Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/cboone/agent-harness-plugins/agents-mdgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWhat 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 | $0.01544 | $0.01544 |
| Opus 5 | $0.00772 | $0.00772 |
| Sonnet 5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00154 | $0.00154 |
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 2d 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.
Claude Code Plugins
Project overview
This repository is the canonical source for a collection of Claude Code plugins (skills and hooks). Committed mirrors under dist/codex/ and dist/opencode/ make the same plugins work in Codex CLI and OpenCode. User-facing details live in README.md.
Where to find things
plugins/<name>/: canonical plugin source. Each plugin has.claude-plugin/plugin.json,README.md, and eitherskills/<name>/SKILL.mdorhooks/hooks.json(or both)..claude-plugin/marketplace.json: catalog of record for the Claude Code marketplace. Source of truth for plugin metadata and versions..agents/plugins/marketplace.jsonanddist/codex/: generated Codex CLI marketplace plus mirrored plugin roots. Regenerate withbin/build-codex-marketplace.dist/opencode/: generated OpenCode mirror. Regenerate withbin/build-opencode-mirror. CI fails if either generated tree drifts from source.bin/compute-catalog-state: canonical implementation of the marketplace catalog state tag (metadata.versioninmarketplace.json). Consumed bybin/validate-pluginsand.github/workflows/release.yml.bin/version-audit,bin/validate-plugins,bin/validate-json: pre-merge validation.docs/plans/: planning documents.docs/plans/done/is a historical archive and may not match current code.
Plugin layout
A typical skill plugin looks like:
plugins/commit/
├── .claude-plugin/
│ └── plugin.json
├── README.md
└── skills/
└── commit/
└── SKILL.md
Skills with longer reference material add a references/ subdirectory:
plugins/handle-secrets/
├── .claude-plugin/
│ └── plugin.json
├── README.md
└── skills/
└── handle-secrets/
├── SKILL.md
└── references/
├── anti-patterns.md
├── checklist.md
└── ...
A hook plugin that targets all three harnesses (Claude Code, Codex CLI, and OpenCode) carries split manifests, harness-specific entry points, and any helper scripts or assets:
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.
- 2d ago First seen · 117 lines · 1,544 tokens per session scan A 04d806bddcc0
agent-harness-plugins AGENTS.md is an instructions file published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,544 tokens to every session, about $0.0077 per session on Opus 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
wispterm AGENTS.md
Instructions for xuzhougeng/wispterm, covering agents.md, architecture, ui presentation styles, cohesion and coupling and integration layer vs feature domains.
moonproxy-desktop AGENTS.md
Instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.
cctop AGENTS.md
Instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
mcp-screenshot-server CLAUDE.md
Instructions for sethbang/mcp-screenshot-server, covering claude.md, what this is, commands, environment variables and architecture.
klaudiush CLAUDE.md
Instructions for smykla-skalski/klaudiush, covering claude.md, project overview, commands, completion (shell completion scripts) and doctor (diagnose setup and configuration).
dev-flow AGENTS.md
Instructions for daphnee-ovo/dev-flow, covering dev-flow plugin, language policy, 注意事项, 命令 and 流程.