audit

A command for checking specifications marked Ready against the code that implements them. It follows project guidance and examines only functional differences, such as broken behavior, missing features, wrong data, or incorrect boundary types.

In plain words
What is it for?
Use it to audit completed specifications, record supported findings in the appropriate files, and leave already implemented, draft, or deprecated specifications untouched.
Why use it?
It helps find real implementation problems without treating naming, formatting, documentation gaps, or harmless pattern differences as defects.

Command for Claude Code

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.

agentmods
npx agentmods add commands/justifi-tech/web-component-library/audit
Clone the repo
git clone --depth 1 https://github.com/justifi-tech/web-component-library

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 940 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00940
Opus 5 $0.00000 $0.00470
Sonnet 5 $0.00000 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 2d ago against content hash 62782fb5a74e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/specd/audit.md · 105 lines

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.

Study AGENTS.md for guidelines. Study specs/README.md to find all specs and their statuses.

Your task is to audit Ready specs against code, then write findings to the appropriate files.

Scope

Only audit specs with status Ready. Skip Implemented, Draft, and Deprecated specs entirely.

What counts as a finding

Only flag things that are functionally wrong — broken behavior, missing features, incorrect data, wrong types at system boundaries. The bar is high:

  • Code produces wrong results or crashes → finding
  • A spec-required feature is missing entirely → finding
  • Types are wrong at API boundaries causing runtime errors → finding
  • Code works correctly but uses a different pattern than the spec suggests → NOT a finding
  • Spec wording doesn't perfectly match implementation details → NOT a finding
  • Cosmetic differences (naming, formatting, ordering) → NOT a finding
  • Documentation gaps in the spec → NOT a finding

Do NOT bump spec versions for documentation clarifications. If the spec wording is imprecise but the code is correct, the spec is fine. Only bump versions when the spec needs to prescribe genuinely new or changed behavior.

Process

Work through each Ready spec sequentially. For each spec:

Step 1: Gather

Launch a research agent (model: Sonnet) to audit the spec against code. The agent:

  1. Reads the full spec
  2. Reads the code that implements it
  3. Reports raw findings: broken behavior, missing features, incorrect data handling

The agent applies the "what counts as a finding" bar above. It does NOT write or modify any files.

Step 2: Validate

When the agent returns findings, you validate each one yourself:

  1. Read the actual code for each finding — confirm or reject the claim against the source
  2. Cross-check against specd_work_list.md and specd_history.md to avoid duplicates (grep for the spec name in specd_history.md — never read it in full)
  3. For each finding, answer: "Is the code actually broken or producing wrong results?" If no, reject the finding.
  4. Categorize each confirmed finding:
    • Code is broken / produces wrong results → specd_work_list.md item
    • Spec needs to prescribe new behavior → spec update candidate (version bump required)
    • Ambiguous, needs human → specd_review.md item
    • Already known / in progress / duplicate → skip
    • Code works fine, just different from spec wording → skip (do NOT flag)

Read the full file on GitHub · 105 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. 2d ago First seen · 105 lines · 0 tokens per session scan A 62782fb5a74e

Subscribe to this mod's changes

audit is a command published in the GitHub repository justifi-tech/web-component-library (5 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 940 tokens. 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.