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/orq-ai/assistant-plugins/claude-mdgit clone --depth 1 https://github.com/orq-ai/assistant-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/orq-ai/assistant-plugins/claude-md)<a href="https://agentmods.dev/instructions/orq-ai/assistant-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/orq-ai/assistant-plugins/claude-md.svg" alt="Measured on agentmods" 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 | $0.02641 | $0.02641 |
| Opus 5 | $0.01321 | $0.01321 |
| Sonnet 5 | $0.00528 | $0.00528 |
| Haiku 4.5 | $0.00264 | $0.00264 |
Grade A, and why
assistant-plugins CLAUDE.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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orq-skills — Maintainer Notes
Versioning
This repo follows Semantic Versioning. Version is tracked in 4 plugin manifests that must stay in sync:
plugin.json— portable Agent Plugins 1.0.0 manifest.claude-plugin/plugin.json.codex-plugin/plugin.json.cursor-plugin/plugin.json
When to bump
| Change | Bump |
|---|---|
| Bug fix, typo, small doc tweak | PATCH (0.0.x) |
| New skill, new command, backward-compatible capability | MINOR (0.x.0) |
| Skill removed/renamed, breaking frontmatter change, MCP server URL change | MAJOR (x.0.0) |
Exception: removing shipped content that was never the canonical surface (e.g. stale duplicates tracked outside skills/) is a PATCH, not MAJOR — cleanup is not a breaking change.
How to bump
- Update
versionin all 4 plugin.json files (same value). - Add an entry to
CHANGELOG.mdunder a new## [X.Y.Z] - YYYY-MM-DDheading. Use### Added / Changed / Fixed / Removedsections. - Run
tests/scripts/validate-plugin-manifests.sh— passes. - Commit with message:
chore: bump version to X.Y.Z.
Plugin manifest rules
- All 4 plugin.json
versionfields must match —validate-skills.mjsenforces this in CI. - Root
plugin.jsonis a closed Agent Plugins 1.0.0 manifest: only$schema,name,version,description,author,homepage,repository,license,keywords,extensionsare permitted. Never addskills/mcpServersto it — the spec fixes those locations (skills/,mcp.json). CI validates it withajvagainsttests/schemas/agent-plugins-1.0.0.plugin.schema.json, a vendored copy of the published schema; re-vendor it if the spec revs. - The per-harness manifests cannot be removed yet, and this is not just a scheduling matter. The Codex
interfaceblob (displayName, logo, brandColor, category, privacy/ToS URLs) and Cursor'sdisplayNamehave nowhere to go in the portable manifest: they belong underextensions["<reverse.domain>"], and no client has published a namespace — the spec defines no registry. Until one does, dropping.codex-plugin/or.cursor-plugin/loses store-listing metadata. Do not "finish the migration" without checking that first. - Only the repo root may be an Agent Plugins root. A nested
plugin.jsoncarrying the 1.0.0$schemais rejected by CI — it would re-create theplugins/orqescape (symlinks that stayed inside the repo but left their own plugin root). Client-specific manifests (.claude-plugin/,.codex-plugin/,.cursor-plugin/,plugins/trace-hooks/) are unaffected; they are matched by$schema, not filename. mcp.json,.claude-plugin/.mcp.json,.claude-plugin/skillsare symlinks. Do not replace with copies; every tracked symlink must resolve inside the repo root (CI enforces).- New skill = add to:
skills/<name>/SKILL.md,agents/AGENTS.md(path list +<available_skills>block),README.mdskills table,tests/skills.md(smoke tests + Critical Files), andskills-lock.json(see below). All five are enforced byvalidate-skills.mjs: each surface is diffed againstskills/in both directions, each must list a skill exactly once, and where the surface carries a target path (theAGENTS.mdpath list, theREADME.mdtable's[SKILL.md](…)link) the label and the target must agree — a registration pointing at another skill's file passes a name diff while every harness loads the wrong file. A missing surface file, or aREADME.mdthat has lost its table markers, is an error rather than a skipped check. One half is deliberately not covered:tests/skills.mdis checked for a## \`` smoke-test section per skill, but its "Critical Files" list is free prose and nothing verifies a skill appears there — add it by hand.
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 · +2 lines · +87 tokens per session ec952e6aee56
- 4d ago First seen · 90 lines · 2,554 tokens per session scan A 5d8d5dde8596
assistant-plugins CLAUDE.md is an instructions file published in the GitHub repository orq-ai/assistant-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 2,641 tokens to every session, about $0.0132 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.