Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pau-vega/Devkit-AI/plugin install jsdoc-standardsWrote 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/commands/pau-vega/devkit-ai/jsdoc-review)<a href="https://agentmods.dev/commands/pau-vega/devkit-ai/jsdoc-review"><img src="https://agentmods.dev/badge/commands/pau-vega/devkit-ai/jsdoc-review.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 5.1 | $0.00052 | $0.00463 |
| Opus 5 | $0.00026 | $0.00231 |
| Sonnet 5 | $0.00010 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
jsdoc-review 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 6d 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.
What it actually says
JSDoc Review
Dispatch the jsdoc-reviewer agent to audit TypeScript files for JSDoc compliance.
Arguments: $ARGUMENTS
Argument Parsing
Parse the arguments to extract the enforcement level and optional path:
- No arguments — use
standardlevel, review changed files - Level only (e.g.,
strict) — use that level, review changed files - Level and path (e.g.,
standard src/utils) — use that level, review files at path - Path only (e.g.,
src/utils) — usestandardlevel, review files at path
Valid levels: minimal, standard, strict.
Execution
- Load the jsdoc-conventions skill from
${CLAUDE_PLUGIN_ROOT}/skills/jsdoc-conventions/SKILL.mdto get the full rule set - Determine the enforcement level from arguments (default:
standard) - Discover target
.tsand.tsxfiles:- If a path was provided, glob for files at that path
- If no path, run
git diff --name-only HEADto find changed files - If no uncommitted changes, run
git diff --name-only HEAD~1for the last commit - Filter for
.tsand.tsxfiles only
- Read each file and check against the rules for the selected level
- Report findings grouped by file, using severity levels:
- Error — Required JSDoc is completely missing
- Warning — JSDoc is present but incomplete or malformed for the level
- Suggestion — Opportunity to improve documentation quality
- End with a summary: total files reviewed, errors, warnings, suggestions, and the level used
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.
- 6d ago First seen · 44 lines · 52 tokens per session scan A ba0579d5ffc9
jsdoc-review is a command published in the GitHub repository pau-vega/Devkit-AI (2 stars, last pushed 21d ago), licensed MIT. It adds 52 tokens to every session and 463 once invoked, about $0.0003 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
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
spec
Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
tdd
Test-driven development with tests that actually catch breaks: red before green, name the break each test catches, and the mutation check before done.