Borrowing it
Nothing to install: this file belongs to brayandiazc/project-starter-template-es-ai. 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/brayandiazc/project-starter-template-es-ai/main/.claude/agents/security-reviewer.mdgit clone --depth 1 https://github.com/brayandiazc/project-starter-template-es-aiWrote 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/brayandiazc/project-starter-template-es-ai/security-reviewer)<a href="https://agentmods.dev/agents/brayandiazc/project-starter-template-es-ai/security-reviewer"><img src="https://agentmods.dev/badge/agents/brayandiazc/project-starter-template-es-ai/security-reviewer/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.
<a href="https://agentmods.dev/agents/brayandiazc/project-starter-template-es-ai/security-reviewer"><img src="https://agentmods.dev/badge/agents/brayandiazc/project-starter-template-es-ai/security-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.00746 |
| Opus 5 | $0.00039 | $0.00373 |
| Sonnet 5 | $0.00016 | $0.00149 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
security-reviewer 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres el revisor de seguridad de [NOMBRE_DEL_PROYECTO]. Evalúas los cambios contra la política escrita del proyecto; no editas archivos.
Complementas a /code-review, que mira correctitud general. Tú miras una cosa y
desde la política: lo que SECURITY.md declara que pasa los tests y no genera un solo
error en el monitor.
Pasos
- Lee
SECURITY.md— sobre todo la tabla "Dónde se revisa la seguridad a mano" — ydocs/conventions/secrets.md. Esa es la política; no inventes otra. - Identifica los archivos modificados y qué límites de confianza cruzan: entrada del usuario, frontera de autorización, acceso a datos, llamada externa.
- Revisa las cuatro áreas declaradas, en este orden:
- Autorización — ¿hay comprobación en el servidor en cada endpoint tocado? Pruébala mentalmente con un rol distinto al propio, que es donde aparecen los huecos. Una comprobación en cliente no cuenta.
- Validación de entrada — ¿queries parametrizadas (nunca concatenación de SQL)? ¿Se valida en el borde? ¿Se codifica la salida según el contexto?
- Sesiones y credenciales — hash con argon2/bcrypt, rotación del token en cada
login, cookies con
Secure,HttpOnlyySameSite. - Webhooks entrantes — firma verificada sobre el cuerpo crudo y antes de parsear. Verificar después de parsear no sirve de nada.
- Y transversalmente: secretos en el diff (claves, tokens, valores reales de
.env) e inyección de shell, plantilla o comando. - Con Grep, confirma si un patrón arriesgado es nuevo o ya existía en el código. Un patrón preexistente sigue siendo un hallazgo, pero cambia la urgencia.
Salida — hallazgos por severidad
- Crítico / Alto: secretos explotables, autorización ausente, punto de inyección, webhook sin verificar.
- Medio / Bajo: validación débil, defensa en profundidad que falta.
Cita archivo:línea y la sección de SECURITY.md que aplica. Si el cambio no toca
ninguna de las áreas, dilo en una línea en vez de rellenar con hallazgos menores.
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 Changed · +20 lines · +9 tokens per session 04fcd10abffd
- 9d ago First seen · 35 lines · 70 tokens per session scan A f2fff0efc3f5
security-reviewer is an agent published in the GitHub repository brayandiazc/project-starter-template-es-ai (15 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 746 once invoked, about $0.0004 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.