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.
npx skills add EZotoff/ez-omo-config --skill verify-built.tmpgit clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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.
[](https://agentmods.dev/skills/ezotoff/ez-omo-config/verify-built.tmp)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/verify-built.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/verify-built.tmp/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.
<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/verify-built.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/verify-built.tmp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00069 | $0.00868 |
| Opus 5.5 | $0.00028 | $0.00347 |
| Sonnet 5.5 | $0.00014 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
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 11d 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.
This is a copy
94% identical to verify-built — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 53 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.
- Executed-plan record check: if the plan shows signs of execution (any checked
- [x]box), also extract record requirements — oneExecution baseline:line and oneF#<n>: verdictline per final-wave reviewer under## Execution Record. Missing lines map to GAP ledger entries ("execution record missing: baseline" / "…: F# verdict") — flag them; never reconstruct or invent them.
3. Map to evidence
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.
- 11d ago First seen · 53 lines · 69 tokens per session scan A ea926cb60919
verify-built is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 868 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to verify-built, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
harbor
Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence.…
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
omc-review
Evaluate finished work for defects, risk, and simplification before it ships.
code-review
Use when reviewing code for bugs, security issues, performance problems, or adherence to best practices. Provides structured code review with severity levels and actionable feedback.
armada-ledger
Pick the right ledger for a finding. Use when writing defects, adversarial findings, or security findings. Triggers on: ledger, defect, adversarial, security finding, DEF-001, ADV-001, SEC-001.
armada-pr
PR-first finish for a feature lane. Use before reporting a feature done. Triggers on: PR, finish feature, gh pr create, merge, lane complete.