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 skills add jezweb/vite-flare-starter --skill review-outputgit clone --depth 1 https://github.com/jezweb/vite-flare-starterWrote 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/skills/jezweb/vite-flare-starter/review-output)<a href="https://agentmods.dev/skills/jezweb/vite-flare-starter/review-output"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/review-output/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/skills/jezweb/vite-flare-starter/review-output"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/review-output.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 40 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00044 | $0.00555 |
| Opus 5.5 | $0.00018 | $0.00222 |
| Sonnet 5.5 | $0.00009 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
review-output 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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review criteria — generic quality bar
Use these criteria when reviewing the worker's draft. Issue exactly one verdict per iteration:
- APPROVE — passes all checks cleanly. Ship it.
- REVISE — 1-2 specific fixable issues. Be concrete: "the second paragraph claims X but the source says Y" not "make it better".
- REJECT — fundamentally wrong shape. Examples: answered the wrong question, wrong format, contradicts the task entirely. Use sparingly; most issues are revisable.
Checks
-
Accuracy — every factual claim is grounded in the provided context or independently verifiable. No invented stats, dates, names, URLs, or quotes. If the worker hedged ("approximately", "in some cases") that's fine; if they stated as fact something not in the source, that's REVISE.
-
Matches intent — does this actually answer what the user asked for, not the adjacent question? An email asking for a refund should request a refund, not apologise. A code review should flag bugs, not document the code.
-
Tone matches situation — formal email needs formal language; internal Slack message can be casual. Look for tone mismatches that would jar the recipient.
-
No hallucinations — invented references, made-up function names, fake API endpoints, fictional people. These are always REVISE — the worker can usually fix by removing the offending claim.
-
Clarity — could a reasonable reader act on this without asking questions? Vague references ("the thing we discussed"), undefined terms, missing context — REVISE.
-
Length appropriate to task — a one-line summary task should produce a one-liner, not a paragraph. A detailed report should not be three sentences. Both directions are REVISE.
Verdict format
Respond with ONE LINE in this exact shape:
VERDICT: APPROVE — passes all checks
VERDICT: REVISE — second paragraph claims 23% growth but source says 18%
VERDICT: REJECT — answered "what's our pricing" instead of "draft a thank-you email"
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.
- 1mo ago First seen · 59 lines · 44 tokens per session scan A 9573c9e5431f
review-output is a skill published in the GitHub repository jezweb/vite-flare-starter (49 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 555 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…