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/geoffjay/claude-plugins/documentationgit clone --depth 1 https://github.com/geoffjay/claude-pluginsWhat 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 | $0.00017 | $0.03404 |
| Opus 5 | $0.00009 | $0.01702 |
| Sonnet 5 | $0.00003 | $0.00681 |
| Haiku 4.5 | $0.00002 | $0.00340 |
Grade A, and why
claude-plugin:documentation 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 — 660 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Generation Command
Regenerate all documentation files (agents.md, agent-skills.md, plugins.md, usage.md) from the marketplace catalog and plugin metadata using Jinja2 templates.
Arguments
$1- Specific file to generate:agents,agent-skills,plugins,usage, orall(optional, defaults toall)$2- Additional options as JSON (optional)
Usage
# Regenerate all documentation files
/claude-plugin:documentation
# Regenerate specific file
/claude-plugin:documentation agents
# Dry run to preview changes
/claude-plugin:documentation all '{"dry_run": true}'
# Specify custom paths
/claude-plugin:documentation all '{"marketplace": ".claude-plugins/marketplace.json", "output": "docs"}'
Workflow
This command orchestrates documentation generation by:
-
Validating Prerequisites
- Verify marketplace.json exists and is valid
- Check template files exist in documentation-update skill
- Ensure plugin directories are accessible
- Verify output directory exists or can be created
-
Preparing Context
- Load marketplace catalog
- Scan all plugin directories
- Extract agent/command/skill metadata
- Build component indexes
- Calculate statistics
-
Generating Documentation
- Invoke documentation-update skill
- Render Jinja2 templates with context
- Write output to docs/ directory
- Report any warnings or errors
-
Verifying Output
- Check all requested files were generated
- Verify file formatting and structure
- Validate links and references
- Report success and statistics
Implementation
Target File: ${1:-"all"} Options: ${2:-"{}"}
Step 1: Validate Prerequisites
Check that all required components exist:
# Check marketplace exists
if [ ! -f .claude-plugins/marketplace.json ]; then
echo "Error: Marketplace file not found at .claude-plugins/marketplace.json"
exit 1
fi
# Check skill exists
if [ ! -f plugins/claude-plugin/skills/documentation-update/doc_generator.py ]; then
echo "Error: Documentation update skill not found"
exit 1
fi
# Check templates exist
if [ ! -d plugins/claude-plugin/skills/documentation-update/assets ]; then
echo "Error: Template directory not found"
exit 1
fi
# Create docs directory if needed
mkdir -p docs
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 · 660 lines · 17 tokens per session scan A 7e582c83d5df
claude-plugin:documentation is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 17 tokens to every session and 3,404 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 2026-08-31.
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.