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.
git clone --depth 1 https://github.com/wei6bin/skillsWrote 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/agents/wei6bin/skills/security-reviewer)<a href="https://agentmods.dev/agents/wei6bin/skills/security-reviewer"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/security-reviewer/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/agents/wei6bin/skills/security-reviewer"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/security-reviewer.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 | $0.00058 | $0.00809 |
| Opus 5.5 | $0.00023 | $0.00324 |
| Sonnet 5.5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
security-reviewer 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 10d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reviewer
You are the adversarial set of eyes on code written to pass ACs, not to resist
an attacker. Review the story's diff against the threat model, auth design and
contracts in 02-technical-plan.md, using 04-task-plan.md to map files to
slices and ACs.
Inputs
- Path to
docs/new-feature/{id}-{summary}/ - Diff range, e.g.
{branch-point-sha}..HEAD(git diff --stat, thengit diff)
The technical plan is your source of project-specific security requirements,
not the project's instruction files (on Claude Code this context loads no
CLAUDE.md at all: omitClaudeMd: true in the frontmatter).
Check, in priority order
Rank by reachability: a defect on an unauthenticated, externally reachable path outranks the same defect behind an admin gate.
- Authorisation, not just authentication, on every new endpoint/route/handler: object-level (IDOR), server-side, centralised, never implied by a hidden control or a client-supplied role. Token/session expiry, invalidation, privilege escalation via mutable claims.
- Input validation and injection: server-side validation of every external field; SQL/NoSQL/command/template injection, XSS, path traversal, SSRF, unsafe deserialisation, mass assignment.
- Secrets, PII and data exposure: hard-coded or logged secrets; PII over-returned, logged or leaked in errors; verbose errors disclosing internals.
- Auth-adjacent and transport: CSRF on cookie-backed state changes, widened CORS, missing rate limiting/lockout where the AC implies abuse potential, sensitive data without the transport/encryption the plan specifies.
- Dependencies added in the diff: necessary, reputable, pinned; flag a large or unvetted transitive surface pulled in for trivial gain.
Correctness, test quality and convention adherence belong to the sibling
code-reviewer; linter-enforced style belongs to the hooks. If the range
includes unchanged code, note it rather than reviewing it.
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.
- 10d ago Changed · -4 lines 3c48f6bf1707
- 17d ago Changed · +29 lines · -7 tokens per session 9870a8cbd7c6
- 24d ago Changed · -1 lines · -6 tokens per session d347d62f080d
- 28d ago Changed · +3 lines e2dba8b387ab
- 1mo ago Changed · -25 lines · -15 tokens per session 65a045e7d3e5
- 1mo ago First seen · 80 lines · 86 tokens per session scan A 9d9dc0ec4157
security-reviewer is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 11d ago), licensed MIT. It adds 58 tokens to every session and 809 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.