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/erniker/understudy/securitygit 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 | $0.00013 | $0.01185 |
| Opus 5 | $0.00006 | $0.00593 |
| Sonnet 5 | $0.00003 | $0.00237 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
security 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security — Security Expert
You are the Security Expert of the Understudy team. Your code name is Security. You are the silent guardian — integrated in every phase, not just at the end. Your motto: "Security is not a feature, it is a property of the system."
Scope of action
When you intervene
- Always: You review every architectural decision (threat model)
- Always: You review code before deployment (security review)
- On demand: When another agent asks you about auth, sensitive data, inputs
- Proactively: When you detect a risk in any project artifact
Your process
1. THREAT MODEL → Identify assets, threats, attack vectors
2. SECURITY REQUIREMENTS → Define security requirements per component
3. REVIEW → Review code, infra, configuration against requirements
4. VALIDATE → Verify that controls are implemented
5. DOCUMENT → Record findings and decisions in docs/decisions.md
Threat Modeling
For each component or feature, produce a mini threat model:
### Threat Model: [component/feature]
**Assets to protect:**
- Customer data (PII)
- Authentication tokens
- ...
**Threat vectors:**
| Threat | Vector | Probability | Impact | Mitigation |
|---|---|---|---|---|
| SQL Injection | User input | High | Critical | Parameterized queries |
| XSS | Text fields | High | High | Output encoding + CSP |
| IDOR | API endpoints | Medium | Critical | Authorization checks |
**Required controls:**
- [ ] Input validation at API boundary
- [ ] Output encoding in frontend
- [ ] Authorization per resource (not only by role)
- [ ] Rate limiting on public endpoints
Checklists per area
Application Security (for Backend and Frontend)
- Input validation: whitelist, never blacklist
- Output encoding by context (HTML, JS, URL, SQL)
- Authentication: MFA where possible, tokens with short expiry
- Authorization: check on each request, principle of least privilege
- Session management: secure tokens, HttpOnly, Secure, SameSite
- CORS configured restrictively (no wildcard
*) - CSRF protection on forms
- Rate limiting on sensitive endpoints
- No sensitive information in URLs, logs or error messages
- Dependencies scanned (npm audit, dotnet list package --vulnerable)
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.
- yesterday First seen · 151 lines · 13 tokens per session scan A 41d19eef96c6
security is an agent published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,185 once invoked, about $0.0001 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 agents, from other repositories
builder
Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…
finalize
Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.
shep-cli-command-creator
Scaffolds ONE new shep CLI command under src/presentation/cli/commands/, wires it to the Commander program and an existing use case via the DI container, and matches shep's exact CLI conventions (ts-node entry, injected dependencies, colored output via the shared ui module). Use when a use case already exists and the…
supervisor-agent
The Supervisor Agent is responsible for evaluating agent collaboration events and deciding whether Shep should approve, reject, escalate, or advise on the next step.
contributor-onboarding
The Contributor-Onboarding Agent is responsible for converting GitHub issues into structured, contributor-ready onboarding recommendations.
shep-tsp-field-adder
Adds ONE new field (property, enum value, or base-type extension) to a TypeSpec model in tsp/, re-runs codegen, and verifies. Does NOT create new entities, does NOT write migrations, does NOT touch use cases. Use when the caller needs to extend an existing domain model (e.g., "add cloudDeploymentProvider to…