CLAUDE.mdA

CLAUDE.md from trustabl/agent-reliability-analyzer is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.

Install it, pinned
mdr add trustabl/agent-reliability-analyzer/CLAUDE.md@git:20261013.5de28bf

Pins git:20261013.5de28bf in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
CLAUDE.md file
Repository
trustabl/agent-reliability-analyzer
Path
CLAUDE.md
Versions recorded
13
Latest version
git:20261013.5de28bf, committed Oct 13, 2026
First version recorded
Sep 29, 2026
Size
37,267 bytes
Repository stars
76
License
Apache-2.0

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Instructions for Claude — Trustabl

This file captures durable architectural commitments that span the whole
codebase. Per-area conventions live in nested CLAUDE.md files (see
[`testdata/rules-fixture/CLAUDE.md`](testdata/rules-fixture/CLAUDE.md)
for rule authoring). The detection rule packs do **not** live in this repo:
they live in the external **`agent-reliability-rules`** repository
(`https://github.com/trustabl/agent-reliability-rules`), which the engine pulls at
scan time. `testdata/rules-fixture/` is an in-engine **test mirror** of those
packs — see [Two-repo rule model](#two-repo-rule-model-rules-vs-engine) below,
which is required reading before touching any rule.

For the current implementation, see [`ARCHITECTURE.md`](ARCHITECTURE.md).
This file is for principles; ARCHITECTURE.md is for facts.

## Project naming

The product is named **Trustabl** (capital T). Use this spelling in all
human-facing prose: docs, status reports, finding messages shown in scan
reports, and CLI help text.

The lowercase `trustabl` is reserved for machine identifiers that must
**not** be capitalized: the binary name, the CLI command (`trustabl scan`,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add trustabl/agent-reliability-analyzer/CLAUDE.md@sha256:1ebd3206440f9199

The line at the top of this page pins the label git:20261013.5de28bf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rlcwmcky7zqkoe5h.svg)](https://markdownregistry.com/a/art_rlcwmcky7zqkoe5h)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 13 versions of this file, between Sep 29, 2026 and Oct 13, 2026, about one every day.

versioncommittedcommitsizeaudit
git:20261013.5de28bf latest2026-10-13 5de28bf 37,267 BA view · diff
git:20261012.323cb5c2026-10-12 323cb5c 36,451 BA view · diff
git:20261012.126c76e2026-10-12 126c76e 34,249 BA view · diff
git:20261011.ae803ee2026-10-11 ae803ee 34,706 BA view · diff
git:20261008.29f00d02026-10-08 29f00d0 35,337 BA view · diff
git:20261005.840c7bb2026-10-05 840c7bb 33,592 BA view · diff
git:20261005.7ea47e62026-10-05 7ea47e6 32,896 BA view · diff
git:20261002.57f62622026-10-02 57f6262 31,825 BA view · diff
git:20261001.de387372026-10-01 de38737 31,032 BA view · diff
git:20261001.1f79d9c2026-10-01 1f79d9c 30,082 BA view · diff
git:20260930.f0016a32026-09-30 f0016a3 29,046 BA view · diff
git:20260930.a1e09592026-09-30 a1e0959 28,935 BA view · diff
git:20260929.d838d502026-09-29 d838d50 27,897 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (37267 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

trustabl/agent-reliability-analyzer · 76 stars · license Apache-2.0 · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rlcwmcky7zqkoe5h
GET https://markdownregistry.com/api/v1/resolve?ref=trustabl/agent-reliability-analyzer/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/1ebd3206440f91996acf1decd03b916af8ebddf69e7b489da3ff892afa9e7daa

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.

