agentleFS
NeuraCerebra-AINeuraCerebra-AI/Shipworthy/llms.txt

Shipworthy

llms.txt2 starsChanged 3 months agoMITView on GitHub

Free, open-source AI testing agent for automated frontend, end-to-end (E2E), and backend-symptom testing of web apps and AI agents. It walks every safe user path like a real user, checks the backend behind each one, runs an independent verifier over the evidence, and returns a proof-backed ship-or-don't verdict — ready, conditionally ready, not ready, or cannot determine. Read-only by default; it never overclaims. Shipworthy installs as four skills for Claude Code, Codex, or any SKILL.md-compatible agent. Trigger a full run…

The file

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read-only by default; zero telemetry, zero credential access, zero network calls, zero auto-update

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 3,727 llms.txt 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# Shipworthy

> Free, open-source AI testing agent for automated frontend, end-to-end (E2E), and backend-symptom testing of web apps and AI agents. It walks every safe user path like a real user, checks the backend behind each one, runs an independent verifier over the evidence, and returns a proof-backed ship-or-don't verdict — ready, conditionally ready, not ready, or cannot determine. Read-only by default; it never overclaims.

Shipworthy installs as four skills for Claude Code, Codex, or any SKILL.md-compatible agent. Trigger a full run by asking "Are we shipworthy?". A full run does automated end-to-end testing across the frontend (browser, Playwright, or Computer Use), analyzes backend symptoms (failed API calls, 500s behind "success" screens, data that never saved), runs a minimum of three independently-verified waves, labels every path with one of seven coverage statuses, and generates a self-contained HTML report. It is not a load test, a penetration test, or a full backend/security audit.

## Docs

- [README](https://raw.githubusercontent.com/NeuraCerebra-AI/shipworthy/HEAD/README.md): overview, install, what a run looks like, FAQ
- [Architecture](https://raw.githubusercontent.com/NeuraCerebra-AI/shipworthy/HEAD/ARCHITECTURE.md): the control stack — who owns the evidence ledger, the coverage frontier, and the verifier gates

## The four skills

- [ship-readiness-orchestrator](https://raw.githubusercontent.com/NeuraCerebra-AI/shipworthy/HEAD/ship-readiness-orchestrator/SKILL.md): the conductor — owns the one evidence ledger, coverage map, and readiness verdict, and dispatches the three lanes without letting them overclaim
- [ship-deep-review](https://raw.githubusercontent.com/NeuraCerebra-AI/shipworthy/HEAD/ship-deep-review/SKILL.md): the evidence engine — multi-wave agent dispatch, with no wave summary until an independent verifier has checked the raw outputs
- [ship-product-workflows](https://raw.githubusercontent.com/NeuraCerebra-AI/shipworthy/HEAD/ship-product-workflows/SKILL.md): the path walker — safely tries or traces every meaningful user path across UI, state, forms, permissions, and backend symptoms
- [ship-workflow-clarity](https://raw.githubusercontent.com/NeuraCerebra-AI/shipworthy/HEAD/ship-workflow-clarity/SKILL.md): the human lens — comprehension, next-action, recovery, trust, and harmful-simplification checks

## Key facts

- License: MIT (free, open-source)
- Read-only by default; zero telemetry, zero credential access, zero network calls, zero auto-update
- Platforms: Claude Code, Codex, and other SKILL.md-compatible agents
- Output: a self-contained HTML report; can export SARIF for GitHub code scanning
- Repository: https://github.com/NeuraCerebra-AI/shipworthy

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.