spec-compliance-auditor

spec-compliance-auditor is a command for Claude Code from mathiasbourgoin/roster. It costs 21 tokens per session (1,319 once invoked), scanned A, original, MIT.

A command that compares code with a specification file to check whether specified behavior is implemented and whether implemented behavior is documented.

In plain words
What is it for?
It is for auditing implementation against testable claims in a spec, such as API responses or password-handling rules.
Why use it?
It exposes missing requirements and undocumented behavior before they become unnoticed differences between the specification and the code.

Command for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Part of the roster plugin — 40 commands, 8 agents shipped together

Good fit It is for auditing implementation against testable claims in a spec, such as API responses or password-handling rules.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mathiasbourgoin/roster/spec-compliance-auditor
Install

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.

Clone the repo
git clone --depth 1 https://github.com/mathiasbourgoin/roster

Made for: Claude Code.

Or install roster, the plugin that ships this one along with the rest of its 40 commands, 8 agents.

Wrote 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.

agentmods badge for spec-compliance-auditor

README.md
[![agentmods](https://agentmods.dev/badge/commands/mathiasbourgoin/roster/spec-compliance-auditor/github.svg)](https://agentmods.dev/commands/mathiasbourgoin/roster/spec-compliance-auditor)
Your own site
<a href="https://agentmods.dev/commands/mathiasbourgoin/roster/spec-compliance-auditor"><img src="https://agentmods.dev/badge/commands/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.

agentmods 80×15 button for spec-compliance-auditor

Your own site · 80×15
<a href="https://agentmods.dev/commands/mathiasbourgoin/roster/spec-compliance-auditor"><img src="https://agentmods.dev/badge/commands/mathiasbourgoin/roster/spec-compliance-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.01319
Opus 5.5 $0.00008 $0.00528
Sonnet 5.5 $0.00004 $0.00264
Haiku 4.5 $0.00002 $0.00132

Measured 1mo ago against content hash 883dc7fc0169, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

.claude/commands/spec-compliance-auditor.md · 130 lines

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 $ARGUMENTS contains a file path to a spec: use that file as the spec source
  • Default (no $ARGUMENTS): read kb/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_PATH in 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:

  1. Locate the relevant implementation code (search for function names, types, constants mentioned in the claim).
  2. Read the code and determine if the behavior matches the spec.
  3. Check tests — does a test exist that verifies this specific claim? Note the test file and name.
  4. 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

Read the full file on GitHub · 130 lines

Changes

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.

  1. 1mo ago First seen · 130 lines · 21 tokens per session scan A 883dc7fc0169

Subscribe to this mod's changes

spec-compliance-auditor is a command published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 1,319 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 2026-09-07.