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 spec-compliance-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/spec-compliance-auditor)<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/spec-compliance-auditor"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/spec-compliance-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/spec-compliance-auditor"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/spec-compliance-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 | $0.00021 | $0.01319 |
| Opus 5 | $0.00010 | $0.00660 |
| Sonnet 5 | $0.00004 | $0.00264 |
| Haiku 4.5 | $0.00002 | $0.00132 |
Grade A, and why
spec-compliance-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 4d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Compliance Auditor
Compare the implementation against a spec file to verify every specified behavior is implemented and every implemented behavior is specified.
Input Contract
- If
$ARGUMENTScontains a file path to a spec: use that file as the spec source - Default (no
$ARGUMENTS): readkb/spec.md - Fail gracefully if neither exists: report "No spec source available" and exit
Steps
1. Extract Testable Claims
SPEC_PATH="${ARGUMENTS:-kb/spec.md}"
[ -f "$SPEC_PATH" ] || { echo "No spec at $SPEC_PATH — skipping"; exit 0; }
- Read the spec file at
$SPEC_PATHin full. - For a generated
kb/spec.md, use each projected qualified identifier (<namespace>/FR-NNN,<namespace>/AC-N,<namespace>/CHECK-N) as the claim reference. Do not collapse it back to an unqualified local ID. Exclude the projection itself as evidence that the claim is implemented. - Extract every concrete, testable claim. A testable claim is a statement that can be verified by reading code or running a test. Examples:
- "The API returns 404 when the resource is not found"
- "Passwords are hashed with bcrypt, cost factor 12"
- "The retry limit is 3 attempts with exponential backoff"
- Ignore aspirational or process-oriented statements ("we aim to...", "the team will...").
- For legacy prose without qualified identifiers, number each claim
legacy:S1,legacy:S2, etc. The prefix makes the weaker extraction path visible in reports.
2. Verify Each Claim
For each testable claim:
- Locate the relevant implementation code (search for function names, types, constants mentioned in the claim).
- Read the code and determine if the behavior matches the spec.
- Check tests — does a test exist that verifies this specific claim? Note the test file and name.
- Classify:
| Status | Meaning |
|---|---|
| PASS | Code matches spec, test exists |
| UNTESTED | Code matches spec, no test covering it |
| DIVERGE | Code behaves differently than spec states |
| MISSING | No implementation found for this spec item |
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.
- 4d ago Changed · +22 lines · -2 tokens per session 883dc7fc0169
- 11d ago First seen · 108 lines · 23 tokens per session scan A 5b4022922fa0
spec-compliance-auditor is a skill published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 1,319 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…