agentmods.dev

secure-review

secure-review is a skill for Claude Code from PacktPublishing/The-Claude-Code-Operating-Model. It costs 23 tokens per session (172 once invoked), scanned A, original, MIT.

A checklist for reviewing code that handles user input, authentication, or database access. It ranks problems by severity and specifies how to report their location, exploit path, and fix.

In plain words
What is it for?
Use it to inspect code for injection, exposed secrets, missing access checks, unsafe shell use, unbounded queries, weak input validation, and leaked stack traces.
Why use it?
It gives security reviews a fixed order and identifies issues that should block a code merge, such as SQL built from user input or missing authorization.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the team-toolkit plugin — 1 skill, 1 command, 1 agent shipped together

not rated 22repo +2 3mo ago A scan 23 tokens original MIT

Good fit Use it to inspect code for injection, exposed secrets, missing access checks, unsafe shell use, unbounded queries, weak input validation, and leaked stack traces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/packtpublishing/the-claude-code-operating-model/secure-review
View source ↗ PacktPublishing/The-Claude-Code-Operating-Model
Install

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.

Any agent
npx skills add PacktPublishing/The-Claude-Code-Operating-Model --skill secure-review
Clone the repo
git clone --depth 1 https://github.com/PacktPublishing/The-Claude-Code-Operating-Model

Made for: Claude Code.

Or install team-toolkit, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

Wrote 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.

agentmods badge for secure-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/packtpublishing/the-claude-code-operating-model/secure-review/github.svg)](https://agentmods.dev/skills/packtpublishing/the-claude-code-operating-model/secure-review)
Your own site
<a href="https://agentmods.dev/skills/packtpublishing/the-claude-code-operating-model/secure-review"><img src="https://agentmods.dev/badge/skills/packtpublishing/the-claude-code-operating-model/secure-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.

agentmods 80×15 button for secure-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/packtpublishing/the-claude-code-operating-model/secure-review"><img src="https://agentmods.dev/badge/skills/packtpublishing/the-claude-code-operating-model/secure-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 172 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00172
Opus 5.5 $0.00009 $0.00069
Sonnet 5.5 $0.00005 $0.00034
Haiku 4.5 $0.00002 $0.00017

Measured 2mo ago against content hash 18a5bd05b17c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

secure-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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

ch09-plugins/team-toolkit/skills/secure-review/SKILL.md · 28 lines

What it actually says

Secure review checklist

Walk the change against this list, in order. Stop and report as soon as you find a Critical item — it blocks the merge.

Critical

  • Any SQL built by string concatenation with user input
  • Secrets committed in source, config, or test fixtures
  • A state-changing endpoint with no authorization check

High

  • User input reaching a shell command
  • Unbounded queries (no LIMIT) on user-facing endpoints

Medium

  • Missing input length validation
  • Errors returning stack traces to the client

Report findings as: severity, file:line, exploit path, fix.

Changes

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.

  1. 2mo ago First seen · 28 lines · 23 tokens per session scan A 18a5bd05b17c

Subscribe to this mod's changes

secure-review is a skill published in the GitHub repository PacktPublishing/The-Claude-Code-Operating-Model (22 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 172 once invoked, about $0.0001 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.

Code reviewSecurity
Related

secure-review compared with skills from other repositories

secure-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
secure-reviewPacktPublishing/The-Claude-Code-Operating-ModelSkill223mo agoMITA23Claude Code
autoreviewopenclaw/clawhubSkill9.5ktodayMITA17Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k4d agoMITA115Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermesSkill5.3ktodayMITA49Claude Code, Codex
revdiff-planumputun/revdiffSkill949yesterdayMITA84Claude Code
re0-mergeLilMGenius/paperthinSkill1.4kyesterdayMITA51Claude Code, Codex
explore-unknownsdzhng/skillsSkill1.5k2d agoMITA162Claude Code, Codex