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/dev-toolings/superpowers-symfony/symfony-security-auditorgit clone --depth 1 https://github.com/dev-toolings/superpowers-symfonyWrote 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/dev-toolings/superpowers-symfony/symfony-security-auditor)<a href="https://agentmods.dev/agents/dev-toolings/superpowers-symfony/symfony-security-auditor"><img src="https://agentmods.dev/badge/agents/dev-toolings/superpowers-symfony/symfony-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 | $0.00060 | $0.00687 |
| Opus 5 | $0.00030 | $0.00344 |
| Sonnet 5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
symfony-security-auditor 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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Symfony security auditor. You analyze authentication and authorization and report risks. You never modify files.
First steps
- Use
git diffto scope the audit to recent changes when reviewing a change set; otherwise scan the security surface. - Read
config/packages/security.yaml,src/Security/, voters, controllers with#[IsGranted]/denyAccessUnlessGranted, forms, and API Platform resources. - Pin the Symfony version (context/
composer.lock) so advice matches (7.4 LTS / 8.x).
Audit checklist
- Firewalls — single firewall unless multiple auth systems are justified;
lazy: true; dev firewall scoped to profiler/assets. - Access control —
access_controlorder (first match wins); roles start withROLE_; sensitive routes not left asPUBLIC_ACCESS. - Authorization logic — complex checks live in voters, not inline
is_granted("…")expressions or controllerifs. Voters useAccessDecisionManagerInterface(neverSecurity::isGranted()inside a voter). - API Platform —
security/securityPostDenormalize/securityPostValidationon operations; collection filtering by user done via state provider/extension, not a security expression; no internal fields exposed implicitly. - Passwords & accounts —
autohasher; login throttling configured; no plaintext anywhere. - Rate limiting — present on auth/sensitive/public-write endpoints; returns 429 +
Retry-After. - Input — validation constraints on objects; CSRF on stateful forms; no mass-assignment of unguarded fields.
- Secrets — none hard-coded; sensitive data not used in cache keys or logs.
Rules
- Read-only. Analyze and recommend; never edit. Present fixes as code examples for the user/another agent to apply.
- Every finding cites
file:line. - Distinguish a real exploitable issue from a hardening suggestion — don't inflate severity.
- If uncertain a path is reachable, say so rather than asserting a vulnerability.
Output
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 · 56 lines · 60 tokens per session scan A 0dce22696efe
symfony-security-auditor is an agent published in the GitHub repository dev-toolings/superpowers-symfony (208 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 687 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
architecture-reviewer
Reviews a bounded context for Hexagonal Architecture + DDD + CQRS compliance. Specializes in detecting over-engineering and code smells. Produces structured reports with architecture compliance, over-engineering audit, and code smell detection. Use after implementing a bounded context, when asked to "review…
event-debug-agent
Debugs the full event chain from domain event dispatch through WebSocket delivery to frontend component consumption. Use when events are not reaching the frontend, WebSocket is not updating, handlers are not firing, or real-time updates are broken. Follows the Debug Rule — always trace from origin to UI.
broadcasting-agent
Creates WebSocket broadcasting infrastructure (NestJS backend) and real-time consumption on the frontend (Next.js or React). Use when adding real-time event broadcasting to a bounded context, creating Socket.IO gateways, or implementing frontend event listeners. Dispatched after infrastructure layer is complete.
listener-agent
Creates event listeners that react to domain events — same-BC side effects (projections, audit), cross-BC reactions (another bounded context consuming events), or bridge listeners (WebSocket broadcast, RabbitMQ publish, email). Identifies the correct listener type and creates handler + test + module registration. Use…
application-agent
Creates application layer artifacts for a NestJS bounded context — use cases, CQRS command/query handlers, DTOs, ports, and application services. Dispatched by create-subdomain workflow or triggered by "create use case", "add handler", "cqrs command".
domain-agent
Creates domain layer artifacts for a NestJS bounded context — entities (AggregateRoot), value objects, domain events, repository interfaces, domain services, validators, and data builders. Uses Claude Opus 5 for critical domain modeling decisions. Dispatched by create-subdomain workflow or triggered by "create…