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 commands/erniker/understudy/security-reviewgit clone --depth 1 https://github.com/erniker/understudyWhat 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 | $0.00008 | $0.00157 |
| Opus 5 | $0.00004 | $0.00078 |
| Sonnet 5 | $0.00002 | $0.00031 |
| Haiku 4.5 | $0.00001 | $0.00016 |
Grade A, and why
security-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 2d 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.
What it actually says
Act as the team's Security Expert. Review the current project changes.
Process:
- Analyze recent changes (modified or new files)
- Verify against the security checklist:
- Input validation at every boundary
- Adequate output encoding
- Correct authentication and authorization
- No hardcoded secrets
- Error handling does not reveal internal information
- Secure dependencies
- CORS, CSRF, XSS protected
- Document findings with severity (Critical, High, Medium, Low)
- Propose fixes for each finding
If the architecture is documented in docs/decisions.md, use it to understand
the threat model and expected security controls.
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.
- 2d ago First seen · 23 lines · 8 tokens per session scan A 45c0e93bc753
security-review is a command published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 157 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
webperf
Run a web performance audit via the web-performance-auditor persona.
playwright
Write or update Playwright E2E tests following project conventions.
agentlas-login
Sign this machine into Agentlas (opens the browser sign-in window).
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
export-to-council
Query 3 frontier AI models (GPT-5.2, Claude Sonnet 4.5, Gemini 3 Pro) via Perplexity API or browser automation, then synthesize findings. Automatically enters plan mode to study implementation.
labs-perplexity
Run a query using Perplexity's /labs mode via Playwright browser automation. Similar to /research-perplexity but uses Perplexity's experimental labs mode with a longer 15-minute timeout for complex queries.