Codex

provenance-report

Generate provenance coverage dashboard and statistics

104 stars

byjmagly

View on GitHub Installation ↓

Best use case

provenance-report is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

It is a strong fit for teams already working in Codex.

Generate provenance coverage dashboard and statistics

Teams using provenance-report should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/provenance-report/SKILL.md --create-dirs "https://raw.githubusercontent.com/jmagly/aiwg/main/.agents/skills/provenance-report/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/provenance-report/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How provenance-report Compares

Feature / Agent	provenance-report	Standard Approach
Platform Support	Codex	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Generate provenance coverage dashboard and statistics

Which AI agents support this skill?

This skill is designed for Codex.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

Cursor vs Codex for AI Workflows

Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

SKILL.md Source

# Provenance Report Command

Generate a dashboard showing provenance tracking coverage, agent attribution, and chain health.

## Instructions

When invoked, generate provenance report:

1. **Count tracked vs untracked artifacts**
   - Scan `.aiwg/` directories for all artifacts
   - Count provenance records in `.aiwg/research/provenance/records/`
   - Calculate coverage percentage

2. **Breakdown by entity type**
   - Categorize: document, code, test, schema, template, agent, command
   - Show tracking percentage per type

3. **Breakdown by agent**
   - Group records by agent URN
   - Count artifacts per agent
   - Show activity types per agent

4. **Chain health metrics**
   - Count broken links
   - Count orphaned records
   - Count missing back-references
   - Calculate chain completeness score

5. **Activity timeline**
   - Recent provenance activities (last 7 days)
   - Most frequently modified artifacts
   - Activity distribution by type

6. **Generate report**
   - Format as markdown dashboard
   - Include tables and summary metrics
   - Optionally save to `.aiwg/reports/provenance-report.md`

## Arguments

- `--brief` - Show summary only
- `--save` - Save report to `.aiwg/reports/provenance-report.md`
- `--since [date]` - Only include activities since date
- `--format [markdown|json]` - Output format (default: markdown)

## References

- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/agents/provenance-manager.md - Provenance Manager agent
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/provenance/prov-record.yaml - PROV record schema
- @.aiwg/research/provenance/docs/provenance-guide.md - Provenance guide
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/provenance-tracking.md - Provenance tracking rules