verify

verify is a skill for Claude Code, Codex from ApurvBazari/claude-plugins. It costs 57 tokens per session (1,534 once invoked), scanned A, original, MIT.

A tool for independently checking whether documented software features meet their acceptance criteria.

In plain words
What is it for?
Use it to test all incomplete features, one feature by ID, or the features in a sprint from a project's feature list.
Why use it?
It separates outcome checking from the reasoning used to build a feature, making it easier to identify work that does not actually pass its requirements.

Skill for Claude CodeCodex

Part of the onboard plugin — 8 skills, 5 agents shipped together

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/apurvbazari/claude-plugins/verify
Any agent
npx skills add ApurvBazari/claude-plugins --skill verify
Clone the repo
git clone --depth 1 https://github.com/ApurvBazari/claude-plugins

Made for: Claude Code, Codex.

Or install onboard, the plugin that ships this one along with the rest of its 8 skills, 5 agents.

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 verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/verify.svg)](https://agentmods.dev/skills/apurvbazari/claude-plugins/verify)
Your own site
<a href="https://agentmods.dev/skills/apurvbazari/claude-plugins/verify"><img src="https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,534 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 $0.00057 $0.01534
Opus 5 $0.00028 $0.00767
Sonnet 5 $0.00011 $0.00307
Haiku 4.5 $0.00006 $0.00153

Measured 3d ago against content hash 22e615216039, 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 3d 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.

onboard/skills/verify/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Skill — Independent Feature Evaluation

You are orchestrating an independent verification of features against the project's feature list. This implements the evaluator layer from Anthropic's harness design — a separate agent that judges purely on outcomes, not implementation reasoning.

Guard

Read docs/feature-list.json in the project root. If not found:

No feature list found. Create docs/feature-list.json with your project's features to enable verification.

See the harness design reference for the expected format.

Stop and do not proceed.

Step 1: Determine Mode

Parse the command arguments:

  • /onboard:verify (no args) — verify all features where passes is false
  • /onboard:verify F001 — verify a single feature by ID
  • /onboard:verify --sprint 1 — verify all features in Sprint 1 and check sprint contract

Read docs/feature-list.json and identify the target features based on the mode.

Report to the developer:

Verification mode: [all incomplete / feature F001 / Sprint 1] Features to test: [N] Strategy: [verificationStrategy from onboard-meta.json]

Starting independent evaluation...

Step 2: Load Verification Context

Read .claude/onboard-meta.json to get the verificationStrategy (browser-automation, api-testing, cli-execution, test-runner, or combination).

If sprint mode, also read docs/sprint-contracts/sprint-N.json for the negotiated criteria.

Step 3: Spawn Feature Evaluator

Spawn the feature-evaluator agent with:

  • The list of target feature IDs
  • The verification strategy
  • The sprint contract (if sprint mode)

The agent runs in worktree isolation (isolation: worktree) — it gets a throwaway copy of the project and is strictly read-only (it never writes docs/feature-list.json or a report file; any write in its worktree is discarded). It tests the running application and returns structured verdicts ({id, passes, evidence} per feature) plus the full verification-report body as text. You (verify) perform every write.

Read the full file on GitHub · 140 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. 3d ago First seen · 140 lines · 57 tokens per session scan A 22e615216039

Subscribe to this mod's changes

verify is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 27d ago), licensed MIT. It adds 57 tokens to every session and 1,534 once invoked, about $0.0003 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.