sdd-audit

sdd-audit is a skill for Claude Code from viamus/claude-sdd-plugin. It costs 33 tokens per session (2,231 once invoked), scanned A, original, MIT.

A final review step for generated code. It checks engineering quality and production readiness after a separate check confirms that the code matches its specification.

In plain words
What is it for?
It helps review security, test coverage, and other configured quality areas, using project settings from sdd.config.json when available.
Why use it?
It catches problems that a specification check may miss, such as security issues, weak tests, and configuration-defined quality failures.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the sdd plugin — 8 skills shipped together

Good fit It helps review security, test coverage, and other configured quality areas, using project settings from sdd.config.json when available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/viamus/claude-sdd-plugin/sdd-audit
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.

Any agent
npx skills add viamus/claude-sdd-plugin --skill sdd-audit
Clone the repo
git clone --depth 1 https://github.com/viamus/claude-sdd-plugin

Made for: Claude Code.

Or install sdd, the plugin that ships this one along with the rest of its 8 skills.

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 sdd-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/viamus/claude-sdd-plugin/sdd-audit.svg)](https://agentmods.dev/skills/viamus/claude-sdd-plugin/sdd-audit)
Your own site
<a href="https://agentmods.dev/skills/viamus/claude-sdd-plugin/sdd-audit"><img src="https://agentmods.dev/badge/skills/viamus/claude-sdd-plugin/sdd-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,231 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 $0.00033 $0.02231
Opus 5 $0.00016 $0.01115
Sonnet 5 $0.00007 $0.00446
Haiku 4.5 $0.00003 $0.00223

Measured 8d ago against content hash 35cfbbce44bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sdd-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 8d 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.

skills/sdd-audit/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Audit — Final Quality Gate

You are a Senior Software Engineer conducting a comprehensive quality audit. Your job goes BEYOND spec consistency (that's what /sdd:sdd-check does). You review the code as if you were approving a Pull Request — checking engineering quality, best practices, and production-readiness.

Configuration

Before running any checks, read sdd.config.json from the project root. If it doesn't exist, use default values (all dimensions enabled, default thresholds).

The config controls:

  • Which dimensions are enabled/disabled
  • Severity per dimension: "error" (can trigger loop-back) or "warning" (reported but non-blocking)
  • Individual rules within each dimension (can be toggled on/off)
  • Thresholds (e.g., min_coverage_percent: 80)

Example config excerpt:

{
  "audit": {
    "dimensions": {
      "security": {
        "enabled": true,
        "severity": "error",
        "rules": {
          "check_owasp_top_10": false,
          "check_hardcoded_secrets": true
        }
      },
      "test_coverage": {
        "enabled": true,
        "severity": "error",
        "rules": {
          "min_coverage_percent": 80
        }
      },
      "performance": {
        "enabled": false
      }
    }
  }
}

Instructions

1. Load configuration

  1. Read sdd.config.json from the project root
  2. If not found, use defaults (all enabled, severity: error, standard thresholds)
  3. Merge: config values override defaults, missing values fall back to defaults

2. Identify what to audit

  • If $ARGUMENTS contains --all: audit ALL approved specs with output_files
  • If $ARGUMENTS is provided (one or more paths): use each one
  • Otherwise, search specs/ for specs with status: approved and output_files defined
  • Read the spec AND all generated code files

3. Run enabled dimensions

Only run dimensions where enabled: true in config. Skip disabled dimensions entirely (don't even mention them in the report).

Read the full file on GitHub · 215 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. 8d ago First seen · 215 lines · 33 tokens per session scan A 35cfbbce44bf

Subscribe to this mod's changes

sdd-audit is a skill published in the GitHub repository viamus/claude-sdd-plugin (4 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 2,231 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

chimera

Use this skill for post-session code quality review of files added or modified during a WrongStack session. It runs automatically when a session ends, and on demand. Trigger on the explicit vocabulary — "review", "code review", "quality check", "post-session review", "chimeric review", "chimera" — and on the task…

WrongStack/WrongStack · 182 tokens

auto-review

Use this skill to configure and understand the built-in auto-review plugin (wstack-auto-review) that fires automated code review subagents on every code change during a session. Triggers: user says "auto review", "otomatik review", "auto code review", "her değişiklikte review", "/auto-review".

WrongStack/WrongStack · 67 tokens

ia-code-review

Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs. For the full multi-agent workflow, use the ia-review command (/ia-review in Claude Code).

iliaal/whetstone · 61 tokens

skill-distiller

Fetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining the best elements. Use when the user asks to "distill skills for X", "find and combine skills for X", "synthesize skills", "merge skills", "make a skill for X from skills.sh", "update distilled skill", or…

iliaal/whetstone · 91 tokens

python-services

Python patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/parallel Python, FastAPI services, background jobs, or configuring Python project tooling (uv, ruff, ty).

iliaal/whetstone · 48 tokens

react-frontend

React, TypeScript, and Next.js patterns for frontend development. Use when building React components, managing state, fetching data, optimizing performance, or working with Next.js App Router. Covers React 18-19, hooks, Server Components, and type-safe patterns.

iliaal/whetstone · 57 tokens