dredd-audit

dredd-audit is a command for Claude Code from pduggusa/judge-dredd-plugin. It costs 11 tokens per session (432 once invoked), scanned A, original, MIT.

A project audit command based on the Judge Dredd framework, which checks whether a software project follows operational, security, and maintenance practices.

In plain words
What is it for?
Use it to review commits, project instructions, tests, Dockerfiles, continuous-integration workflows, security records, dependency freshness, infrastructure sizing, licensing, and open-source status.
Why use it?
It gathers evidence from the repository so you can spot missing documentation, weak testing, outdated dependencies, unsafe containers, and other compliance gaps.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the judge-dredd plugin — 2 commands, 2 hooks shipped together

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/pduggusa/judge-dredd-plugin/dredd-audit
Clone the repo
git clone --depth 1 https://github.com/pduggusa/judge-dredd-plugin

Made for: Claude Code.

Or install judge-dredd, the plugin that ships this one along with the rest of its 2 commands, 2 hooks.

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 dredd-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/pduggusa/judge-dredd-plugin/dredd-audit.svg)](https://agentmods.dev/commands/pduggusa/judge-dredd-plugin/dredd-audit)
Your own site
<a href="https://agentmods.dev/commands/pduggusa/judge-dredd-plugin/dredd-audit"><img src="https://agentmods.dev/badge/commands/pduggusa/judge-dredd-plugin/dredd-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 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 5.1 $0.00011 $0.00432
Opus 5 $0.00005 $0.00216
Sonnet 5 $0.00002 $0.00086
Haiku 4.5 $0.00001 $0.00043

Measured 5d ago against content hash 214aeece3d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dredd-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 5d 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.

commands/dredd-audit.md · 58 lines

What it actually says

Context

  • Current git status: !git status
  • Recent commits: !git log --oneline -20
  • Project directory: !pwd

Your task

Run a Judge Dredd compliance audit on this project. Check the following dimensions:

D1: Commit Compliance

  • Are commit messages descriptive and conventional?
  • Is there a consistent commit style?
  • Are there any force-pushes or amended published commits in recent history?

D2: Corpus Alignment

  • Does the project have a README?
  • Is there a CLAUDE.md or equivalent project instructions file?
  • Are there tests? What's the test coverage situation?

D3: Production Evidence

  • Are there Dockerfiles? Do they follow hygiene (no :latest, no Alpine, platform specified)?
  • Are there CI/CD workflows? Do they have proper gates?
  • Is there a security policy or SBOM?

D4: Temporal Decay

  • When was the last commit?
  • Are there stale branches?
  • Are dependencies up to date? Any known CVEs in lockfiles?

D5: Financial Efficiency

  • Is the infrastructure right-sized? (Check Dockerfiles for resource hints)
  • Are there unnecessary dependencies?
  • Any signs of over-engineering?

D6: Democratic Sharing

  • Is the project open source? What license?
  • Are contributions acknowledged?
  • Is documentation public and accessible?

Output Format

Score each dimension 0-95 (NEVER 100 — we guarantee 5% bullshit exists).

Provide:

  1. Per-dimension score and 1-line justification
  2. Overall score (weighted average)
  3. Top 3 violations (most impactful issues)
  4. Top 3 commendations (things done well)
  5. Verdict: COMPLIANT (>80), ADVISORY (60-80), or VIOLATION (<60)

Be honest. The scales know.

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. 5d ago First seen · 58 lines · 11 tokens per session scan A 214aeece3d17

Subscribe to this mod's changes

dredd-audit is a command published in the GitHub repository pduggusa/judge-dredd-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 432 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.