More from trustabl/agent-reliability-analyzer

trustabl-scan SKILL.md skill
trustabl/agent-reliability-analyzer · distributions/wshobson-agents/skills/trustabl-scan/SKILL.md · Use right after you write or modify AI agent, tool, subagent, or MCP-server code (Claude Agent SDK, OpenAI Agents SDK…
v0.1.13 · audit A · 76 stars
llms.txt llms.txt file
trustabl/agent-reliability-analyzer · llms.txt
git:20260910.ef076a1 · audit A · 76 stars
trustabl-enrich SKILL.md skill
trustabl/agent-reliability-analyzer · skills/trustabl-enrich/SKILL.md · Enriches source files flagged by a Trustabl scan — adds what is missing and corrects what is wrong, guided entirely by…
v1.0.0 · audit A · 76 stars
trustabl-scan SKILL.md skill
trustabl/agent-reliability-analyzer · skills/trustabl-scan/SKILL.md · Use right after you write or modify AI agent, tool, subagent, or MCP-server code (OpenAI Agents SDK, Claude Agent SDK…
v0.1.13 · audit A · 76 stars
CLAUDE.md@testdata/corpus/email-agent CLAUDE.md file
trustabl/agent-reliability-analyzer · testdata/corpus/email-agent/CLAUDE.md
git:20260527.58ef39d · audit B · 76 stars
action-creator SKILL.md skill
trustabl/agent-reliability-analyzer · testdata/corpus/email-agent/agent/.claude/skills/action-creator/SKILL.md · Creates user-specific one-click action templates that execute email operations when clicked in the chat interface. Use…
git:20260527.58ef39d · audit A · 76 stars
listener-creator SKILL.md skill
trustabl/agent-reliability-analyzer · testdata/corpus/email-agent/agent/.claude/skills/listener-creator/SKILL.md · Creates event-driven email listeners that monitor for specific conditions (like urgent emails from boss, newsletters to…
git:20260527.58ef39d · audit A · 76 stars
executive-briefing SKILL.md skill
trustabl/agent-reliability-analyzer · testdata/corpus/research-agent/.claude/skills/executive-briefing/SKILL.md · Transforms research findings into executive-ready briefings. Automatically activated when user mentions 'executive'…
git:20260527.58ef39d · audit A · 76 stars
pdf SKILL.md skill
trustabl/agent-reliability-analyzer · testdata/corpus/research-agent/.claude/skills/pdf/SKILL.md · Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents…
git:20260527.58ef39d · audit A · 76 stars
CLAUDE.md@testdata/corpus/simple-chatapp CLAUDE.md file
trustabl/agent-reliability-analyzer · testdata/corpus/simple-chatapp/CLAUDE.md
git:20260527.58ef39d · audit A · 76 stars
bound-skill SKILL.md skill
trustabl/agent-reliability-analyzer · testdata/corpus/skill-agent-specific/.claude/skills/bound-skill/SKILL.md · A skill bound to one specific agent, used for reading files that agent points it at.
git:20260812.c9b4ad1 · audit A · 76 stars
dup-skill SKILL.md skill
trustabl/agent-reliability-analyzer · testdata/corpus/skill-duplicate-tool-refs/.claude/skills/dup-skill/SKILL.md · A skill with duplicate tool references, used for reading a file the user names.
git:20260812.c9b4ad1 · audit A · 76 stars

Every file in trustabl/agent-reliability-analyzer

Other files named CLAUDE.md

CLAUDE.md CLAUDE.md file
affaan-m/ecc · CLAUDE.md
git:20260528.04c68e4 · audit A · 284,510 stars
CLAUDE.md CLAUDE.md file
firecrawl/firecrawl · CLAUDE.md
git:20261008.5a75dca · audit A · 193,096 stars
CLAUDE.md CLAUDE.md file
garrytan/gstack · CLAUDE.md
git:20261011.5d64745 · audit A · 136,966 stars
CLAUDE.md CLAUDE.md file
juliusbrussee/caveman · CLAUDE.md
git:20261010.505ac30 · audit B · 113,780 stars
CLAUDE.md CLAUDE.md file
addyosmani/agent-skills · CLAUDE.md
git:20260720.8fd2081 · audit A · 109,013 stars
CLAUDE.md CLAUDE.md file
nexu-io/open-design · CLAUDE.md
git:20260430.9b57c22 · audit B · 102,533 stars
CLAUDE.md CLAUDE.md file
thedotmack/claude-mem · CLAUDE.md
git:20261013.84bbb53 · audit A · 102,153 stars
CLAUDE.md CLAUDE.md file
egonex-ai/understand-anything · CLAUDE.md
git:20260710.6677c67 · audit B · 87,696 stars

Browse by kind, by grade A, or by owner.