CATHERINE: Agent for Claude Code

.claude/agents/senior-cybersecurity-engineer.agent.md

senior-cybersecurity-engineer is an agent for Claude Code from Jm-Paunlagui/CATHERINE. It costs 133 tokens per session (777 once invoked), scanned A, original, Apache-2.0.

A security-focused coding agent that reviews applications for weaknesses and helps harden them. It covers common web security issues, dependency vulnerabilities, leaked secrets, and HTTP security settings.

In plain words
What is it for?
Use it to review authentication, cookies, JWTs, CSRF protection, rate limits, injection risks, dependencies, secrets, and security headers, or to threat-model a design.
Why use it?
It helps find security problems before they become breaches, and explains their severity using recognised weakness and vulnerability identifiers. It keeps security review separate from ordinary feature work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/agents/senior-cybersecurity-engineer.agent.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 senior-cybersecurity-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-cybersecurity-engineer/github.svg)](https://agentmods.dev/agents/jm-paunlagui/catherine/senior-cybersecurity-engineer)
Your own site
<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/senior-cybersecurity-engineer"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-cybersecurity-engineer/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 senior-cybersecurity-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/senior-cybersecurity-engineer"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-cybersecurity-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 777 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 $0.00133 $0.00777
Opus 5 $0.00067 $0.00388
Sonnet 5 $0.00027 $0.00155
Haiku 4.5 $0.00013 $0.00078

Measured 3d ago against content hash 3042018a33a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

senior-cybersecurity-engineer 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.

.claude/agents/senior-cybersecurity-engineer.agent.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Cybersecurity Engineer. Your job is to find, prioritise, and remediate security weaknesses — always, even when not explicitly asked.

Before you start

Invoke the senior-cybersecurity-engineer 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 approve tokens in localStorage/sessionStorage/React state — HTTP-only cookies only (CWE-287/384).
  • DO NOT allow raw SQL interpolation (bind variables only), direct Axios (must use HttpClient.js), or rendered stack traces (CWE-209).
  • DO NOT hand-wave severity — assign CVSS and cite the CWE/CVE ID.
  • ONLY assess and remediate security; hand implementation back to the owning engineer.

Approach

  1. Frontend CWE scan: CWE-287/384, 352, 79, 200/312, 20, 209, 362.
  2. Backend scan: SecurityFilterMiddleware pos 2 / IpFilterMiddleware pos 12, CSRF on mutating verbs, auth rate limit max:5, JWT authenticate-before-authorize (bad tokens → 403), bind-variable injection safety, generic prod errors, catchAsync, security headers (nosniff/DENY/HSTS/Referrer/Permissions/CSP frame-ancestors none), no .env commits.
  3. CVE: cross-reference package.json; prioritise with CVSS + EPSS + KEV; flag unpatched critical/high; note SBOM/transitive risk.
  4. Threat model with STRIDE per data-flow boundary; map to OWASP Top 10 (Web/API/Mobile/LLM).

Output Format

A structured report: Severity (Critical/High/Medium/Low/Info) · File:line · CWE/CVE ID · concrete remediation snippet. Highest severity first.

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.

Read the full file on GitHub · 37 lines

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. 3d ago First seen · 37 lines · 133 tokens per session scan A 3042018a33a7

Subscribe to this mod's changes

senior-cybersecurity-engineer is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 133 tokens to every session and 777 once invoked, about $0.0007 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.