Skip to content
Back to skills

Provenance

ASecurity

Sources for changed process contracts in [SKILL.md](../../skills/system-design/SKILL.md). Mechanism provenance lives in [HEURISTICS.md](HEURISTICS.md), [AUDIT.md](AUDIT.md), and [RUNTIME.md](RUNTIME.md).

  • 26 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agentsgit

Security analysis

A100/100

Pro scans all 12 files and shows the line behind each finding

Scanned November 11, 2026

npx -y skills add pinchen147/system-design-skill --skill provenance --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Provenance?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Provenance
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/pinchen147-provenance/badge)](https://www.skillsdirectory.com/skills/pinchen147-provenance)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Provenance — System Design

Sources for changed process contracts in [SKILL.md](../../skills/system-design/SKILL.md). Mechanism provenance lives in [HEURISTICS.md](HEURISTICS.md), [AUDIT.md](AUDIT.md), and [RUNTIME.md](RUNTIME.md).

## Route the ask

| Claim | Source |
|---|---|
| Small routing entry point and conditional reference loading | [Pinned REA router](https://github.com/morluto/rea/blob/705058f3e2df82503f1c601fc464aea7cbb626b8/.agents/skills/reverse-engineer-anything/SKILL.md); adapted to architecture work, which REA itself excludes. |

## Process

### 1. Locate and resume

| Claim | Source |
|---|---|
| Unchanged HEAD does not identify staged, unstaged, or untracked working-tree bytes | Git working-tree/index/commit distinction; runtime hashes the actual scoped source bytes. |
| Installed local runtime maintains tracked investigation state and explicit recovery | [RUNTIME provenance](RUNTIME.md); selected product design. |

### 2. Establish the current truth

| Claim | Source |
|---|---|
| Observed, derived, and inferred evidence retains scope and limitations; unanswered questions remain explicit | [Evidence lifecycle](HEURISTICS.md#evidence-and-uncertainty). |

### 8. Audit the architecture for debt

| Claim | Source |
|---|---|
| Finder and verifier are fallible; uncertainty is neither confirmation nor refutation | [Audit pipeline provenance](AUDIT.md#the-pipeline). |

### 9. Write, render, and verify

| Claim | Source |
|---|---|
| Structural validation, semantic review, and browser inspection establish distinct properties | [Evidence lifecycle](HEURISTICS.md#evidence-and-uncertainty); report diagnostics only inspect rendering. |

Files in this skill

  • ARCHETYPES.md647 B
  • AUDIT.md29.5 KB
  • HEURISTICS.md13.2 KB
  • README.md1.7 KB
  • RUNTIME.md3.1 KB
  • SKILL.md1.6 KB
  • archetypes/authoritative-state.md4 KB
  • archetypes/control-security.md3.3 KB
  • archetypes/data-delivery.md2.1 KB
  • archetypes/derived-serving.md5.2 KB
  • archetypes/realtime-sync.md3.6 KB
  • archetypes/traffic-work.md3.8 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.