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/edwardangert/docs-agent-plugin/templategit clone --depth 1 https://github.com/EdwardAngert/docs-agent-pluginWhat 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 | $0.00016 | $0.00760 |
| Opus 5 | $0.00008 | $0.00380 |
| Sonnet 5 | $0.00003 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
template 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold a Documentation Template
Give the contributor a proven starting structure instead of a blank page. Built for the moment a support lead, engineer, or PM says "people keep asking about this and we should just write it down."
Templates supplement the content types in ${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/content-types.md; they never replace them.
The full method, including the catalog, selection models, fetch, and fallback, is in ${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/templates.md. Read it before you run this.
Process
1. Turn the Feature On if Needed
Read .docs-assist/templates.yml.
- If it is missing, offer to scaffold it from
${CLAUDE_PLUGIN_ROOT}/assets/config/templates.ymlinto the project's.docs-assist/directory, and setenabled: true. Explain that it is opt-in and fetches template bodies from The Good Docs Project (MIT-0) only when a template is picked. - If it exists but
enabled: false, ask before proceeding, and offer to flip it on.
2. Understand What They Need
Use $ARGUMENTS if given: a problem ("users keep hitting a login loop"), a topic, or a template name ("troubleshooting").
If nothing was passed, ask one question: what is the problem or topic, and what should the reader be able to do afterward.
Do not make them learn template names. Their words are enough.
3. Suggest a Template
Follow the selection model in templates.yml (content-type by default, seven-action if set), using the catalog at ${CLAUDE_PLUGIN_ROOT}/assets/templates/gooddocs-catalog.yml.
- Match their intent to a catalog entry using its
content_type,seven_action, andsignals. - Name the one you suggest and why, in a sentence. Offer the closest alternative when it is a near tie.
- Let them accept, pick another, or decline and use the built-in structure.
4. Fetch and Scaffold
When they accept:
- Fetch the entry's
template_url. Read itsguide_urlwhen you need to understand how a section is meant to be filled. - Produce the doc on that skeleton, filled with what they know, applying
${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/tone-and-voice.md. Adapt the skeleton: drop sections that do not apply, and keep the plugin's formatting rules over the template's. - If the fetch fails, tell them and offer to retry, use the built-in structure, or cancel. Never stop silently.
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 · 58 lines · 16 tokens per session scan A 92571d94a5a0
template is a command published in the GitHub repository EdwardAngert/docs-agent-plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 760 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.