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 skills add Security-Phoenix-demo/security-skills-claude-code --skill phoenix-security-engineergit clone --depth 1 https://github.com/Security-Phoenix-demo/security-skills-claude-codeWrote 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/skills/security-phoenix-demo/security-skills-claude-code/phoenix-security-engineer)<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-security-engineer"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-security-engineer/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/skills/security-phoenix-demo/security-skills-claude-code/phoenix-security-engineer"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-security-engineer.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 | $0.00197 | $0.01151 |
| Opus 5 | $0.00098 | $0.00575 |
| Sonnet 5 | $0.00039 | $0.00230 |
| Haiku 4.5 | $0.00020 | $0.00115 |
Grade A, and why
phoenix-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 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phoenix Security — Security Engineer (Role 06)
Token Budget: ≤1200 tokens
Depends On: Roles 01–04 — CLEAN_CONTEXT, SCOPE_DEFINITION, ACTIVE_SET, NORMATIVE_REQUIREMENTS
Feeds Into: Role 07 — Contract Architect
Output: 06-security.md
Phoenix Trust Boundaries (evaluate all; include applicable ones in threat model)
- Customer tenant ↔ Phoenix platform — vuln data, asset inventory, API keys (strongest boundary)
- Phoenix platform ↔ integrated tools — GitHub AS, Snyk, Qualys, Wiz, Azure SC, Backstage, Jenkins
- Phoenix platform ↔ AI/LLM layer — GCP Gemini custom model, Claude API — prompt/response handling
- Phoenix platform ↔ customer CI/CD — Jenkins/GitHub Actions gating; code execution adjacency
- Phoenix platform ↔ AWS infra — onboarding, core services, secrets management
- Phoenix CTI ↔ GCP — vuln scanning, CTI enrichment, CISA KEV correlation
High-Value Assets (address applicable ones)
- Customer vulnerability data (CONFIDENTIAL)
- API keys / integration credentials (per-tenant)
- Reachability analysis results (code structure exposure)
- SBOM / dependency graph data
- AI model inputs/outputs (prompt injection surface)
- Board-level risk reports (exec-grade, NDA)
Phoenix AI Agent Security Posture
- Agents MUST be assistive-only, disabled by default
- No autonomous action without explicit user confirmation
- No customer data ingestion by AI without opt-in
- Prompt injection is P0 for any LLM-touching feature
- Attribution + prioritisation must complete before any agent action
Regulatory Context
- UK: NCSC Cyber Essentials, UK GDPR, DORA (financial sector)
- US: NIST CSF, FedRAMP-awareness, CISA KEV compliance
Core Rules
- No fictional threats — ground every control in actual feature behaviour and data flows.
- Every security MUST must be verifiable (test/contract/static/manual).
- Preventative first, detective second, corrective third.
- Prompt injection is a required threat entry if any LLM component is in scope.
- PSC-03 (multi-tenancy) must appear in threat model whenever customer data flows exist.
- MITRE ATT&CK: map high-risk flows to techniques where applicable.
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 · 105 lines · 197 tokens per session scan A 229c54eaf019
phoenix-security-engineer is a skill published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (70 stars, last pushed yesterday), licensed MIT. It adds 197 tokens to every session and 1,151 once invoked, about $0.0010 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 2026-09-11.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…