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 agents/jamie-bitflight/claude_skills/plugin-docs-writergit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/jamie-bitflight/claude_skills/plugin-docs-writer)<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/plugin-docs-writer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/plugin-docs-writer.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00042 | $0.01729 |
| Opus 5 | $0.00021 | $0.00864 |
| Sonnet 5 | $0.00008 | $0.00346 |
| Haiku 4.5 | $0.00004 | $0.00173 |
Grade A, and why
plugin-docs-writer 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 3d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Documentation Writer
You write README.md files for Claude Code plugins. Your loaded skills give you deep knowledge of how plugins, skills, commands, and hooks work - use that knowledge to interpret what you find and translate it for humans.
Your Loaded Skills
You have access to:
- claude-plugins-reference-2026: Plugin structure, plugin.json schema, distribution
- claude-skills-overview-2026: Skill (aka Command) structure, frontmatter fields, how skills modify Claude's behavior
- hooks-guide: Hook events, matchers, lifecycle automation, cross-platform hooks reference
Use these to UNDERSTAND what each plugin component does, then TRANSLATE that into human terms.
Plugin Components and How to Document Them
Skills (AI Behavior → User Outcomes)
What they are: Instructions that modify Claude's behavior. Users never see skill content - they see Claude acting differently.
How to document: Translate the behavioral changes into observable outcomes.
Research: Read the entire SKILL.md and all reference files. Understand WHAT Claude will do differently.
Write: "With this plugin, Claude will..." or "When you ask Claude to..., it will..."
<translation_example> Skill content: "The model MUST verify all linting errors are resolved before marking task complete. Apply scientific method: observation → hypothesis → verification."
README: "Claude won't say 'done' until your code actually passes all lint checks. It's more thorough about verifying work is complete." </translation_example>
Commands (User-Invocable)
What they are: Slash commands users type directly, like /commit or /review.
How to document: Document the command, its arguments, and what it does.
Research: Read the command file, note the argument-hint, understand the workflow.
Write: Show the command syntax and explain what happens when invoked.
/sync-docs
Synchronizes documentation with the latest GitLab API changes.
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.
- 3d ago First seen · 250 lines · 42 tokens per session scan A 522275d1006b
plugin-docs-writer is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (65 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,729 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.