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-code-securitygit 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-code-security)<a href="https://agentmods.dev/skills/jezweb/vite-flare-starter/review-code-security"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/review-code-security/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-code-security"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/review-code-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00693 |
| Opus 5.5 | $0.00020 | $0.00277 |
| Sonnet 5.5 | $0.00010 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
review-code-security scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `fetch(userProvidedUrl)` without scheme/host validation: REVISE How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code security review criteria
Review the worker's code draft against security + correctness checks. Strict: when in doubt, REVISE rather than APPROVE.
Critical checks (any failure = REVISE)
-
No SQL injection vectors:
- String concatenation into queries: REVISE
- User input passed to
sql.unsafe()without param array: REVISE - Drizzle / parameterised queries: OK
-
No secret leakage:
- Hardcoded API keys, tokens, passwords in the draft: REVISE
- Logging full request bodies that might contain secrets: REVISE
- Returning provider error responses verbatim (often contain API keys in URLs): REVISE
-
Auth checks present:
- Routes that read/write user data must check
c.get('userId')or equivalent - Routes that mutate must check ownership (the row's userId matches the caller's userId)
- Admin-only routes must check role
- Routes that read/write user data must check
-
No prototype pollution:
Object.assign(target, untrustedInput)where target is shared state: REVISE- Deep merges of user input into config: REVISE
-
No SSRF:
fetch(userProvidedUrl)without scheme/host validation: REVISE- URL parsing with allowlist: OK
Quality checks (single failure = REVISE; multiple = REJECT)
-
Error handling at boundaries:
- External fetches wrapped in try/catch
- Returns structured errors (not raw provider responses)
-
No silent failures:
- Empty catch blocks: REVISE
- Errors logged then swallowed without explanation: REVISE
-
Project conventions:
- Uses Drizzle, not raw D1 (where available)
- Uses Hono context, not Express patterns
- Imports from
@/server/...not relative../../../
When to APPROVE
- All 5 critical checks pass
- All quality checks pass or have one minor REVISE-worthy item that was already addressed
When to REVISE
- 1-2 specific issues from the lists above. Be concrete: "line 12
concatenates
userIdinto the query string — switch toeq(table.userId, userId)"
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 · 82 lines · 51 tokens per session scan A 000b3511a022
review-code-security is a skill published in the GitHub repository jezweb/vite-flare-starter (49 stars, last pushed 22d ago), licensed MIT. It adds 51 tokens to every session and 693 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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…