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/setup-lintgit 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 | $0.02803 |
| Opus 5 | $0.00014 | $0.01401 |
| Sonnet 5 | $0.00005 | $0.00561 |
| Haiku 4.5 | $0.00003 | $0.00280 |
Grade A, and why
setup-lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up Documentation Linting
Add deterministic documentation linting to this repo. The linters encode the same rules the plugin writes by, so the agent and the checks stay in sync.
Linting is optional and is never bundled. This command only scaffolds it when asked, respects any linter the repo already has, and prefers npx so nothing needs a global install. The optional argument ($ARGUMENTS) names a tool to skip the selection question.
Process
1. Resolve the Project Config
Read .docs-assist/config.yml. The linter config is generated from it, so the checks match how the plugin writes:
heading_case,list_marker,ordered_list_style,no_em_dashes,no_ai_voice, and thefrontmatterfields all map to specific rules.- If
.docs-assist/config.ymldoes not exist, offer to run/docs-assist:initfirst. You can proceed with the defaults, but tell the user the linter will encode defaults, not their conventions.
Also read .docs-assist/reference.yml if it exists. Its term entries (canonical value plus variants) become a generated Vale rule in step 4; the other entry kinds (example-variable, fact, pointer) have no linter equivalent and stay agent-checked.
2. Detect Existing Linters First
Never clobber what is already there. Look for:
.vale.iniand astyles/directory..markdownlint.jsonc,.markdownlint.json,.markdownlint.yaml, or.markdownlint-cli2.*..mega-linter.yml.cspell.jsonorcspell.config.*..markdown-link-check.json..doc-detective.jsonordoc-detective.config.json, or adoc-detectivedependency inpackage.json. Not scaffolded by this command (/docs-assist:verifydetects and uses it directly if present); note it here so the link-check question in step 3 can mention that Doc Detective already covers link validation as part of a verify run, and a separatemarkdown-link-checksetup would be redundant with it.- Lint scripts in
package.json, a.pre-commit-config.yaml, and existing workflows in.github/workflows/.
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.
- 2d ago First seen · 123 lines · 27 tokens per session scan A b638dee51fff
setup-lint 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 2,803 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.