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 mathiasbourgoin/roster --skill ambiguity-auditorgit clone --depth 1 https://github.com/mathiasbourgoin/rosterWrote 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/mathiasbourgoin/roster/ambiguity-auditor)<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/ambiguity-auditor"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/ambiguity-auditor/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/mathiasbourgoin/roster/ambiguity-auditor"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/ambiguity-auditor.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 | $0.00023 | $0.01070 |
| Opus 5.5 | $0.00009 | $0.00428 |
| Sonnet 5.5 | $0.00005 | $0.00214 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
ambiguity-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 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ambiguity Auditor
Scan all knowledge base files and produce a structured report of ambiguity, inconsistency, and staleness issues.
Steps
1. Load KB
- Read
kb/index.mdto enumerate all KB files. - Read
kb/glossary.mdto build the set of defined terms. - Read every KB file listed in the index.
2. Check: Undefined or Inconsistent Terms
- Extract all domain-specific nouns and noun phrases from each KB file.
- For each term, verify it appears in
kb/glossary.md. - Flag terms used but not defined.
- Flag terms defined differently in glossary vs. usage in context (inconsistent usage).
3. Check: Vague Requirements
Scan for patterns indicating unquantified or untestable requirements:
- Subjective qualifiers: "should be fast", "handle errors gracefully", "in a timely manner", "as needed", "if possible", "reasonable", "appropriate"
- Missing thresholds: "low latency" (how low?), "high availability" (what SLA?), "scalable" (to what load?)
- Weasel phrases: "generally", "typically", "in most cases", "may", "might"
For each match, flag and recommend a quantified replacement.
4. Check: Contradictions Between Files
- Cross-reference claims across all KB files.
- Specifically compare:
spec.mdvsproperties.md,architecture.mdvsspec.md, any file vsglossary.md. - Flag: same concept described with conflicting behavior, conflicting constraints, or conflicting ownership.
5. Check: Missing Cross-References
- When a KB file mentions a concept that has its own KB entry or glossary definition, verify a cross-reference exists (link, explicit "see X", or inline definition).
- Flag missing cross-references.
6. Check: Stale Content
- Check
last-updatedfrontmatter in each KB file. Flag files older than 30 days. - Check for references to components, functions, or files that no longer exist in the codebase (use
find/grepto verify). - Flag dead references.
7. Cross-Spec Entity Consistency (conditional)
ls specs/*.md 2>/dev/null
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +7 lines · +1 tokens per session 49e836453623
- 2mo ago First seen · 114 lines · 22 tokens per session scan A cca80ebecb4e
ambiguity-auditor is a skill published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 1,070 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…