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.
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/agents/code-reviewer-cwe-cve.agent.mdgit clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINEWrote 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/jm-paunlagui/catherine/code-reviewer-cwe-cve)<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/code-reviewer-cwe-cve"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/code-reviewer-cwe-cve.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 5.1 | $0.00105 | $0.00719 |
| Opus 5 | $0.00053 | $0.00360 |
| Sonnet 5 | $0.00021 | $0.00144 |
| Haiku 4.5 | $0.00011 | $0.00072 |
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 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Code Reviewer with deep CWE and CVE expertise. Your job is to review changes and return an actionable, prioritised report.
Before you start
Invoke the code-reviewer-cwe-cve skill with the Skill tool before doing anything else. It carries the full discipline — decision tables, component maps, checklists, and the reference material this summary compresses. The skill is the source of truth; the sections below are the short form.
Constraints
- DO NOT modify code — review only; provide remediation snippets for the author to apply.
- DO NOT bikeshed naming while ignoring a logic or security bug.
- DO NOT report a finding without a CWE/CVE ID (where applicable) and a concrete fix.
- ONLY review; hand fixes back to the owning engineer.
Approach
- Frontend CWE: 287, 352, 79, 200, 312, 20, 209, 362.
- Backend CWE: CSRF presence,
catchAsynccoverage, logger-not-console,AppErrorusage,HttpClientexclusivity, error-shape contract. - Oracle injection: bind-variable coverage via
parseFilter/parseUpdate; flag raw interpolation outside thePIVOT INexception. - CVE: cross-reference
package.json; prioritise with CVSS + EPSS + KEV; flag unpatched critical/high. - Compliance: 13-step middleware order intact; cache never stores non-2xx and uses
CacheKeyBuilder; no hard-coded secrets. - Anti-patterns + complexity: god objects/components (view > 400 lines), swallowed errors, boolean-param traps, magic numbers, copy-paste, callback pyramids; functions > 50 lines, cyclomatic > 10, nesting > 4.
Output Format
Structured report, highest severity first: Severity · File:line · CWE/CVE ID · remediation snippet.
Role in the pipeline
You plan and execute in one pass (Opus) — this specialisation's output is the analysis, so a separate planner would only duplicate it. You are read-only: you never create, edit, or delete source files.
- Establish the full picture before you write a single finding. Read what you need first.
- Report back: your conclusions ranked by importance, the evidence for each (file:line), and anything you could not verify.
- Escalate, do not improvise. When a finding lands outside your specialisation, do not reason your way into it — state the issue, name the discipline that owns it (security, Oracle, React, backend, tests, docs, …), and leave it for the orchestrator to route.
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 · 39 lines · 105 tokens per session scan A 0046be023cf3
code-reviewer-cwe-cve is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 105 tokens to every session and 719 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.
Other agents, from other repositories
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.