AGENTS.mdB

AGENTS.md from arcjet/skills is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add arcjet/skills/AGENTS.md@git:20260521.04d07cb

Pins git:20260521.04d07cb in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 13 of 14 checks passed
Kind
AGENTS.md file
Repository
arcjet/skills
Path
AGENTS.md
Versions recorded
5
Latest version
git:20260521.04d07cb, committed May 21, 2026
First version recorded
Apr 17, 2026
Size
2,851 bytes
Repository stars
4
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

# AGENTS.md

Loose lessons learned while using the **skill-creator** skill (at `.agents/skills/skill-creator/`). Terse on purpose. **Always read `.agents/skills/skill-creator/SKILL.md` first** — this file only supplements it.

## Subagent prompts for test runs

- Keep prompts minimal. The prescribed format (`Skill path / Task / Input files / Save outputs to`) is enough — don't add framing like "you're running an eval," "report what you did," or environment hints the agent should discover itself (e.g. that the CLI is pre-authenticated).
- Don't add restrictions like "don't run the server" or "typechecking optional." Those bias the agent away from the verification step you're trying to measure.

## Aggregation gotchas

- The aggregator expects per-run subdirectories: `eval-X/<config>/run-N/grading.json` (plus `timing.json`). If you save outputs at `eval-X/<config>/grading.json` (no `run-N`), it picks up nothing and reports 0%.
- Config ordering in `benchmark.md` is alphabetical, which means `new_skill` / `old_skill` and `with_skill` / `without_skill` flip the delta sign. Sanity-check the sign by hand.

## Capturing subagent transcripts
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add arcjet/skills/AGENTS.md@sha256:6504c220d8ddc29b

The line at the top of this page pins the label git:20260521.04d07cb, 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_t26nt7mupzdwfkua.svg)](https://markdownregistry.com/a/art_t26nt7mupzdwfkua)

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

Versions

The registry has recorded 5 versions of this file, between Apr 17, 2026 and May 21, 2026, about one every 8 days. Its first recorded version is graded A and its latest B.

versioncommittedcommitsizeaudit
git:20260521.04d07cb latest2026-05-21 04d07cb 2,851 BB view · diff
git:20260511.27996292026-05-11 2799629 3,322 BA view · diff
git:20260417.50d5ad52026-04-17 50d5ad5 3,220 BA view · diff
git:20260417.869e9da2026-04-17 869e9da 2,331 BA view · diff
git:20260417.bd04f5c2026-04-17 bd04f5c 2,145 BA view

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: No script tag (matched: <script)
  • pass: Size between 200 bytes and 200 KB (2851 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

Starting a new one? Use a template for AGENTS.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

arcjet/skills · 4 stars · license Apache-2.0 · pushed 2026-10-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_t26nt7mupzdwfkua
GET https://markdownregistry.com/api/v1/resolve?ref=arcjet/skills/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/6504c220d8ddc29bf4ee4666d531684fa1867fce6dede21525b6319cc4051f04

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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from arcjet/skills

