verify

A verification step that compares an implementation with its specification documents and checks whether the documented behavior matches the code. It also reports possible documentation drift, meaning documents that no longer reflect the software.

In plain words
What is it for?
Use it to verify completed changes against requirements, review distilled specifications against current behavior, and obtain separate implementation and code-review findings.
Why use it?
It catches missing or incorrect work before a change is archived. Independent checks help reveal issues that the original implementer may overlook.

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/kirkchen/beat/verify
Any agent
npx skills add kirkchen/beat --skill verify
Clone the repo
git clone --depth 1 https://github.com/kirkchen/beat

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,266 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 $0.00020 $0.02266
Opus 5 $0.00010 $0.01133
Sonnet 5 $0.00004 $0.00453
Haiku 4.5 $0.00002 $0.00227

Measured 2d ago against content hash 6150ffc10773, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

skills/verify/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify implementation against change artifacts across five dimensions. Uses independent subagents to eliminate context bias.

<decision_boundary>

Use for:

  • Validating implementation completeness against spec artifacts before archive
  • Verifying distilled specs match current code behavior (accuracy mode, source: distill)
  • Independent verification via subagents to catch context bias
  • Surfacing living-doc drift (Layer 1/2/3) as advisory findings

NOT for:

  • Creating or modifying spec artifacts (use /beat:design)
  • Writing tasks (use /beat:plan)
  • Running implementation (use /beat:apply)
  • Archiving the change (use /beat:archive)

Trigger examples:

  • "Verify the change" / "Check implementation against spec" / "Run verification"
  • Should NOT trigger: "design a feature" / "implement the change" / "archive it"

</decision_boundary>

Dispatch the verification subagent AND code-reviewer in parallel — they are independent checks.

If a subagent fails, proceed with findings from the other. If BOTH fail, report the failure — do NOT fall back to self-verification.

After presenting the combined report: you MUST record the outcome in the top-level verification field of status.yaml (see step 6). If verification could not run at all (both subagents failed), do NOT record — a failed run is not a verification outcome.

Rationalization Prevention

Thought Reality
"The change is small, I can verify it myself" Self-verification creates confirmation bias. You saw the implementation — you can't objectively verify it.
"I already reviewed the code during apply" That's exactly why you need an independent verifier. Familiarity breeds blind spots.
"Running two subagents is overkill for this" Code quality and spec alignment are independent dimensions. A single agent conflates them.
"I'll just run the tests, that's verification enough" Tests verify behavior but not spec alignment, design adherence, or code quality.
"I'll dispatch them sequentially to save context" They're independent — parallel dispatch is faster and prevents one report from biasing the other.
"The report is delivered, the status.yaml write is just bookkeeping" The verification field is how archive knows verify ran. Skip it and archive warns "never verified" on a verified change. Ten seconds — write it.

Read the full file on GitHub · 191 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 191 lines · 20 tokens per session scan A 6150ffc10773

Subscribe to this mod's changes

verify is a skill published in the GitHub repository kirkchen/beat (7 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 2,266 once invoked, about $0.0001 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 2026-08-31.

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens