Skip to content
Back to skills

Pact Check

ASecurity

Run PACT cognitive redirections against recent changes

  • 15 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added May 27, 2026
data-aidocumentation

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add jonathanmr22/pact --skill pact-check --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pact Check?

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

Security grade badge for Pact Check
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jonathanmr22-pact-check/badge)](https://www.skillsdirectory.com/skills/jonathanmr22-pact-check)

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
---
description: Run PACT cognitive redirections against recent changes
disable-model-invocation: false
---

Review the changes made in this session against PACT's cognitive redirections. For each question, evaluate honestly:

**1. Dependency trace:** For every file edited this session, what depends on it and what does it depend on? Were all downstream consumers updated?

**2. Staleness audit:** What did the changes make stale? Check:
   - Architecture map (SYSTEM_MAP.yaml) — does it still reflect reality?
   - Feature flow docs — do they still describe the correct behavior?
   - Package knowledge files — any new packages used without research?
   - Pending work tracker — updated with current status?

**3. Cache consistency:** If any provider/state management was modified, were ALL caches updated (both list and map caches)?

**4. Package verification:** Were any packages used based on assumption rather than verified documentation? Check `knowledge/packages/` for knowledge files.

**5. Lifecycle impact:** Do the changes survive all app states? Fresh install, normal open, background, force close, backup restore?

Report findings as:
- **PASS** — checked and correct
- **STALE** — needs updating (specify what)
- **UNCHECKED** — couldn't verify (explain why)
- **VIOLATION** — cognitive redirection was not followed (specify which)

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.

Comments

Loading comments…

Newsletter

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