plan-verify

A verification workflow that checks a finished implementation against its development plan. It runs the required tests and acceptance checks, then records whether each work item passed, failed, or is blocked.

In plain words
What is it for?
Use it to locate a plan, extract its checklist, run repository gates, verify acceptance criteria, and produce a pass/fail report with evidence.
Why use it?
It replaces a general claim that work is complete with evidence tied to the plan’s requirements. It also makes missing tests and unrunnable checks visible.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/xiaolai/vmark/plan-verify
Any agent
npx skills add xiaolai/vmark --skill plan-verify
Clone the repo
git clone --depth 1 https://github.com/xiaolai/vmark

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.00368
Opus 5 $0.00016 $0.00184
Sonnet 5 $0.00006 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured 2d ago against content hash 54042555e3b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-verify scanned grade A with 0 findings 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 2d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/plan-verify/SKILL.md · 54 lines

What it actually says

Plan Verify

Overview

Runs the plan’s required tests/gates and validates acceptance criteria, producing a pass/fail verification report.

Workflow (Verify)

  1. Locate the plan

    • Prefer dev-docs/plans/<plan>.md.
    • If unclear, ask for the plan path.
  2. Extract verification checklist

    • For each WI, list:
      • Acceptance criteria
      • Required tests
      • Manual checks (if any)
  3. Run gates

    • Use repo-specific gates from .claude/commands/feature-workflow.md or plan “Testing Procedures”.
    • If tests are not runnable, note the blocker explicitly.
  4. Verify acceptance

    • For each WI, mark each acceptance criterion as Pass/Fail/Blocked.
    • Include evidence (test output, file refs, manual steps).
  5. Report results

    • Summarize pass/fail with concrete next actions.

Output Format (required)

  • Verification Summary
    • Total WIs verified
    • Pass/Fail/Blocked counts
  • Gate Results
    • Command → status
    • Failures with key error lines
  • Acceptance Matrix
    • WI‑### → criterion → Pass/Fail/Blocked
  • Manual Checks
    • Steps executed + outcome

Verification Rules

  • Always run tests unless the user explicitly forbids it.
  • If tests are skipped or fail, mark WI as Blocked.
  • Do not claim “verified” without test evidence.
  • Manual checks must include evidence (step list + observed result).
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. 2d ago First seen · 54 lines · 32 tokens per session scan A 54042555e3b5

Subscribe to this mod's changes

plan-verify is a skill published in the GitHub repository xiaolai/vmark (544 stars, last pushed 2d ago), licensed ISC. It adds 32 tokens to every session and 368 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens