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.
git 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/commands/mathiasbourgoin/roster/ambiguity-auditor)<a href="https://agentmods.dev/commands/mathiasbourgoin/roster/ambiguity-auditor"><img src="https://agentmods.dev/badge/commands/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/commands/mathiasbourgoin/roster/ambiguity-auditor"><img src="https://agentmods.dev/badge/commands/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 | $0.00022 | $0.01005 |
| Opus 5 | $0.00011 | $0.00502 |
| Sonnet 5 | $0.00004 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00101 |
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 9d 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 — 114 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 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.
- 9d ago First seen · 114 lines · 22 tokens per session scan A cca80ebecb4e
ambiguity-auditor is a command published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,005 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.