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 tmj-90/gaffer --skill security-reviewgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/security-review)<a href="https://agentmods.dev/skills/tmj-90/gaffer/security-review"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/security-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/skills/tmj-90/gaffer/security-review"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/security-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 | $0.00099 | $0.01678 |
| Opus 5.5 | $0.00040 | $0.00671 |
| Sonnet 5.5 | $0.00020 | $0.00336 |
| Haiku 4.5 | $0.00010 | $0.00168 |
Grade A, and why
security-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 16d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security review lens
Security defects are the most expensive to miss and the easiest to skim past, because the code works. Walk the diff against this checklist, organised by OWASP ASVS 5.0 chapter. A finding is a concrete, reachable defect — a source (input an attacker controls), a sink (where it does harm) and the missing control between them — never a hardening wish.
Steps
- Map the attack surface of the diff. New inputs (params, headers, bodies, files,
messages, env, webhook payloads), new data read or written, new outbound calls, new
privileges or roles. If the diff touches none, write "no new attack surface" and stop.
Call
search_lorefor the repo's security conventions and past incidents. - Trace each input to its sinks by opening the files: query builders, shell/exec, templates, file paths, URL fetchers, deserialisers, redirects, authorisation checks. Walk only the checklist sections those sinks need.
- For each item write "n/a", "ok — ", or a finding with file, line, attacker, input, impact and the single concrete fix.
- Rate each finding. Blocking: exploitable by an unauthenticated or ordinary user,
leaks data, or bypasses a control. Should-fix: exploitable only with elevated access or
in combination. Note: hardening with no exploit path. Only blocking and should-fix
justify
RECOMMEND CHANGES; notes are "(optional)". - Record each finding with
record_ac_evidence(evidence_type: manual_note: the checklist item, file, line, severity, fix). As a lens inside the primary review, thereview-ticketverdict carries the result. As the second-opinion security reviewer, you give the verdict: RECOMMEND CHANGES for any blocking or should-fix finding, else RECOMMEND APPROVE, then as the very last line, alone, exactly{"verdict":"CHANGES"}or{"verdict":"APPROVE"}; do not run tests or the build, and stay under 12 tool calls. Never fix the code yourself. Read the diff once and open only the files it touches.
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.
- 16d ago Changed · +25 lines · +3 tokens per session 207a8a2d38e8
- 19d ago First seen · 78 lines · 96 tokens per session scan A b846f149dfe0
security-review is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,678 once invoked, about $0.0004 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 skills, from other repositories
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.
spec-drift-check
Audits a WP brief for drift against current code — extracts claims, verifies each, emits PROCEED/STOP verdict. Use when starting a new WP, before consuming a spec as binding, or when a doc references paths/lines/functions.
besimple-broccoli-blind
Non-interactive wrapper: plan-sketch -> auto-pick recommended options -> plan-write -> plan-critique-loop -> implement-from-plan -> claude-simplify-wrapper -> dedup -> code-review-loop. No PR creation and no Linear comments.
code-review-loop
Iterative review+fix loop for BASESHA..HEAD: generate findings, apply accepted fixes, run checks, commit, and re-review up to 3 iterations or until clean.
dedup
Dedupe-only pass for BASESHA..HEAD: remove duplicate code introduced by the diff or reuse existing shared utils; applies changes + commits.