Borrowing it
Nothing to install: this file belongs to DmitriyYukhanov/claude-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/DmitriyYukhanov/claude-plugins/main/AGENTS.mdgit clone --depth 1 https://github.com/DmitriyYukhanov/claude-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/dmitriyyukhanov/claude-plugins/agents-md)<a href="https://agentmods.dev/instructions/dmitriyyukhanov/claude-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/dmitriyyukhanov/claude-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/dmitriyyukhanov/claude-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/dmitriyyukhanov/claude-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 | $0.01217 | $0.01217 |
| Opus 5.5 | $0.00487 | $0.00487 |
| Sonnet 5.5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
claude-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 9d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Plugins Repository
Collection of Claude Code plugins: skills, agents, hooks, and scripts. Issues and PRs live in DmitriyYukhanov/claude-plugins.
Repository hygiene
docs/superpowers/and.serena/are local-only and gitignored. Never commit them.- Stage with explicit paths (
git add <path>), nevergit add -Aorgit add .. - Before committing, run
git diff --cached --name-only; anything under those two directories getsgit restore --staged <path>.
Plugin versioning
Any change under plugins/<name>/ bumps "version" in plugins/<name>/.claude-plugin/plugin.json and the matching entry in .claude-plugin/marketplace.json. The pre-commit hook enforces the bump and its changelog entry only on commits to main or master, and rejects the two manifests disagreeing on any branch; CI checks each PR against its merge base. Bump the version and add the CHANGELOG entry before opening the PR; local development commits may defer that bookkeeping.
Semantic Versioning:
- PATCH (x.y.Z): bug fixes, typos, minor documentation tweaks
- MINOR (x.Y.0): new features, skill improvements, prompt changes, non-breaking additions
- MAJOR (X.0.0): breaking changes to skill behavior, major restructuring, removed functionality
Changelog
Every version bump adds an entry to plugins/<name>/CHANGELOG.md in Keep a Changelog format (Added, Changed, Deprecated, Removed, Fixed, Security). On main the pre-commit hook rejects a bump without one.
Entry rules:
- One short sentence per entry, imperative mood, describing the user-facing outcome: "Add search skill", not "Added search skill".
- No implementation details (step numbers, file names, tool names) and no vague filler ("various improvements").
- Group sub-changes by user-visible outcome. Internal-only changes are not documented.
- Every version header carries an ISO 8601 date:
## [1.2.0] - 2026-04-03. - Write the entry as you make the change, not at release time.
Good: "Cross-validation step: each model verifies the other's findings before presenting to user" Bad: "Cross-validation step (Step 5): after initial triage, each model's findings are verified by the other model before presenting to user, using CONFIRM/REJECT/REFINE verdicts from validation-format.md"
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.
- 9d ago Changed · -5 tokens per session 17b78c57d7c2
- 21d ago Changed · +85 tokens per session 03dba44a23ad
- 26d ago First seen · 108 lines · 1,137 tokens per session scan A 28f46e1c19e7
claude-plugins AGENTS.md is an instructions file published in the GitHub repository DmitriyYukhanov/claude-plugins (8 stars, last pushed 6d ago), licensed MIT. It adds 1,217 tokens to every session, about $0.0049 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 2026-09-21.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).