Borrowing it
Nothing to install: this file belongs to kochetkov-ma/claude-brewcode. 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/kochetkov-ma/claude-brewcode/main/AGENTS.mdgit clone --depth 1 https://github.com/kochetkov-ma/claude-brewcodeWrote 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/kochetkov-ma/claude-brewcode/agents-md)<a href="https://agentmods.dev/instructions/kochetkov-ma/claude-brewcode/agents-md"><img src="https://agentmods.dev/badge/instructions/kochetkov-ma/claude-brewcode/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/kochetkov-ma/claude-brewcode/agents-md"><img src="https://agentmods.dev/badge/instructions/kochetkov-ma/claude-brewcode/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 | $0.01076 | $0.01076 |
| Opus 5.5 | $0.00430 | $0.00430 |
| Sonnet 5.5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
claude-brewcode 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 yesterday.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex workspace
This repository develops four Claude Code plugins: brewcode/ (skill/agent/rule authoring, semantic search, setup skills), brewdoc/ (documentation), brewtools/ (text and ops utilities, manager and subagent-guard setups), and brewui/ (placeholder, no skills). Two Claude Code mods, brewmod-plan-effort/ and brewmod-placeholders/ (TypeScript hooks modules), are Claude Code only: Codex has no mirror for them. Claude product files are a separate compatibility surface.
- Use
gpt-6.1-solfor this workspace. Codex plugins and remote plugins stay disabled; do not install or enable them. - Native instructions: this file and
.codex/rules/; skills:.codex/skills/with discovery aliases in.agents/skills/; agents:.codex/agents/*.toml..codex/plugins/is a generated compatibility mirror, not an active plugin dependency. - Do not configure
CLAUDE.mdas a Codex instruction fallback. Read Claude source files when modifying those products, not as Codex runtime instructions. gh: switch withgh auth switch --user kochetkov-mawhen needed;mkochetkov_tfinhas no repository access.
Native skills
Read the relevant .codex/skills/<name>/SKILL.md before use. Invoke native skills by $name, not Claude slash commands.
| Skill | Use when |
|---|---|
$docs |
Creating, updating, fixing, or reviewing public documentation; mandatory for those changes |
$superreview |
Deep project review |
$brewcode-review |
Reviewing Brewcode product changes |
$memory-sync |
Explicitly requested instruction/memory synchronization |
$claude-plugin-guide |
Looking up Claude Code plugin development contracts |
$update-overview |
Reporting the native static Codex setup inventory |
$eurodns |
Authorized DNS work through EuroDNS |
Rule index
Before work, read each rule whose condition matches; its paths metadata does not enable Codex autoloading. Keep this index synchronized with .codex/rules/*.md.
| Rule | Load when | Purpose |
|---|---|---|
| .codex/rules/avoid.md | Any implementation or validation change | Prevent version drift, destructive edits, and shell failure traps |
| .codex/rules/best-practice.md | Any implementation; Claude product skills/agents; requested releases | Claude product authoring, setup lifecycle, releases, and native execution |
| .codex/rules/docs-workflow.md | Public docs or public behavior changes; requested releases | Mandatory native documentation workflow and exemptions |
| .codex/rules/semble-first.md | Code discovery or search-engine changes | Semantic search when available; exact and exhaustive search boundaries |
| .codex/rules/astro-avoid.md | Astro, MDX, or docs-site changes | Astro and Starlight failure patterns |
| .codex/rules/astro-best-practice.md | Astro, MDX, or docs-site changes | Proven Astro and Starlight patterns |
| .codex/rules/web-accessibility.md | Web UI or docs-site changes | Accessible web content and interaction |
| .codex/rules/docker-avoid.md | Dockerfiles, Compose, or container changes | Container anti-patterns |
| .codex/rules/docker-best-practice.md | Dockerfiles, Compose, or container changes | Container configuration and verification |
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.
- yesterday Changed · +40 tokens per session b60338616ccb
- 3d ago Changed · -3 lines · -95 tokens per session 8491600b8ee7
- 15d ago First seen · 50 lines · 1,131 tokens per session scan A 0c5331be9348
claude-brewcode AGENTS.md is an instructions file published in the GitHub repository kochetkov-ma/claude-brewcode (32 stars, last pushed today), licensed MIT. It adds 1,076 tokens to every session, about $0.0043 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 2026-10-01.
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).