skill-creator SKILL.md skill
arcjet/skills · .agents/skills/skill-creator/SKILL.md · Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a…
git:20260420.e0292b1 · audit A · 4 stars
arcjet SKILL.md skill
arcjet/skills · arcjet/SKILL.md · Add Arcjet security protection to HTTP routes, AI agent tool calls, MCP servers, background jobs, and queue workers…
git:20261007.436baca · audit A · 4 stars
integrate-arcjet-guard-agent-framework-go SKILL.md skill
arcjet/skills · integrate-arcjet-guard-agent-framework-go/SKILL.md · Integrate Arcjet Guard into Microsoft Agent Framework for Go (github.com/microsoft/agent-framework-go). Wrap a functool…
git:20260917.b9606c2 · audit A · 4 stars
integrate-arcjet-guard-claude-agent-sdk-py SKILL.md skill
arcjet/skills · integrate-arcjet-guard-claude-agent-sdk-py/SKILL.md · Integrate Arcjet Guard into the Python Claude Agent SDK — wrap authored @tool with guard_tool, and use guard_hooks for…
git:20260916.f8959e1 · audit A · 4 stars
integrate-arcjet-guard-claude-managed-agents-py SKILL.md skill
arcjet/skills · integrate-arcjet-guard-claude-managed-agents-py/SKILL.md · Integrate Arcjet Guard into Python Claude Managed Agents — screen user.message with guard_events before…
git:20261003.d9b5d6d · audit A · 4 stars
integrate-arcjet-guard-cloudflare-think SKILL.md skill
arcjet/skills · integrate-arcjet-guard-cloudflare-think/SKILL.md · Integrate Arcjet Guard into Cloudflare Think — delegate beforeToolCall to guardHooks so a DENY substitutes or blocks…
git:20260922.4ae5d84 · audit A · 4 stars
integrate-arcjet-guard-crewai SKILL.md skill
arcjet/skills · integrate-arcjet-guard-crewai/SKILL.md · Integrate Arcjet Guard into official CrewAI — register process-wide PRE_TOOL_CALL with register_arcjet_hooks, or wrap a…
git:20260916.f8959e1 · audit A · 4 stars
integrate-arcjet-guard-google-adk-py SKILL.md skill
arcjet/skills · integrate-arcjet-guard-google-adk-py/SKILL.md · Integrate Arcjet Guard into Python Google ADK — assign guard_tool to LlmAgent(before_tool_callback=), put guard_plugin…
git:20260922.4ae5d84 · audit A · 4 stars
integrate-arcjet-guard-langchain-py SKILL.md skill
arcjet/skills · integrate-arcjet-guard-langchain-py/SKILL.md · Integrate Arcjet Guard into Python LangChain — wrap a BaseTool you call with guard_tool, put ArcjetMiddleware +…
git:20260916.f8959e1 · audit A · 4 stars
integrate-arcjet-guard-openai-agents-py SKILL.md skill
arcjet/skills · integrate-arcjet-guard-openai-agents-py/SKILL.md · Integrate Arcjet Guard into Python OpenAI Agents — wrap FunctionTool / function_tool with guard_tool and read a…
git:20260916.f8959e1 · audit A · 4 stars
integrate-arcjet-guard-strands-agents-py SKILL.md skill
arcjet/skills · integrate-arcjet-guard-strands-agents-py/SKILL.md · Integrate Arcjet Guard into Python Strands Agents — wrap authored @tool with guard_tool, and put guard_hooks on…
git:20260916.f8959e1 · audit A · 4 stars

Every file in arcjet/skills

Other files named AGENTS.md

AGENTS.md AGENTS.md file
morluto/rea · AGENTS.md
git:20261102.920d634 · audit A · 433,876 stars
AGENTS.md AGENTS.md file
obra/superpowers · AGENTS.md
git:20261020.b739a8a · audit A · 314,583 stars
AGENTS.md AGENTS.md file
affaan-m/ecc · AGENTS.md
git:20261030.f29e332 · audit A · 299,696 stars
AGENTS.md AGENTS.md file
firecrawl/firecrawl · AGENTS.md
git:20261008.5a75dca · audit A · 199,595 stars
AGENTS.md AGENTS.md file
dietrichgebert/ponytail · AGENTS.md
git:20261008.2a1fe84 · audit A · 185,249 stars
AGENTS.md AGENTS.md file
graphify-labs/graphify · AGENTS.md
git:20260926.98d73fe · audit A · 144,492 stars
AGENTS.md AGENTS.md file
garrytan/gstack · AGENTS.md
git:20261107.ef99eb5 · audit A · 140,694 stars
AGENTS.md AGENTS.md file
juliusbrussee/caveman · AGENTS.md
git:20261106.e45976c · audit A · 118,366 stars

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