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/baleen37/bstack/claude-mdgit clone --depth 1 https://github.com/baleen37/bstackWhat 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 | $0.01152 | $0.01152 |
| Opus 5 | $0.00576 | $0.00576 |
| Sonnet 5 | $0.00230 | $0.00230 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
bstack 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 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
me
Purpose
bstack - AI 코딩 어시스턴트 툴킷 (Claude Code, Codex)
AI 보조 개발을 위한 도구들을 제공하며, 반복적 자기 참조 AI 개발 루프(Ralph Loop), Git 워크플로우 보호, 개인용 개발 워크플로우 자동화 등의 기능을 포함합니다.
Key Files
| File | Description |
|---|---|
package.json |
Project dependencies and scripts (commitizen, husky, semantic-release) |
.releaserc.js |
Semantic-release configuration synchronizing marketplace.json and all plugin versions |
CLAUDE.md |
Project guidance for AI coding agents (architecture, commands, guidelines) |
README.md |
Project overview and documentation |
.pre-commit-config.yaml |
Pre-commit hooks configuration (YAML, JSON, ShellCheck, markdownlint, commitlint) |
.commitlintrc.js |
Commitlint configuration for Conventional Commits |
.gitignore |
Git ignore patterns |
Subdirectories
| Directory | Purpose |
|---|---|
plugins/ |
Plugin sources, one subdirectory per plugin (me, slack, notion, datadog, autoresearch); each holds its own agents/, hooks/, skills/, and .claude-plugin/plugin.json |
scripts/ |
Utility scripts (handoff, conflict checks, PR verification) |
.claude-plugin/ |
Marketplace configuration (marketplace.json) listing all plugins |
.github/ |
GitHub Actions workflows and custom actions (see .github/AGENTS.md) |
tests/ |
BATS test suites (see tests/AGENTS.md) |
schemas/ |
JSON schemas for validation (see schemas/AGENTS.md) |
docs/ |
Development and testing documentation (see docs/AGENTS.md) |
.claude/ |
Claude Code session data |
For AI Agents
Agent Compatibility
- Claude Code and Codex compatibility is a required baseline. Preserve both when changing project guidance, plugin metadata, skills, hooks, or validation scripts.
- Treat this file as provider-neutral project guidance. It must remain usable by Claude Code, Codex, and future LLM coding agents.
- Keep durable project rules in this file. Keep provider-specific glue in thin adapter files only when a provider requires different filenames, tool names, or invocation syntax.
- Do not duplicate architecture, workflow, or command guidance across agent-specific files. Link or mirror only the minimum needed for compatibility.
- When adding new guidance, prefer capability-based wording such as "AI agents", "coding agents", or "LLM providers" unless the rule is truly specific to Claude Code or Codex.
- If a rule depends on a provider feature, include the generic intent first and the provider-specific mechanism second, so other providers can map it later.
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 · 100 lines · 1,152 tokens per session scan A e661261103cc
bstack CLAUDE.md is an instructions file published in the GitHub repository baleen37/bstack (4 stars, last pushed 12d ago), licensed MIT. It adds 1,152 tokens to every session, about $0.0058 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
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.
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).
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.