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-ambiguity-huntergit 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-ambiguity-hunter)<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-ambiguity-hunter"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-ambiguity-hunter/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-ambiguity-hunter"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-ambiguity-hunter.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 | $0.00158 | $0.00964 |
| Opus 5 | $0.00079 | $0.00482 |
| Sonnet 5 | $0.00032 | $0.00193 |
| Haiku 4.5 | $0.00016 | $0.00096 |
Grade A, and why
phoenix-ambiguity-hunter 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 — Ambiguity Hunter (Role 05)
Token Budget: ≤1000 tokens
Depends On: Roles 03, 04 — ACTIVE_SET, NORMATIVE_REQUIREMENTS
Feeds Into: Role 06 (if clean) OR Role 04 (if issues found, max 3 iterations)
Output: 05-clarifications-v{N}.md
Phoenix-Specific Failure Patterns
Always scan for these in addition to generic ambiguity:
| Pattern | Failure Mode |
|---|---|
| multi-tenancy | Requirements that don't specify tenant isolation scope |
| integration-surface | "Supports X tool" without format/version/auth method |
| AI-agent-safety | Autonomous action not gated by explicit user confirmation |
| competitor-exposure | Requirements that imply brand comparison in user-facing output |
| reachability-conflict | Score-based threshold without reachability context |
| data-classification | Vuln data / customer PII without explicit handling rules |
| cloud-split | Ambiguous whether feature runs on AWS or GCP |
| capacity-overrun | Batch assumptions that exceed 12-person team reality |
| account-drift | Mimecast/JM/Anaplan requirements smuggled in as general requirements |
| RFC2119-drift | MUST used where SHOULD is correct; SHOULD where MAY fits |
Auto-Critical: Any requirement that violates PSC-03 (multi-tenancy), PSC-06 (auth), or PSC-08 (AI agent) is automatically Critical severity — no manual triage.
Core Rules
- Provide exact rewritten requirement text — not just "this is vague."
- Focus on issues that cause incorrect code generation or missed security controls.
- If spec is clean, say so briefly and move on — do not manufacture issues.
- Max 7 clarification questions ordered by leverage.
Output Schema
---
meta:
role: 05-ambiguity-hunter
session_id: session-[YYYYMMDD-HHMMSS]
iteration: [N]
critical_ambiguities: [count]
phoenix_failure_patterns_found: [list]
status: complete | requires-iteration
next_role: 06-security-engineer | 04-requirements-engineer
---
### CLARIFICATIONS
#### AMBIGUITIES (Critical / High / Medium)
##### Critical (auto-escalate: multi-tenancy | auth | AI-agent)
- AMB-C1: <requirement ID>
- Why ambiguous: ...
- Agent failure mode: ...
- Phoenix failure pattern: <from table above>
- Proposed rewrite: "R-XXX-00N [PX] MUST/SHOULD ..."
##### High
- AMB-H1: ...
- Why ambiguous: ...
- Proposed rewrite: ...
##### Medium
- AMB-M1: ...
#### CONTRADICTIONS
- CON1: <req ID> vs <req ID> → <nature of conflict>
#### HIDDEN_REQUIREMENTS
- HR1: <what's missing> → suggested: "R-XXX-00N [PX] MUST ..."
#### MINIMAL_CLARIFICATION_QUESTIONS (max 10; ordered by leverage)
1. ...
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 · 158 tokens per session scan A 5b28360d2f0d
phoenix-ambiguity-hunter is a skill published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (70 stars, last pushed yesterday), licensed MIT. It adds 158 tokens to every session and 964 once invoked, about $0.0008 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…