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/initgit 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 | $0.01574 |
| Opus 5 | $0.00008 | $0.00787 |
| Sonnet 5 | $0.00003 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade A, and why
init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Project Configuration
Set up a committed .docs-assist/ configuration for this project so Docs Assist matches the project's house style, and so the linters share the same settings.
This earns its keep at every team size: for a team it makes every contributor write to the same conventions, and for a solo maintainer it gives the plugin a consistent line to hold their docs to, like a second reader.
The optional argument ($ARGUMENTS) is the docs directory to use. Detect it if not given.
Process
1. Detect Existing Conventions
Do not ask the user what they could observe yourself. Survey the repo first:
- Find the docs directory (
docs/,documentation/,content/, or the path in$ARGUMENTS). Check static-site config (docusaurus.config.js,mkdocs.yml,astro.config.*,_config.yml) if present. - Read frontmatter from several existing docs to learn the field names in use (
tagsvskeywords,typevscontent-type) and any required SSG fields. - Sample headings to infer heading case (title vs sentence) and whether they are action-oriented.
- Check list markers (
-,*,+) and whether docs use one sentence per line. - Check ordered lists specifically: do they consistently use repeated
1.or true sequential numbering, or is it mixed across files? Both are legitimate; only proposeordered_list_style: repeated-onewhen the corpus actually uses it consistently. If it's mixed, or the corpus has too few ordered lists to tell, say so and default to the more permissivesequential-and-repeated-one-both-allowed reading rather than locking in a style nothing in the repo demonstrated. - Look for an existing linter (
.vale.ini,.markdownlint*,.mega-linter.yml,cspell.json) and record which tool, if any. - Check for
.docs-assist/example-variables.txtor.docs-assist/terms.txt. These predate.docs-assist/reference.ymland the plugin no longer reads them; if either exists, plan to offer a one-time migration in step 4 rather than treating the project as having no registry.
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 · 71 lines · 16 tokens per session scan A 12701a0bbdf8
init 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 1,574 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.