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 juanmhidalgo/claude-plugins/plugin install feature-devWrote 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/juanmhidalgo/claude-plugins/review)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/review"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/review"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00068 | $0.02332 |
| Opus 5.5 | $0.00027 | $0.00933 |
| Sonnet 5.5 | $0.00014 | $0.00466 |
| Haiku 4.5 | $0.00007 | $0.00233 |
Grade A, and why
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 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Artifact argument: $ARGUMENTS
- Feature store: each feature lives in
.feature-dev/features/<slug>/, managed by${CLAUDE_PLUGIN_ROOT}/scripts/features.py(pass--root <repo root>). Layout: artifact-locations.md.
The review happens in a local page instead of the chat. Specs and plans of 332–1073 lines were approved 37–72 s after being written, from chat summaries, and nobody opened the files; the page puts the document, its decisions and its changes since the last version in front of the reviewer, and turns what they mark into a file this command applies.
The page is served by review_server.py on 127.0.0.1, on a random free port. It uses the Python 3 standard library only and loads nothing from the network: no CDN, fonts or external scripts, so it is safe on proprietary repos.
Phase 0: Resolve the artifact
- If
$ARGUMENTSis#N,owner/repo#N, or an issue URL → resolve it per issue-store.md's Argument parsing, then run issue-store.md's Import algorithm against it, start to finish. Do not restate Import's steps here — follow the reference. A failedghpreflight, or a failedgh issue viewcall, stops here and names the issue that could not be read. On success, continue as if$ARGUMENTShad been the resulting spec path (the reference's own step 6). An issue argument only ever produces a SPEC — there is no PLAN equivalent. - If
$ARGUMENTSnames an existing file → use it. If it does not exist, STOP and report. An artifact of this repo must sit in.feature-dev/features/<slug>/; refuse any other path (a rootSPEC-*.md, or the layout older than 2.0.0) in one line and name.feature-dev/features/<slug>/as the only place artifacts live. - If
$ARGUMENTSis empty → run${CLAUDE_PLUGIN_ROOT}/scripts/features.py list --json --root <repo root>and collect theartifactsof every feature (each haskind,path,needs_review). A missing.feature-dev/features/is an empty list. 0 → STOP and point to/feature-dev:spec. 1 → use it. 2+ → AskUserQuestion (label = file name, description = the feature's slug andstatus; put artifacts withneeds_reviewfirst). - The kind is SPEC or PLAN, from the file name prefix (or the
kindin the list). The feature slug is its folder name under.feature-dev/features/. Do not derive review paths yourself: every file path below comes from the scripts. - If the project's
.gitignoredoes not include.feature-dev/, add it. It holds the feature store, review files and version history: all local working artifacts.
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 Changed · +1 lines 8a13f7c5409b
- 14d ago Changed · +1 lines a76eb153098a
- 18d ago Changed · +6 lines 779a035dbcfb
- 19d ago First seen · 96 lines · 68 tokens per session scan A fd342ca24b3b
review is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 2,332 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-28.
Other commands, from other repositories
Captures the current page in tandem's Chrome as a PDF (if headless Chrome) or full-page PNG screenshot (in normal tandem mode). Saves to /.claude/tandem/output/.
browse
Generate a single-file markdown browser HTML — tree sidebar + marked.js render. Scans project docs/ + /.claude/{plans,projects} by default.
screenshot
A macOS-only command that captures a window, the full screen, or a selected area and then makes the image available for analysis. It uses macOS’s built-in screencapture tool and does not itself take a screenshot without being asked.
view-document
Open Trio wiki in the browser, rooted at the current working directory. Auto-invoke when the user asks to open their Markdown wiki, browse notes, or view the current folder as a wiki.
scrape
Scrape one or more web pages to clean Markdown.
brand-generate
Generate an on-brand document from a saved Brand Profile.