sdlc-audit

sdlc-audit is a command for coding agents from MCKRUZ/claude-code-sdlc. It costs 0 tokens per session (387 once invoked), scanned A, original, MIT.

A command that examines the results of quality gates across completed stages of an SDLC project. A gate is a check that must pass before work moves forward.

In plain words
What is it for?
Use it on a project's .sdlc/state.yaml file to review gate counts, failures, overrides, and suggested changes.
Why use it?
It shows which checks regularly catch problems, never fail, fail often, or are overridden. This helps teams adjust gates based on evidence rather than habit.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-code-sdlc plugin — 9 skills, 28 commands, 20 agents 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/mckruz/claude-code-sdlc/sdlc-audit
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc

Or install claude-code-sdlc, the plugin that ships this one along with the rest of its 9 skills, 28 commands, 20 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 sdlc-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-audit.svg)](https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-audit)
Your own site
<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-audit"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-audit.svg" alt="Measured on agentmods" height="20"></a>
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 387 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 $0.00387
Opus 5 $0.00000 $0.00193
Sonnet 5 $0.00000 $0.00077
Haiku 4.5 $0.00000 $0.00039

Measured 4d ago against content hash 141f3714b7f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-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 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.

commands/sdlc-audit.md · 32 lines

What it actually says

/sdlc-audit — Gate Effectiveness Analysis

Analyze gate results across completed phases in the current project's state.yaml to identify which gates are useful and which are candidates for adjustment.

Instructions

  1. Locate state file: Look for .sdlc/state.yaml in the current project directory. If not found, tell the user to run /sdlc-setup first.

  2. Read state: Load .sdlc/state.yaml and extract gate_results from every completed phase.

  3. Run audit analysis: Execute the audit script:

    uv run --project ${CLAUDE_PLUGIN_ROOT}/scripts ${CLAUDE_PLUGIN_ROOT}/scripts/audit_gates.py --state .sdlc/state.yaml
    
  4. Display results: Show the audit report with:

    • Gate effectiveness summary — table of every gate that was checked, how many times it ran, and how many times it failed
    • Always-pass gates — gates that never failed across all phases (candidates for removal or tightening)
    • High-fail gates — gates that failed frequently (may indicate process issues or overly strict thresholds)
    • Override history — any gates that were overridden, with justification text
    • Recommendations — suggested actions based on the analysis
  5. Optionally compare profiles: If --compare <other-state.yaml> is provided, compare gate effectiveness between two projects.

Arguments

  • No arguments: audit current project
  • --compare <path>: compare with another project's state.yaml

Important

  • This command is read-only — it analyzes existing data, never modifies state.
  • Useful gate auditing requires at least 3-4 completed phases to have meaningful data. If fewer phases are complete, warn the user that results may not be representative.
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. 4d ago First seen · 32 lines · 0 tokens per session scan A 141f3714b7f6

Subscribe to this mod's changes

sdlc-audit is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 387 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.