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/cfircoo/claude-code-toolkit/claude-mdgit clone --depth 1 https://github.com/cfircoo/claude-code-toolkitWhat 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 | $0.00828 | $0.00828 |
| Opus 5 | $0.00414 | $0.00414 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
claude-code-toolkit 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Toolkit Brain — AI Brain
Auto-generated by The AI Brain. Edit .brain/brain.yaml and run
/the-ai-brain:brain-vault-alignto update. Last generated: 2026-03-28
About the Owner
- Name: cfircoo
- Role: Developer / AI tooling builder
- Domain: Claude Code skills, agents, hooks, commands
Vault Structure
Human/— Human-authored content (READ only unless explicitly asked)Human/Daily/— Daily notes (YYYY-MM-DD.md)Human/Projects/— Project filesHuman/Archive/— Completed/archived items
Machine/— AI-managed content (READ and WRITE freely)Machine/Session-Logs/— Session continuity logsMachine/Memory/— Persistent memory (entities, decisions, corrections)Machine/Rules/— Self-updating behavioral rulesMachine/Templates/— Note/project templatesMachine/Canvases/— Obsidian JSON canvas visualizations
Startup Protocol
Before doing ANY work:
- Read
Machine/Rules/active-rules.md - Read
Machine/Memory/context-cache.md - Read the most recent file in
Machine/Session-Logs/ - Read today's daily note if it exists
Obsidian CLI (active — v1.12.7)
On WSL2, obsidian is a wrapper to the Windows Obsidian.com CLI binary.
Prefer CLI commands over raw file reads:
| Task | CLI command | Fallback |
|---|---|---|
| Search vault | obsidian search query=<text> format=json |
Grep files |
| Today's daily note | obsidian daily / obsidian daily:read |
Read file |
| Incomplete tasks | obsidian tasks todo format=json |
Grep - [ ] |
| Find orphans | obsidian orphans format=json |
Manual link scan |
| Get backlinks | obsidian backlinks file=<name> format=json |
Grep [[name]] |
| Open a note | obsidian open path=<path> |
N/A |
Formatting Conventions
- Use [[wikilinks]] for all internal references
- Include YAML frontmatter on every new file
- Date format: YYYY-MM-DD
- Tags in frontmatter arrays:
tags: [tag1, tag2]
Directory Permissions
Human/— READ freely, WRITE only when explicitly askedMachine/— READ and WRITE freely.brain/— READ only (config, do not modify manually)
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 · 76 lines · 828 tokens per session scan A 5a2daca56245
claude-code-toolkit CLAUDE.md is an instructions file published in the GitHub repository cfircoo/claude-code-toolkit (17 stars, last pushed 5mo ago), licensed MIT. It adds 828 tokens to every session, about $0.0041 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 2026-08-30.
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.