Skip to content
Back to skills

Verify

ASecurity

Run ICM stage 03 - report the implementation against the plan's Validation checklist

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 26, 2026
ai-agents

Security analysis

A100/100

Scanned September 26, 2026

npx -y skills add andyrids/icm-spec --skill verify --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Verify?

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

Security grade badge for Verify
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andyrids-verify/badge)](https://www.skillsdirectory.com/skills/andyrids-verify)

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
---
name: verify
description: Run ICM stage 03 - report the implementation against the plan's Validation checklist
disable-model-invocation: true
---

# ICM stage 03 - verification

The argument names the plan slug. If it is empty, use the single `status: in-progress` plan in
`plans/`; if that is ambiguous, ask which slug to run.

1. Read `ICM/process-plan/stages/03-verification/CONTEXT.md`. If it is missing, stop and
   suggest `/icm:init`.
2. Execute the stage contract exactly as written, reporting against the Validation checklist in
   `plans/<slug>.md` and the specs its `specs:` frontmatter names.
3. Stop at the workspace's review gate: present the verification report for explicit user
   acceptance. `/icm:document` is the next step once accepted; a spec divergence finding
   re-enters at stage 01 instead.

$ARGUMENTS

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.