 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.
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 0 are common, 1 is distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — 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 40,246 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.
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.

