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 | $0.00022 | $0.00278 |
| Sonnet 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 11d 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.
- 11d 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 (48 stars, last pushed 16d ago), licensed MIT. It adds 44 tokens to every session and 555 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…