Borrowing it
Nothing to install: this file belongs to cboone/agent-harness-plugins. 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/cboone/agent-harness-plugins/main/AGENTS.mdgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/agents-md)<a href="https://agentmods.dev/instructions/cboone/agent-harness-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/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/cboone/agent-harness-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/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 | $0.01407 | $0.01407 |
| Opus 5.5 | $0.00563 | $0.00563 |
| Sonnet 5.5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
agent-harness-plugins 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 today.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Harness Plugins
Project overview
This is the canonical source for Claude Code plugins (skills and hooks), with a committed generated mirror for Codex CLI. See README.md for installation and the catalog.
Critical constraints
- Edit canonical sources in
plugins/<name>/. Never hand-editdist/,.agents/,set-up-review-config'sreferences/checklists/copies of each style guide'sreferences/review-checklist.md,suggest-next-issue's copy ofpublish-report-board'sreferences/progress-model.md, or thetrim-commentsandtrim-textcopies ofreview-anti-patterns'sreferences/codex-exec.md; regenerate withmake buildand commit the results when source changes affect them. .claude-plugin/marketplace.jsonis the catalog of record. Each plugin's.claude-plugin/plugin.jsonis its sole version source; a.codex-plugin/plugin.jsonmirrors that version when present. New plugins start at1.0.0; wording/fixes are patch changes, new capabilities are minor changes, and breaking changes are major changes.- After merging, rebasing or before creating a PR, use the repository's check-versions skill.
- Merge PRs with merge commits only (
gh pr merge --merge). The repository disables squash and rebase merging. - Root and plugin README descriptions match the catalog description verbatim. Preserve root README anchors
installandcodex-cli-known-limitations; plugin READMEs always link toinstalland link to the other anchor when relevant.
Navigation and scoped instructions
Read the applicable scoped file before editing its directory, including when working from the repository root. Every scoped CLAUDE.md is a symlink to its sibling AGENTS.md.
- plugins/AGENTS.md: skill and hook source, bundled helpers, registration and versioning.
- bin/AGENTS.md: repository validators, generators and tooling.
- tests/AGENTS.md: scrut suites, fixture stubs and CI environment wiring.
- docs/AGENTS.md: plans, reviews and reference documentation.
- Plugin development: full layouts, adding plugins, cross-reference syntax, README catalog format and version rules. Read this before editing plugin or catalog surfaces, including the root README and marketplace files.
.github/copilot-instructions.md: Copilot review rules;.github/instructions/: scoped review guidance.
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.
- today Changed · +15 tokens per session 331451ec9989
- 13d ago Changed · +68 tokens per session f6850b451def
- 16d ago Changed · +34 tokens per session 42202e86aa88
- 18d ago Changed · +16 tokens per session 875c5cd2951c
- 19d ago Changed · +10 tokens per session b6359d1cf0f5
- 21d ago Changed · +26 tokens per session e6cf589179a4
- 27d ago Changed · +1 lines · +24 tokens per session 42b0d000c443
- 1mo ago Changed · +61 tokens per session 82001a88bd9b
- 1mo ago Changed · +14 lines · +278 tokens per session 9d93b368f584
- 1mo ago First seen · 54 lines · 875 tokens per session scan A 778e3cbe191c
agent-harness-plugins AGENTS.md is an instructions file published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed today), licensed MIT. It adds 1,407 tokens to every session, about $0.0056 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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.