Borrowing it
Nothing to install: this file belongs to vladolaru/claude-code-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/vladolaru/claude-code-plugins/main/AGENTS.mdgit clone --depth 1 https://github.com/vladolaru/claude-code-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/vladolaru/claude-code-plugins/agents-md)<a href="https://agentmods.dev/instructions/vladolaru/claude-code-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/vladolaru/claude-code-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/vladolaru/claude-code-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/vladolaru/claude-code-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 | $0.02173 | $0.02173 |
| Opus 5.5 | $0.00869 | $0.00869 |
| Sonnet 5.5 | $0.00435 | $0.00435 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
claude-code-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 4d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
You maintain vladolaru-claude-code-plugins, Vlad Olaru's dual-host (Claude Code and Codex) plugin marketplace. This file holds the repository-wide rules. A plugin with its own AGENTS.md holds that plugin's rules; read it before changing anything under that plugin.
Development Model
This project is AI-written and AI-maintained. The human (Vlad) sets direction, makes architectural decisions, and reviews work. Claude Code agents do the implementation, testing, analysis, and maintenance. "Single maintainer" means a single human decision-maker with AI execution capacity, not limited implementation bandwidth.
No agent carries context between sessions; every agent reads the code cold. So:
- Prefer single canonical implementations over duplicated patterns. An agent copies whichever pattern it meets first, and two conventions for one thing guarantee drift.
- Constants, types, named helpers, and docstrings are the discovery mechanisms. A fact about one module belongs in that module, where an agent reads it for free when the file is open.
- Consolidating duplicated logic is drift prevention, not polish.
What Belongs in an AGENTS.md
These files are the always-on cost of every session, and the longer they get the less of them an agent follows. Codex reads at most 32 KiB across the root-to-cwd AGENTS.md chain and drops the rest; plugins/pirategoat-tools/tests/test_instruction_budget.py enforces ceilings under that line. Keep the test green by moving content, not by compressing wording:
| Content | Lives in |
|---|---|
| A rule an agent would otherwise violate, with one clause of why | AGENTS.md (root for repo-wide, plugin for plugin-wide) |
| A fact about one module: contract, invariants, importers, history | that module's docstring |
| A procedure longer than a few steps, a design record, a CLI manual, a directory layout | plugins/<plugin>/docs/, pointed at from AGENTS.md with the trigger for reading it |
| Which tests a change should run | the plugin's tests/TESTING.md |
| Counts and inventories of commands, skills, agents | .claude-plugin/marketplace.json and the plugin README, never restated here |
| An incident or a lesson | .claude/docs/learnings/ |
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.
- 4d ago Changed · -2 tokens per session 3c954b65d25b
- 1mo ago Changed · -312 lines · -6,488 tokens per session 32d866235632
- 1mo ago Changed · +1 lines · +342 tokens per session a227ea79f39b
- 1mo ago Changed · -13 tokens per session 7ecdbc0361cb
- 1mo ago First seen · 424 lines · 8,334 tokens per session scan A 7d39e2bdb190
claude-code-plugins AGENTS.md is an instructions file published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 4d ago), licensed MIT. It adds 2,173 tokens to every session, about $0.0087 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.
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).