cad-audit

Pre-ship traceability audit - every requirement traced to a phase, plan and verification, orphan detection both directions, a FAIL gate before shipping

Skill by crenshawdev

IndexedMIT★ 8

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/crenshawdev-cad-audit

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Pre-ship traceability audit - every requirement traced to a phase, plan and verification, orphan detection both directions, a FAIL gate before shipping

Use cases: security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/cad-audit

What's inside

Skill name: cad-audit
Description: Pre-ship traceability audit - every requirement traced to a phase, plan and verification, orphan detection both directions, a FAIL gate before shipping
License: MIT
Instructions: 28 lines in SKILL.md · view on GitHub

Agent Skills spec issues

allowed-tools: must be a space-separated string

Files (1)

SKILL.md

SKILL.md (first lines)

<objective>
Before a milestone ships, prove that nothing was silently dropped. Cross-
reference every requirement against the phases, plans, and verifications that
were supposed to deliver it, and detect orphans in both directions. Produce a
PASS/FAIL verdict: FAIL if any requirement is untraced, unverified, or lost.

This is the check that catches the quiet failure a per-phase flow can miss -
a requirement that no phase ever picked up (an `unpicked` break counted in
`counts.broken`, not a note beside a PASS), or one marked done while its phase
never verified. It reads the authoritative status - the REQUIREMENTS
traceability table (Requirement | Phase | Status) and the ROADMAP `## Phases`
checkbox, the only persisted status. `/cad-plan` creates a table row (always
at Pending); no writer but cad-verify ever sets a Status beyond it, and the
ROADMAP checkbox is cad-verify's alone. It does not write status itself.
</objective>

<execution_context>
@${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/audit.md
</execution_context>

<process>
Run the audit workflow end-to-end and return a clear PASS or FAIL with the
evidence. A FAIL is a real gate - report exactly which requirements are untraced,
unverified, or orphaned; do not soften it. Read-only: never edit status to make
the audit pass.
</process>

From crenshawdev/cadence, MIT.

Signals

Stars: 8
Forks: 0
Open issues: 4
Last commit (this folder): Aug 5, 2026 (2 months ago)
Last release: Oct 12, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/crenshawdev/cadence
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from crenshawdev

Cite this page

cad-audit skill. Agent Mart. https://agentmart.dev/skills/crenshawdev-cad-audit (last updated 2026-10-24)