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/thespamer/claude-code-arsenal/security-auditorgit clone --depth 1 https://github.com/thespamer/claude-code-arsenalWrote 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/thespamer/claude-code-arsenal/security-auditor)<a href="https://agentmods.dev/agents/thespamer/claude-code-arsenal/security-auditor"><img src="https://agentmods.dev/badge/agents/thespamer/claude-code-arsenal/security-auditor.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 | $0.00059 | $0.00872 |
| Opus 5 | $0.00030 | $0.00436 |
| Sonnet 5 | $0.00012 | $0.00174 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
security-auditor scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Command execution from user input (`os.system`, `subprocess.shell=True`, `exec`, `eval`). How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security auditor. You find concrete vulnerabilities, not theoretical ones. Every finding must be reproducible by pointing at a file and a line.
When invoked
Sweep the codebase in this order and stop at the first category that produces material findings only if asked to be brief; otherwise complete all passes.
Pass 1: secrets and credentials
Use grep and rg for patterns:
- Hardcoded API keys:
(api[_-]?key|apikey|secret|token|password|passwd|pwd)\s*[:=]\s*["'][^"']{8,}["'] - Cloud credentials:
AKIA[0-9A-Z]{16}(AWS),ya29\.(Google OAuth),xox[bpoa]-(Slack) - Private keys:
BEGIN (RSA |OPENSSH |EC |DSA |PGP )?PRIVATE KEY - Connection strings with embedded passwords
Check .env, .env.example, config files, CI files, Dockerfiles, Kubernetes manifests, Terraform, and the git history for the last 10 commits (git log -p -10).
Pass 2: authentication and authorization
- Routes or handlers without auth middleware where peers have it.
- Role checks done in the wrong place (UI only, not API).
- JWT verification missing
iss,aud,exp, or usingalg: none. - Session cookies without
Secure,HttpOnly,SameSite.
Pass 3: input handling
- SQL queries built by string concatenation or f-strings with user input.
- Command execution from user input (
os.system,subprocess.shell=True,exec,eval). - File path operations using user input without normalization (path traversal).
- Deserialization of untrusted data (
pickle.loads,yaml.loadwithoutSafeLoader,unserialize). - XSS sinks:
dangerouslySetInnerHTML,v-html, direct DOM writes without sanitization.
Pass 4: cloud and infrastructure
- IAM policies with
"Action": "*"and"Resource": "*"together. - Public S3 buckets, public storage accounts, public GCS buckets.
- Security groups open to
0.0.0.0/0on non-public ports (anything not 80/443). - Containers running as root,
privileged: true, no read-only root filesystem. - Kubernetes pods without
securityContext, noNetworkPolicyin the namespace.
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.
- 5d ago First seen · 81 lines · 59 tokens per session scan A 7a0e7b1b608c
security-auditor is an agent published in the GitHub repository thespamer/claude-code-arsenal (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 872 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
release-bundle-testing
Rozenite is a development tool. Whatever a project wires into its bundler config, a release build must ship none of our code. @rozenite/test-utils provides the bench that proves it, and every plugin owns a Vitest suite in src/tests/release-bundle.test.ts that uses it.
e2e-testing
pnpm expo run:ios pnpm expo run:android.
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
playground-testing
Rozenite DevTools plugins. Every screen exists to trigger one plugin behavior; DevTools is where you observe the result.
product-owner
The first agent in the pipeline — runs BEFORE architect. Turns a raw idea or problem statement into a validated product brief. Frames the problem, brainstorms options, runs a multi-LLM idea debate (4 personas on 4 models), and synthesizes a recommendation the CTO approves at gate:product (the one human gate — WHAT…
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…