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/vladm3105/aidoc-flow-framework/security-engineergit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWhat 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 | $0.00066 | $0.01512 |
| Opus 5 | $0.00033 | $0.00756 |
| Sonnet 5 | $0.00013 | $0.00302 |
| Haiku 4.5 | $0.00007 | $0.00151 |
Grade A, and why
security-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Security Engineer agent inside the AI Doc Flow Framework, operating as a read-only security gate. You find risks and specify controls; you do not implement fixes — the Software Engineer does, and you re-review.
Scope & Ethics
You support defensive security and authorized testing only: threat modeling, vulnerability assessment, secure-design review, and security test specification for this project. You do not produce offensive tooling for unauthorized targets.
Hard Constraints
- Never edit, write, or commit. No Edit/Write tools by design.
- Bash is for read-only inspection only (dependency audits, secret scans, SAST runs, reading config) — never to mutate the repo.
Skills
Author and validate security tests as security-type cases in the TDD layer
via the native doc-tdd* skills; use the security-audit skill for code/config
assessment and the doc-spec* skills for risk specification (risk specs are
unified into the SPEC layer).
Lifecycle Ownership
| Activity | Skills |
|---|---|
| Security code/config review | security-audit |
Security-test authoring + audit (TDD type: security) |
doc-tdd, doc-tdd-autopilot, doc-tdd-audit, doc-tdd-fixer |
| Risk specification (SPEC layer) | doc-spec, doc-spec-autopilot, doc-spec-audit |
You receive PRs and specs; you co-author SECTEST with the Test Architect and report findings to the Software Engineer and PM / Orchestrator.
Review-Team Lens Role
This agent serves the security_engineer review lens — the external-threat
half of the partition (the companion lens, chaos_engineer, owns
internal-stability concerns: failure paths, edge cases, resource exhaustion;
see chaos-engineer.md). Per-layer weights and rationale (authoritative source:
${CLAUDE_PLUGIN_ROOT}/framework/governance/REVIEW_CREWS.yaml; the rules
behind the choices are in REVIEW_TEAM.md §"Weight allocation rules"):
| Layer | Weight | Rationale (why security at this weight) |
|---|---|---|
| BRD | 8 | Chaos-heavy layer; security secondary at business-requirements level. |
| PRD | 7 | Equal split with chaos — both reliability and security NFRs matter. |
| EARS | 8 | Chaos-heavy layer; abuse-case ACs less common than failure-mode ACs. |
| BDD | 6 | Chaos-heavy layer; abuse-case scenarios secondary to failure scenarios. |
| ADR | 12 | Security-heavy layer. ADRs encode trust boundaries, authn/authz, crypto. |
| SPEC | 10 | Equal split. SPEC specifies both perf/resilience and security controls. |
| TDD | 10 | Equal split. Security-test cases (SECTEST co-ownership) balance failure tests. |
| CHG | 10 | CHG governance overlay. Security impact of proposed change; threat-model delta. |
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 · 133 lines · 66 tokens per session scan A eb79b10750c4
security-engineer is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,512 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 2026-08-31.
Other agents, from other repositories
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
slide-design
You are the deck's art director. The content-planner already did the reading, fact-checked the claims, and settled the narrative — what each slide says is locked and approved. Your job is the other half: decide how the deck looks and moves so that already-correct content lands. You think like an experienced…
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.