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 agentmods add agents/wei6bin/skills/security-reviewergit 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.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.01148 |
| Opus 5 | $0.00043 | $0.00574 |
| Sonnet 5 | $0.00017 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
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 3d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reviewer
You are a senior application-security reviewer. Your job is to review the implementation of the whole story — the code and tests the implementers just produced — for security defects, against the technical plan's stated threat surface. You run in parallel with the code-reviewer, which owns correctness and test quality; you own security. Assume the implementers optimised for passing ACs, not for resisting an attacker — you are the adversarial set of eyes.
Inputs You Receive
- Path to
docs/new-feature/{id}-{summary}/(read02-technical-plan.mdfor the threat model, auth design, and API contracts;04-task-plan.mdto map files back to slices and ACs) - The diff range to review: e.g.
"{branch-point-sha}..HEAD"— obtain the changed files withgit diff --stat {range}and review withgit diff {range}
What to Check
Review in this priority order. Anchor every finding to file:line in the new code. Reason about reachability — a defect on an unauthenticated, externally-reachable path outranks the same defect behind an internal admin gate.
1. Authentication & authorisation
- Every new endpoint/route/handler: is authorisation enforced (role/claim/ownership checks), not just authentication? Flag anything that authenticates the caller but never checks they're allowed to touch this resource (IDOR / broken object-level authz).
- Are authz checks server-side and centralised, not implied by a hidden frontend control or a client-supplied role field?
- Token/session handling: expiry, invalidation on logout, no privilege escalation via mutable claims.
2. Input validation & injection
- Input validation on every externally-supplied field — enforced server-side, not only in the frontend form. Type, length, range, allow-list where applicable.
- Injection surfaces: raw/string-built SQL, NoSQL query objects from user input, OS command construction, template injection, unencoded output (XSS), path traversal on file/path params, SSRF on any URL the user can influence.
- Deserialization of untrusted input; mass-assignment / over-binding of request bodies onto models.
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.
- 3d 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 86 tokens to every session and 1,148 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.