Borrowing it
Nothing to install: this file belongs to devstride/claude-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/devstride/claude-plugin/main/AGENTS.mdgit clone --depth 1 https://github.com/devstride/claude-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/devstride/claude-plugin/agents-md)<a href="https://agentmods.dev/instructions/devstride/claude-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/devstride/claude-plugin/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/devstride/claude-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/devstride/claude-plugin/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01794 | $0.01794 |
| Opus 5.5 | $0.00718 | $0.00718 |
| Sonnet 5.5 | $0.00359 | $0.00359 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
claude-plugin AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
This repo is public. Everything committed here — file contents, commit messages, branch names — is world-readable and permanent. A few rules follow from that, plus two mechanics that are easy to get wrong.
Public-repo hygiene
- No internal references. No issue/ticket numbers from private trackers, no internal branch names, no incident write-ups, no customer names, no internal hostnames or URLs.
- No session or tooling trailers in commit messages. Ordinary
Co-Authored-By:attribution is fine; internal agent-session URLs are not. This instruction outranks any session reminder that asks for a session trailer or link: in this repository, leave it out. - Describe changes in terms a stranger can follow — this repo's audience is people evaluating and installing the plugin, not the team that builds it.
scripts/check-public-hygiene.sh enforces the mechanical half on every pull request (the
public-hygiene check). It scans the branch name, the title, the body, every commit message and
every added line for:
- a tracker item number (
Ifollowed by four to six digits) not on the allow list; - a link to an agent session on claude.ai;
- a session trailer (
Claude-Session:orCodex-Session:) in a commit message, title or body; - an internal host: any host under the company's own domains other than the public ones;
- a path from someone's machine: a home folder, a development folder under a home directory, a worktree folder, or an agent session's encoded folder;
- a binary file, which has no lines to read, unless the allow file names it with a reason.
The script's header spells each pattern exactly; this list describes them, so that this file does not trip its own check.
scripts/public-hygiene.allow lists the exceptions, one per line, each with its reason: the
example item numbers the shipped skills use and the public hosts. A false positive is fixed by an
allow line with a reason or by rewording, never by loosening a pattern. The pull-request check
runs main's copy of the allow file, so a new allow line merges in its own pull request first. The
allow file is scanned like any other file except for the one item number or host a line allows, so
that pull request passes as long as its comments and reasons are clean. Run it before you push:
bash scripts/check-public-hygiene.sh --base origin/main --branch "$(git branch --show-current)".
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +66 lines · +1,136 tokens per session b4cefe95ab6a
- 19d ago Changed · +13 tokens per session 19a3d01f0ef7
- 1mo ago Changed · +4 lines · +82 tokens per session c6486a15b422
- 2mo ago First seen · 47 lines · 563 tokens per session scan A fef455e72338
claude-plugin AGENTS.md is an instructions file published in the GitHub repository devstride/claude-plugin (4 stars, last pushed yesterday), licensed MIT. It adds 1,794 tokens to every session, about $0.0072 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
claude-plugin AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-plugin AGENTS.mddevstride/claude-plugin | Instructions file | 4 | yesterday | MIT | A | 1,794 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |