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 commands/stefan-jansen/claude-code-toolkit/docsgit clone --depth 1 https://github.com/stefan-jansen/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 | $0.00014 | $0.00462 |
| Opus 5 | $0.00007 | $0.00231 |
| Sonnet 5 | $0.00003 | $0.00092 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
docs 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.
What it actually says
Documentation Operations
Input: $ARGUMENTS
Usage
/docs fetch # Fetch official Claude Code & library docs
/docs fetch --force # Force complete re-fetch
/docs fetch --libraries # Focus on project dependency docs
/docs search "command syntax" # Search all cached documentation
/docs generate "Added auth" # Generate/update docs after changes
/docs generate --api # Focus on API documentation
Process
1. Determine Operation
- fetch: Download external documentation to
.claude/docs/ - search: Query cached documentation and library docs
- generate: Create/update project documentation
- No args: Show usage guidance
2. Fetch Operations
- Identify documentation sources (official + dependencies)
- Create/update cache in
.claude/docs/ - Track versions and timestamps
- Create searchable index
With Context7: Auto-detect dependencies → resolve library IDs → fetch version-matched docs
3. Search Operations
- Index search for fast results
- Full-text search across cache
- Rank by relevance
With Context7: Resolve library names → fetch live documentation → return focused results
4. Generate Operations
- Assess existing documentation
- Identify gaps and outdated content
- Generate API docs, README updates, migration guides
- Test code examples
Cache Structure
.claude/docs/
├── official/ # Claude Code documentation
├── libraries/ # Third-party library docs
├── project/ # Project-specific docs
└── cache_metadata.json
MCP Enhancement
Context7 (when available):
resolve-library-id→ find library documentationget-library-docs→ fetch comprehensive docs- Fallback: WebFetch with manual caching
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 First seen · 66 lines · 14 tokens per session scan A 8101ee3e45b3
docs is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 462 once invoked, about $0.0001 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 commands, from other repositories
remember
Save something to agent memory - picks project or user scope automatically from context.
disambiguate-plan
Thorough collaborative planning with iterative disambiguation - resolves all ambiguity before planning.
pr-review
Review a GitHub pull request: analyzes changed files to select relevant reviewers, loads project and user memory, runs reviewers in parallel, lets the user pick which findings to post, then submits the review on behalf of the user via gh CLI.
dataviz
Define chart types, color encoding, and data display conventions.
ship
Pre-launch gate — six-domain checklist before any production deployment.
build
Implement the next ready task from .forge/tasks.yaml using TDD discipline.