/cad-report

Render a phase's run record as a receipts narrative - what each dispatch cost, what the gates caught, what got refuted - straight from trace.jsonl and the phase artifacts

Boost this skill

crenshawdev@crenshawdev

GitHub

From plugin

cadence

534 skills30 agents3 hooks

Install

$ npx -y skills add crenshawdev/cadence --skill cad-report --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/cad-report

Context preview

The summary Claude sees to decide when to auto-load this skill.

Render a phase's run record as a receipts narrative - what each dispatch cost, what the gates caught, what got refuted - straight from trace.jsonl and the phase artifacts

SKILL.md

cad-report.SKILL.md

name: cad-report
description: "Render a phase's run record as a receipts narrative - what each dispatch cost, what the gates caught, what got refuted - straight from trace.jsonl and the phase artifacts"
argument-hint: "[phase] [--all]"
allowed-tools:
  - Read
  - Bash
  - Grep
  - Glob

<objective> Turn `.planning/trace.jsonl` and a phase's artifacts into the story of what your tokens bought: every dispatch priced, every gate's outcome named, every refuted assumption cited. Read-only - it renders the record, it never writes it. `--all` spans the whole record for a milestone-shaped view. </objective>

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

<process> Execute end-to-end. </process>

Read it on GitHub ↗

Ships withcadence

Appearance is cheap. Verification is the work. Cadence is for developers using Claude Code on software they will still own after the session ends. Claude can write a convincing plan, produce working code, and tell you the job is finished.

Get the whole plugin

Stats

JavaScript Node Bash Ruby Git

+4 tags

GitHub Anthropic OpenAI Gemini

Stars

Forks

Active

Maintenance

JavaScript

Language

MIT