denylist Claude Code subagentB

denylist from trustabl/agent-reliability-analyzer is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add trustabl/agent-reliability-analyzer/testdata/corpus/subagent-tools-inherit/.claude/agents/denylist.md@git:20261021.307df30

Pins git:20261021.307df30 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 13 of 14 checks passed
Kind
Claude Code subagent
Repository
trustabl/agent-reliability-analyzer
Path
testdata/corpus/subagent-tools-inherit/.claude/agents/denylist.md
Versions recorded
1
Latest version
git:20261021.307df30, committed Oct 21, 2026
Size
127 bytes
Repository stars
88
License
Apache-2.0

Synthetic subagent with a denylist.

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

You review text.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add trustabl/agent-reliability-analyzer/testdata/corpus/subagent-tools-inherit/.claude/agents/denylist.md@sha256:af4cee1bb29e2f49

The line at the top of this page pins the label git:20261021.307df30, 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_edwvjg6hfbxgqqsl.svg)](https://markdownregistry.com/a/art_edwvjg6hfbxgqqsl)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in trustabl/agent-reliability-analyzer/testdata/corpus/subagent-tools-inherit/.claude/agents/denylist.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of denylist.md from somewhere else? Ask it: where did my denylist.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Oct 21, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261021.307df30 latest2026-10-21 307df30 127 BB view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

B  13 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: Size between 200 bytes and 200 KB (127 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 · 88 stars · license Apache-2.0 · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_edwvjg6hfbxgqqsl
GET https://markdownregistry.com/api/v1/resolve?ref=trustabl/agent-reliability-analyzer/testdata/corpus/subagent-tools-inherit/.claude/agents/denylist.md
GET https://markdownregistry.com/api/v1/blob/af4cee1bb29e2f49bdfec637eaa7a96cc0f2d48146ceb8e94effcee4f3912f6f

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: which agent file does what.

More from trustabl/agent-reliability-analyzer

trustabl Plugin marketplace
trustabl/agent-reliability-analyzer · .claude-plugin/marketplace.json · Trustabl's Claude Code plugin marketplace. (1 plugin: trustabl)
git:20260910.ef076a1 · audit A · 88 stars
CLAUDE.md CLAUDE.md file
trustabl/agent-reliability-analyzer · CLAUDE.md
git:20261104.fe75b24 · audit A · 88 stars
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 · 88 stars
llms.txt llms.txt file
trustabl/agent-reliability-analyzer · llms.txt
git:20261026.449ff4d · audit A · 88 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 · 88 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 · 88 stars
researcher Claude Code subagent
trustabl/agent-reliability-analyzer · testdata/corpus/claude-settings-fixture/.claude/agents/researcher.md · Reads files and grep'd content, no writes.
git:20260527.58ef39d · audit B · 88 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 · 88 stars
inbox-searcher Claude Code subagent
trustabl/agent-reliability-analyzer · testdata/corpus/email-agent/agent/.claude/agents/inbox-searcher.md · Email inbox search specialist, takes in appropriate context for the email and a goal of what to search for. Return the…
git:20260527.58ef39d · audit A · 88 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 · 88 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 · 88 stars
style Cursor rule
trustabl/agent-reliability-analyzer · testdata/corpus/guidance-hidden-fixture/.cursor/rules/style.mdc
git:20261029.4ab15e0 · audit B · 88 stars

Every file in trustabl/agent-reliability-analyzer

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