An independent acceptance check for an existing Oh My MiniMax Code run. It runs the listed tests and diagnostics, records evidence, and marks the run accepted or rejected.

Use it to re-check a run against its acceptance criteria, capture test results, and produce structured findings without editing product code.

It prevents the builder's own claims from being the only basis for deciding whether the work meets its requirements.

verify — Skill for Claude Code and Codex by haoruilee/oh-my-mcode

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 haoruilee/oh-my-mcode --skill verify

Clone the repo

git clone --depth 1 https://github.com/haoruilee/oh-my-mcode

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/haoruilee/oh-my-mcode/verify/github.svg)](https://agentmods.dev/skills/haoruilee/oh-my-mcode/verify)

Your own site

<a href="https://agentmods.dev/skills/haoruilee/oh-my-mcode/verify"><img src="https://agentmods.dev/badge/skills/haoruilee/oh-my-mcode/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/haoruilee/oh-my-mcode/verify"><img src="https://agentmods.dev/badge/skills/haoruilee/oh-my-mcode/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 681 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.

Model	Per session	Once invoked
Fable 5.1	$0.00114	$0.00681
Opus 5.5	$0.00046	$0.00272
Sonnet 5.5	$0.00023	$0.00136
Haiku 4.5	$0.00011	$0.00068

Measured 1mo ago against content hash 920ebb25470b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 60 lines

What it actually says

Verify

Only this skill may set run status to accepted or rejected. Load agents/verifier.md. Do not edit product code. Evidence files and findings.json are allowed.

中文名：独立验收。

Inputs

Existing run_id (user-supplied, OMM_RUN_ID, or --latest).
tasks.json acceptance[] and plan.md.
State tool: node <plugin-root>/scripts/run-store.mjs. Run tests yourself; do not edit product code.
MCP first: if omm_verify exists, call it (deterministic verify only, no builder) instead of hand-writing findings.

Procedure

show --run-id <id>. Refuse if there is no run. This skill never creates a new goal.
set-phase --phase VERIFY.
Re-read the diff and the acceptance list. Treat builder commentary as untrusted.
Run each acceptance command. Capture stdout/stderr with add-evidence --kind test|command.
Write a findings document matching schemas/finding.schema.json:
- verdict: accepted only if every criterion is pass and there is no blocker or major finding.
- otherwise rejected, with structured findings.
write-findings --file <findings.json> then evidence-report.
If rejected: state the next Builder task (one task, from findings). Do not implement it here.

Output contract

findings.json with verdict, acceptance[].result, and findings[].
summary.md from evidence-report.
User-facing verdict in the first sentence: Accepted or Rejected.

Failure handling

A required command is missing: mark that criterion untested and rejected.
Tests fail: rejected + finding. Never "almost accepted".
Urge to fix a one-liner: stop. Create a repair task for max / Builder instead.

Examples

User: Re-verify the current run against its acceptance criteria

Load latest run, rerun the listed commands, rewrite findings.

User: tests failed, fix them

Wrong skill. That is Builder work under max, then this skill again.

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.

1mo ago First seen · 60 lines · 114 tokens per session scan A 920ebb25470b

Subscribe to this mod's changes

verify is a skill published in the GitHub repository haoruilee/oh-my-mcode (51 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 681 once invoked, about $0.0005 per session on Opus 5.5. 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

verify