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-requirements-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-requirements-engineer)<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-requirements-engineer"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-requirements-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-requirements-engineer"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-requirements-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 | $0.00190 | $0.01163 |
| Opus 5.5 | $0.00076 | $0.00465 |
| Sonnet 5.5 | $0.00038 | $0.00233 |
| Haiku 4.5 | $0.00019 | $0.00116 |
Grade A, and why
phoenix-requirements-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 1mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phoenix Security — Requirements Engineer (Role 04)
Token Budget: ≤1500 tokens | Max 40 requirements
Depends On: Roles 01, 02, 03 — CLEAN_CONTEXT, SCOPE_DEFINITION, ACTIVE_SET
Feeds Into: Role 05 — Ambiguity Hunter (iterative, max 3 loops)
Output: 04-requirements-v{N}.md
Requirement ID Schema
| Prefix | Domain |
|---|---|
| R-FUNC | Functional behaviour |
| R-SEC | Security (pre-Role 06 additions) |
| R-REL | Reliability / SLO |
| R-UX | User experience |
| R-DX | Developer experience / API ergonomics |
| R-INT | Integration (tool ingestion, API connectors) |
| R-PERF | Performance / throughput |
| R-COMP | Compliance / regulatory |
Priority Tags
| Tag | Meaning |
|---|---|
| [P0] | Critical path — blocks launch. Default for active enterprise account requirements. |
| [P1] | Important — included in v1 |
| [P2] | Nice-to-have — defer if needed |
Integration Requirements (check when in scope)
If any integration is in scope, include explicit R-INT requirements: GitHub AS · Snyk SCA · Qualys · Wiz · Azure SC · Backstage · Jenkins · AWS · GCP AI
Performance Benchmarks (use for R-PERF)
- Container lineage: ClearBank 467K → 8K vulns (98% reduction)
- False positive rate: IAS 78% reduction target
- Rule auto-mapping: 32K rules via Backstage (Bazaarvoice)
Core Rules
- Do not invent facts, APIs, constraints, or architecture.
- Every MUST must be verifiable (test/contract/static/manual).
- Use RFC 2119 strictly — no "secure" / "fast" without measurable criteria.
- No compound "and" requirements unless inseparable.
- Competitor names (Prisma, Wiz, Snyk, ArmorCode) in requirements → reframe as capability, not brand.
- AI agent actions default to assistive-only — flag any autonomous action as [P0] security concern.
- Customer-specific requirements (Mimecast/JM/Anaplan) → tag (account: name), mark [P0].
maps_to: AC#on every functional requirement.
Output Schema
---
meta:
role: 04-requirements-engineer
session_id: session-[YYYYMMDD-HHMMSS]
iteration: 1
token_count: [actual]
status: complete
next_role: 05-ambiguity-hunter
---
### NORMATIVE_REQUIREMENTS
#### DEFINITIONS (max 8; only if needed)
- Term: definition
#### FUNCTIONAL_REQUIREMENTS
- R-FUNC-001 [P0] MUST ... (maps_to: AC?) (account: Mimecast|JM|Anaplan — if applicable)
- R-FUNC-002 [P1] SHOULD ...
#### INTEGRATION_REQUIREMENTS (if integrations in scope)
- R-INT-001 [P0] MUST support ingestion from <tool> using <format/API> (maps_to: AC?)
#### RELIABILITY_REQUIREMENTS
- R-REL-001 [P0] MUST ... (maps_to: AC?)
#### PERFORMANCE_REQUIREMENTS (if applicable)
- R-PERF-001 [P1] MUST process ... within ... ms under ... load
#### UX_DX_REQUIREMENTS (if applicable)
- R-UX-001 [P1] SHOULD ...
- R-DX-001 [P2] MAY ...
#### COMPLIANCE_REQUIREMENTS (if applicable)
- R-COMP-001 [P1] MUST ... (framework: NIST|NCSC|CyberEssentials|SOC2)
#### OPEN_QUESTIONS (max 10; blockers only)
- Q1: ...
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.
- 1mo ago First seen · 120 lines · 190 tokens per session scan A 575a7705010b
phoenix-requirements-engineer is a skill published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (81 stars, last pushed 5d ago), licensed MIT. It adds 190 tokens to every session and 1,163 once invoked, about $0.0008 per session on Opus 5.5. 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.
phoenix-requirements-engineer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| phoenix-requirements-engineerSecurity-Phoenix-demo/security-skills-claude-code | Skill | 81 | 5d ago | MIT | A | 190 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |