verify-built

verify-built is a skill for Claude Code, Codex from EZotoff/ez-omo-config. It costs 69 tokens per session (776 once invoked), scanned A, original, MIT.

An acceptance-check workflow that compares a software plan or specification with the implementation changes. It produces a list of gaps tied to a specific Git commit, which is a saved version of the code.

In plain words
What is it for?
Use it before accepting, submitting for review, or packaging implementation work to list requirements, compare them with the diff, and record unresolved gaps.
Why use it?
It helps reveal whether the delivered change matches what was requested before a handoff or pull request. The commit binding also shows when the check is no longer current because the code changed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before accepting, submitting for review, or packaging implementation work to list requirements, compare them with the diff, and record unresolved gaps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ezotoff/ez-omo-config/verify-built
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 EZotoff/ez-omo-config --skill verify-built
Clone the repo
git clone --depth 1 https://github.com/EZotoff/ez-omo-config

Made for: Claude Code, Codex.

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-built

README.md
[![agentmods](https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/verify-built/github.svg)](https://agentmods.dev/skills/ezotoff/ez-omo-config/verify-built)
Your own site
<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/verify-built"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/verify-built/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 verify-built

Your own site · 80×15
<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/verify-built"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/verify-built.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 776 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.
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 $0.00069 $0.00776
Opus 5 $0.00034 $0.00388
Sonnet 5 $0.00014 $0.00155
Haiku 4.5 $0.00007 $0.00078

Measured 3d ago against content hash 4f9c7fe5525c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-built 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.

skills/verify-built/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify-built — alignment check (stage 1)

Triggers: /verify-built, "verify built", "alignment check", "did we build what we planned", "acceptance check"

The acceptance boundary (non-negotiable)

  • Your output is a pass record for humans to judge, never authorization to proceed. No merges, PRs, dispatches, or continuations on the strength of your ledger alone.
  • The ledger binds to an immutable digest. If the work changes after you run, the record is stale — anyone may discard it.
  • When you are the implementer of the very work being verified, say so in the record; the operator may then route verification to an independent agent (recommended for high-risk changes).

Workflow

1. Bind to a digest FIRST

Record repo / branch / HEAD sha / dirty|clean / timestamp before reading anything. If the tree is dirty, record the diff hash too (git diff | sha1sum). This header is what makes the record trustworthy-or-discardable.

2. Extract requirements

From the active plan (.omo/plans/*.md, task brief, or issue): every requirement, checkbox, and stated done-condition — as a numbered list, each phrased as a checkable statement. Include scope prohibitions ("must not change X") as requirements.

3. Map to evidence

For each requirement, find the implementing evidence: commit sha, file:line, or test name. Rules:

  • Evidence is a pointer, not a paraphrase. "Fixed the parser" is not evidence; commit abc123, src/parser.ts:41-58 is.
  • Tests count as evidence of verification only when you can see they ran (log/output path), not that they exist.
  • Ambiguous mapping → mark INFERRED (you believe it's covered but the linkage is judgment).

Read the full file on GitHub · 51 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 · 51 lines · 69 tokens per session scan A 4f9c7fe5525c

Subscribe to this mod's changes

verify-built is a skill published in the GitHub repository EZotoff/ez-omo-config (5 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 776 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 2026-09-06.