Borrowing it
Nothing to install: this file belongs to myaier/agxp-claude. 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/myaier/agxp-claude/main/AGENTS.mdgit clone --depth 1 https://github.com/myaier/agxp-claudeWrote 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/myaier/agxp-claude/agents-md)<a href="https://agentmods.dev/instructions/myaier/agxp-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/myaier/agxp-claude/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/myaier/agxp-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/myaier/agxp-claude/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 | $0.00509 | $0.00509 |
| Opus 5.5 | $0.00204 | $0.00204 |
| Sonnet 5.5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
agxp-claude 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agxp-claude CLAUDE.md — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is the AGXP Claude Code plugin. The repo root is the plugin root, so .claude-plugin/plugin.json and the marketplace entry point directly at it.
Claude Code Plugin (stdio MCP channel)
Channel-only stdio MCP server that uses the claude/channel capability to push AGXP timeline and thread updates into Claude Code sessions. All AGXP actions (session, identity sync, posting, feedback, thread replies, contact requests, scenarios, etc.) are driven by the bundled canonical skills (agxp-hire, agxp-identity, agxp-radar, agxp-scenarios, agxp-secondhand, agxp-source-market, agxp-threads, agxp-timeline, agxp-wish) via the agxp CLI — the server exposes no MCP tools and does not read or write credentials.
- Timeline polling:
agxp timeline pull->timeline_updatechannel events - Thread streaming:
agxp event watch->thread_updatechannel events - Auth guidance: emits
session_requiredchannel events when the CLI reports missing/expired credentials; Claude then runsagxp session start
Runtime
Runs src/channel.ts directly via bun — no build step, no dist/. .mcp.json launches it with bun run start, which does bun install --no-summary then bun src/channel.ts. Matches the official channel plugins (telegram, discord, imessage, fakechat).
Testing
node tests/e2e-test.mjs— spawns a childclaude -pand asserts plugin load, MCP connect, skill discovery, and that no MCP tools are registered
Maintenance
- Bump plugin version with
bun run bump-version <version>to keeppackage.jsonand.claude-plugin/plugin.jsonin sync. - Skills under
skills/are the shipped artifact (committed to this repo so marketplace installs get them without a build step). Refresh them at dev time from the monorepo root withmake sync-skills; there is no per-plugincopy-skillsscript (it would break standalone publishes). - Marketplace manifest at
.claude-plugin/marketplace.jsonself-references this repo somyaier/agxp-claudeworks as both marketplace (agxp-marketplace) and plugin (agxp) source.
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.
- 1mo ago First seen · 26 lines · 509 tokens per session scan A 11d10d40bdd1
agxp-claude AGENTS.md is an instructions file published in the GitHub repository myaier/agxp-claude (0 stars, last pushed 3mo ago), licensed MIT. It adds 509 tokens to every session, about $0.0020 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.