vibecode-pro-max-kit: Skill for Claude Code

.claude/skills/vc-risk-evidence-pack/SKILL.md

vc-risk-evidence-pack is a skill for Claude Code from withkynam/vibecode-pro-max-kit. It costs 44 tokens per session (1,825 once invoked), scanned B, original, MIT.

A process for collecting proof before completing, pushing, or handing off high-risk software work. It covers six types of risky changes and requires five kinds of evidence.

In plain words
What is it for?
Use it when changes involve areas such as login, identity, or other high-risk surfaces, and when reviewing or completing those changes.
Why use it?
It helps teams avoid declaring sensitive work finished without checking and recording the required safety evidence.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

This is withkynam/vibecode-pro-max-kit's own configuration. It tells Claude Code how to work on vibecode-pro-max-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibecode-pro-max-kit configures →

About the project

vibecode-pro-max-kit is a set of instructions, agents, skills, hooks, and settings that gives AI coding agents a plan-first software development workflow. It is designed for developers, product owners, and other builders using agents such as Claude Code, Codex, Cursor, Windsurf, or Copilot across different technology stacks. The catalogue entries are the kit's own workflow components.

withkynam/vibecode-pro-max-kit · 1,118 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to withkynam/vibecode-pro-max-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/withkynam/vibecode-pro-max-kit/main/.claude/skills/vc-risk-evidence-pack/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/withkynam/vibecode-pro-max-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for vc-risk-evidence-pack

README.md
[![agentmods](https://agentmods.dev/badge/skills/withkynam/vibecode-pro-max-kit/vc-risk-evidence-pack/github.svg)](https://agentmods.dev/skills/withkynam/vibecode-pro-max-kit/vc-risk-evidence-pack)
Your own site
<a href="https://agentmods.dev/skills/withkynam/vibecode-pro-max-kit/vc-risk-evidence-pack"><img src="https://agentmods.dev/badge/skills/withkynam/vibecode-pro-max-kit/vc-risk-evidence-pack/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vc-risk-evidence-pack

Your own site · 80×15
<a href="https://agentmods.dev/skills/withkynam/vibecode-pro-max-kit/vc-risk-evidence-pack"><img src="https://agentmods.dev/badge/skills/withkynam/vibecode-pro-max-kit/vc-risk-evidence-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,825 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 37
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01825
Opus 5 $0.00022 $0.00912
Sonnet 5 $0.00009 $0.00365
Haiku 4.5 $0.00004 $0.00183

Measured 9d ago against content hash a8c3f84e94c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

vc-risk-evidence-pack scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/validate-evidence-pack.mjs, scripts/validate-risk-artifacts.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

Per **task-folder artefact colocation**, all artifacts go inside the selected plan's task folder (e.g. `process/features/{feature}/active/{slug}_{date}/harness/` or `process/general-plans/active/{slug}_{date}/harness/`),
.claude/skills/vc-risk-evidence-pack/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vc-risk-evidence-pack

Output style: Follow process/development-protocols/communication-standards.md — answer-first, plain language, no unexplained jargon, TL;DR on long responses.

Generate and validate the manual-first evidence pack required before finalizing, pushing, or handing off high-risk implementation work.

When To Invoke

  • VALIDATE Layer 1 security surface check — when the plan touches a high-risk class, flag the need for an evidence pack before routing to execute-agent.
  • EXECUTE before marking high-risk work complete — execute-agent must produce or verify the evidence pack exists before reporting DONE on any high-risk class.
  • code-reviewer as pre-PR quality gate — code-reviewer checks for the evidence pack presence before approving changes that touch a high-risk surface.

6 High-Risk Class Definitions

From process/development-protocols/orchestration.md ("High-Risk Execution Handoff") and process/development-protocols/implementation-standards.md ("Risky Work Evidence Contract") — both sources agree:

  1. auth or identity — authentication flows, session tokens, user identity resolution, Clerk JWT handling, or any surface that determines who the caller is.
  2. billing or credits — billing events, credit balance mutations, Stripe charge flows, OpenRouter credit accounting, credit transaction records, or subscription state changes.
  3. schema/data migration or destructive data mutation — Prisma migrations, raw SQL mutations, destructive writes that delete or overwrite persistent data, or schema changes to existing models.
  4. public API or external contract changes — tRPC procedure signature changes visible to the frontend, Hono route contract changes consumed by external callers, webhook shape changes, or any API surface that third parties or the client app depend on.
  5. deploy/runtime/container/proxy/gateway behavior — Dockerfile changes, supervisord config, start.sh, container service ports, Bun server entry, Hono route registration, Caddy proxy config, worker-node provisioning, or any change that affects how a running service starts or routes traffic.
  6. permission, secret, or trust-boundary logic — instance token gating, verifyInstanceOwnership, BYOK secret fetch paths, MITM proxy key injection, Bright Data credential handling, or any logic that controls what a caller is allowed to access.

Read the full file on GitHub · 169 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 169 lines · 44 tokens per session scan B a8c3f84e94c4

Subscribe to this mod's changes

vc-risk-evidence-pack is a skill published in the GitHub repository withkynam/vibecode-pro-max-kit (1,118 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,825 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.