vc-risk-evidence-pack

Generate and validate five-artifact evidence packs for high-risk code changes before finalization.

2|Updated Sep 15, 2025
One-click install
npx skills add https://github.com/marsley01/Marsley-Portfolio-Web --skill vc-risk-evidence-pack-marsley01
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vc-risk-evidence-pack
Source: https://github.com/marsley01/Marsley-Portfolio-Web/tree/main/.agents/skills/vc-risk-evidence-pack
Command: npx skills add https://github.com/marsley01/Marsley-Portfolio-Web --skill vc-risk-evidence-pack-marsley01

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? High-risk changes to auth, billing, migrations, APIs, deploy configs, or permission logic often ship without durable proof of review, making work hard to audit, resume, or hand off safely. ## Core Features & Use Cases - Risk Classification: Defines six high-risk classes (auth, billing, schema migrations, public API contracts, deploy/runtime behavior, and permission/secret handling) with a risk-gate.json stop decision. - Five-Artifact Schema: Specifies risk-gate.json, context-snippets.json, verification.json, review-decision.json, and adversarial-validation.json colocated in the plan's task folder. - Validation Scripts: Ships two Node.js validators that check artifact presence, required fields, and explicit APPROVE/REJECT review decisions. - Use Case: Before merging a change to Stripe credit accounting, generate the evidence pack, run the validator against the harness directory, and record an explicit reviewer decision instead of relying on narrative updates. ## Quick Start Ask the agent to generate a risk evidence pack for the current high-risk change and validate it with the included scripts before marking the work done.

Frequently Asked Questions about vc-risk-evidence-pack

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an evidence pack for a high-risk code change?

Create a harness folder inside the selected plan's task directory and populate five JSON artifacts: risk-gate, context-snippets, verification, review-decision, and adversarial-validation. Then run the validate-risk-artifacts.mjs script against that directory to check required fields.

What counts as a high-risk change requiring an evidence pack?

Six classes qualify: auth or identity flows, billing or credit accounting, schema migrations or destructive writes, public API or external contract changes, deploy/runtime/container/proxy behavior, and permission, secret, or trust-boundary logic.

How do I validate risk artifacts with the Node.js script?

Run node validate-risk-artifacts.mjs with the artifact directory path. It checks required fields in each JSON file, enforces riskLevel values, and exits with code 1 if any failure is found, printing warnings and failures as JSON.

Does the evidence pack block CI or run automatically?

No. The contract is manual-first and opt-in by risk class. The validation scripts check shape only and do not hook into CI or enforce adoption by default; the auto-stop rule is a workflow convention, not a blocking hook.

When is adversarial-validation.json required?

It is required for high-risk or attack-sensitive paths such as auth bypass, privilege escalation, secret exfiltration, or trust-boundary violations. The validator emits a warning when a high-risk pack is missing this artifact.