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/agent-readygit 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 | $0.00027 | $0.00799 |
| Opus 5 | $0.00014 | $0.00400 |
| Sonnet 5 | $0.00005 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
agent-ready scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make the Docs Agent-Ready
Make this repository's documentation legible to AI tools: coding agents, docs assistants, and search systems that read structure before prose.
Readers are no longer only human.
An agent answering questions about this project will do it well or badly depending on whether the docs have a map (llms.txt), per-doc metadata (frontmatter), and consistent conventions it can rely on.
This command retrofits all three onto an existing docs set.
The optional argument ($ARGUMENTS) is the docs directory. Detect it if not given.
Process
1. Survey the Docs Set
- Resolve
.docs-assist/config if present. - Inventory the docs: paths, titles, and what frontmatter each already carries.
- Learn the repo's frontmatter field names and any SSG-required fields, per
${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/frontmatter-spec.md. The repo's conventions win; never fight the build system.
2. Create or Repair llms.txt
llms.txt is the map an AI tool reads first. The format, ordering, and maintenance contract are single-sourced in ${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/llms-txt.md; follow it exactly.
- Missing: generate one to that spec: the H1 project name, the blockquote summary, then sections of
- [title](path): descriptionentries in reader-priority order. - Present: reconcile it against the docs. Add missing entries, remove entries whose files are gone, fix titles, descriptions, and paths that drifted, and restore reader-priority order where it decayed.
- Reserve a section named
Optionalfor genuinely skippable depth (the convention gives that name meaning to AI readers); use descriptive names for everything else. - For a small set, offer the
llms-full.txtcompanion per the reference.
3. Complete the Frontmatter
For each doc missing required metadata, add it using the repo's field names:
title,description, and the content-type field at minimum;audienceand keywords where the content makes them clear.- Never overwrite an existing field, and never remove or reorder SSG-required fields.
- Derive values from the doc's own content. Where a doc is too ambiguous to describe honestly, flag it for its owner instead of inventing a description.
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 · 56 lines · 27 tokens per session scan A 865b1b497933
agent-ready is a command published in the GitHub repository EdwardAngert/docs-agent-plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 799 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.