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/unclecode/claude-code-tools/pp-fetch-docsgit clone --depth 1 https://github.com/unclecode/claude-code-toolsWhat 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 | $0.00000 | $0.01747 |
| Opus 5 | $0.00000 | $0.00873 |
| Sonnet 5 | $0.00000 | $0.00349 |
| Haiku 4.5 | $0.00000 | $0.00175 |
Grade C, and why
pp-fetch-docs scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Delete old docs: `rm -rf api-docs/{library}/` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X GET "https://context7.com/api/v1/search?query={library}" \ How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fetch API Documentation
Fetch and cache API documentation in AI-readable markdown format.
Arguments
$ARGUMENTS
Library name, URL, or package identifier (e.g., "openai", "stripe", "https://docs.stripe.com")
Purpose
Download and cache API documentation locally for quick reference across all projects. Docs are stored globally in the plugin directory and available in all chat sessions.
Storage Location
Global (available across all projects):
~/.claude/plugins/marketplaces/unclecode-tools/plugins/unclecode-cc-toolkit/api-docs/
Execution Instructions
Step 1: Parse Input
Extract from query:
- Library name (e.g., "openai", "stripe", "nextjs")
- URL (if provided, e.g., "https://docs.stripe.com")
- Version (optional, e.g., "[email protected]")
Normalize library name:
- Remove special characters
- Convert to lowercase
- Remove version suffix for directory name
Step 2: Check if Docs Exist
Check for existing documentation:
ls ~/.claude/plugins/marketplaces/unclecode-tools/plugins/unclecode-cc-toolkit/api-docs/{library}/
If directory exists:
- List what's there:
ls -lah api-docs/{library}/ - Show last modified date
- Ask user:
## Documentation Exists
**Library**: {library}
**Location**: api-docs/{library}/
**Last Updated**: {date from stat}
**Files**: {file count} files, {total size}
Documentation already cached. Would you like to:
1. Use existing docs (skip)
2. Update/re-fetch docs
3. View what's cached
Wait for user response.
If doesn't exist:
- Proceed to Step 3
Step 3: Fetch Documentation
Try these methods in order:
Method 1: Context7 API
If library name provided (no URL):
# Search for library
curl -X GET "https://context7.com/api/v1/search?query={library}" \
-H "Authorization: Bearer CONTEXT7_API_KEY"
# Get library ID from response
# Then fetch docs
curl -X GET "https://context7.com/api/v1/{library_id}/docs?type=txt&tokens=5000" \
-H "Authorization: Bearer CONTEXT7_API_KEY"
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 · 271 lines · 0 tokens per session scan C f753134ee040
pp-fetch-docs is a command published in the GitHub repository unclecode/claude-code-tools (4 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,747 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.