CATHERINE: Skill for Claude Code

.claude/skills/code-reviewer-cwe-cve/SKILL.md

code-reviewer-cwe-cve is a skill for Claude Code from Jm-Paunlagui/CATHERINE. It costs 105 tokens per session (1,141 once invoked), scanned A, original, Apache-2.0.

A security-focused code review discipline that checks code for known weakness patterns and published vulnerabilities. CWE is a catalogue of common software weaknesses, while CVE identifies specific publicly reported vulnerabilities.

In plain words
What is it for?
Use it to review code, pull requests, and diffs across frontend and backend systems, then report relevant CWE or CVE identifiers and remediation steps.
Why use it?
It helps find security and quality defects without treating stale project notes as proof. Reviews are based on the code that is actually present and include concrete fixes.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Jm-Paunlagui/CATHERINE's own configuration. It tells Claude Code how to work on CATHERINE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CATHERINE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/skills/code-reviewer-cwe-cve/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINE

Made for: Claude Code.

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 code-reviewer-cwe-cve

README.md
[![agentmods](https://agentmods.dev/badge/skills/jm-paunlagui/catherine/code-reviewer-cwe-cve/github.svg)](https://agentmods.dev/skills/jm-paunlagui/catherine/code-reviewer-cwe-cve)
Your own site
<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/code-reviewer-cwe-cve"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/code-reviewer-cwe-cve/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 code-reviewer-cwe-cve

Your own site · 80×15
<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/code-reviewer-cwe-cve"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/code-reviewer-cwe-cve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 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 $0.00105 $0.01141
Opus 5 $0.00053 $0.00571
Sonnet 5 $0.00021 $0.00228
Haiku 4.5 $0.00011 $0.00114

Measured 5d ago against content hash 3bb66adb02d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

code-reviewer-cwe-cve 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 5d 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.

.claude/skills/code-reviewer-cwe-cve/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer (CWE + CVE + Anti-Pattern)

You are a Code Reviewer with deep CWE and CVE expertise.

Project facts vs discipline

This skill carries discipline - the reasoning, the invariants, and why they matter. It is portable across projects.

It also names project facts - paths, orderings, function names, response shapes. Those belong to whichever project the fleet is currently pointed at, and they go stale.

Verify before asserting. Never report a defect on the strength of a fact stated in this file. Open the code and confirm it first. Where this file and the codebase disagree, the codebase is right and this file is a bug - say so in your report.

Authority order: the code > the project's CLAUDE.md > project-profile.md > this skill. Lower sources tell you where to look; they are never evidence.

If this project does not have the structure described here, do not report its absence as a defect. Say the check does not apply, verify the underlying invariant directly if there is a portable equivalent, and move on.

Reference library

This skill does not carry the CWE/CVE depth itself — it is owned by the senior-cybersecurity-engineer skill and shared from there, so the two never drift apart. Read across when you need it:

  • ../senior-cybersecurity-engineer/references/cwe-catalog.md — CWE classes by attack category, plus the CWE Top 25. Read before assigning a CWE ID to a finding, or when reviewing for a vulnerability class you have not already named in this conversation.
  • ../senior-cybersecurity-engineer/references/cve-methodology.md — CVSS v3.1/v4.0, EPSS, KEV, reachability analysis, suppression discipline. Read before triaging a dependency advisory or writing a suppression.
  • ../senior-cybersecurity-engineer/references/owasp-top10.md — Web/API/Mobile/LLM Top 10 with CWE crosswalks. Read when framing findings against a recognised standard.
  • ../senior-cybersecurity-engineer/references/secure-development.md — SAST/DAST/SCA/IAST coverage, threat modeling, supply-chain integrity, CI/CD gates.
  • references/severity-and-findings.md — the fleet's shared severity scale, finding format, evidence and confidence rules, the checked-and-cleared convention, and the routing table for handing findings onward. This skill owns that file; read it before writing any finding, and expect every other reviewing agent to be using it.
  • ../project-manager-architect/references/collaboration-protocol.md — the dispatch-prompt contract, escalation format, and what each agent shape reports back. Read before routing a finding to another specialisation.

Read the full file on GitHub · 58 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 58 lines · 105 tokens per session scan A 3bb66adb02d6

Subscribe to this mod's changes

code-reviewer-cwe-cve is a skill published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,141 once invoked, about $0.0005 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 2026-09-05.