spec-harness-verify

spec-harness-verify is a skill for Claude Code from chohra-med/expo_boilerplate. It costs 66 tokens per session (327 once invoked), scanned A, original, MIT.

A verification workflow that asks a separate, clean-context agent to check a project against its written goal. It reports PASS or FAIL using the goal's explicit end-state checks.

In plain words
What is it for?
Use it to verify completed work against goal.md, gather evidence for each required check, and identify failures that need correction.
Why use it?
It avoids relying only on the agent that made the changes or on passing tests, which may not prove that the requested outcome was achieved.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions AGENTS.md.

Good fit Use it to verify completed work against goal.md, gather evidence for each required check, and identify failures that need correction.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chohra-med/expo_boilerplate/spec-harness-verify
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.

Any agent
npx skills add chohra-med/expo_boilerplate --skill spec-harness-verify
Clone the repo
git clone --depth 1 https://github.com/chohra-med/expo_boilerplate

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 spec-harness-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/chohra-med/expo_boilerplate/spec-harness-verify/github.svg)](https://agentmods.dev/skills/chohra-med/expo_boilerplate/spec-harness-verify)
Your own site
<a href="https://agentmods.dev/skills/chohra-med/expo_boilerplate/spec-harness-verify"><img src="https://agentmods.dev/badge/skills/chohra-med/expo_boilerplate/spec-harness-verify/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 spec-harness-verify

Your own site · 80×15
<a href="https://agentmods.dev/skills/chohra-med/expo_boilerplate/spec-harness-verify"><img src="https://agentmods.dev/badge/skills/chohra-med/expo_boilerplate/spec-harness-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 327 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00066 $0.00327
Opus 5 $0.00033 $0.00163
Sonnet 5 $0.00013 $0.00065
Haiku 4.5 $0.00007 $0.00033

Measured 12d ago against content hash e77a78b225b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

spec-harness-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 12d 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/spec-harness-verify/SKILL.md · 21 lines

What it actually says

spec-harness-verify

Spawn the sdd-verifier with a clean context. It runs each goal.md end-state check literally (no inference) and emits RESULT: PASS|FAIL + evidence. It must not be the agent that wrote the code.

Run it

  1. Load the full procedure — read the command doc and follow it exactly: .claude/commands/spec-harness/verify.md (this repo) or the spec-harness source commands/verify.md.
  2. Agents — spawn from .claude/agents/: verifier.
  3. Stay inside the 3 pillars — memory bank ( .memory/) · Spec-Driven Development · Harness (ratchet AGENTS.md + verifier + learning loop). Read SPEC-HARNESS.md for how this repo is wired.

Non-negotiables

  • The ratchet only tightens (rules are append/sharpen, never drop).
  • Nothing is "done" until the separate verifier returns PASS against goal.md.
  • Every correction or FAIL cause goes through spec-harness-learn → a dated rule.
  • Never scaffold the second-brain vault. Never commit a client repo unless asked.
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. 12d ago First seen · 21 lines · 66 tokens per session scan A e77a78b225b8

Subscribe to this mod's changes

spec-harness-verify is a skill published in the GitHub repository chohra-med/expo_boilerplate (34 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 327 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 2026-08-30.

Related

Other skills, from other repositories

react-native-testing

Deep React Native Testing Library (RNTL) reference — v13 (React 18 sync) and v14 (React 19 async), queries, userEvent, matchers, anti-patterns.

maikotrindade/awesome-react-native-skills · 45 tokens

monorepo-dev-workflow

Use when building, testing, linting, formatting, typechecking, or running any app or package in the ffmpeg-video-composer monorepo, or when looking for the right pnpm/vp command.

heristop/leclap · 50 tokens

Detox React Native Testing

End-to-end testing for React Native apps using Detox with gray-box testing, synchronization, device simulation, and CI integration.

PramodDutta/qaskills · 30 tokens

react-native-brownfield-migration

Provides an incremental adoption strategy to migrate native iOS or Android apps to React Native or Expo using @callstack/react-native-brownfield for initial setup. Use when planning migration steps, packaging XCFramework/AAR artifacts, and integrating them into host apps.

maikotrindade/awesome-react-native-skills · 59 tokens

react-native-core

React Native core components, layout, styling, animations, lists, platform APIs, and best practices. Use when building iOS/Android UIs with native components.

maikotrindade/awesome-react-native-skills · 37 tokens

upgrading-react-native

Upgrades React Native apps to newer versions by applying rn-diff-purge template diffs, updating package.json dependencies, migrating native iOS and Android configuration, resolving CocoaPods and Gradle changes, and handling breaking API updates. Use when upgrading React Native, bumping RN version, updating from RN 0.x…

maikotrindade/awesome-react-native-skills · 83 tokens