agentmods.dev

verify-omnigent

verify-omnigent is a skill for Claude Code, Codex from omnigent-ai/omnigent. It costs 100 tokens per session (1,691 once invoked), scanned A, original, Apache-2.0.

A verification workflow for Omnigent that runs the real app in an isolated environment and records evidence of its behaviour. It also maps each user entry point to the tests that cover it.

In plain words
What is it for?
Use it to reproduce user-facing bugs, prove that a fix works, and check that a change covers every listed entry point. It can run a server, test runner, and mock model with separate data and settings.
Why use it?
It avoids relying only on code inspection or an unsafe shared server when reproducing bugs or checking fixes. It helps reveal missed screens or interaction paths.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 11krepo +83 changed 26d ago A scan 100 tokens original Apache-2.0

Good fit Use it to reproduce user-facing bugs, prove that a fix works, and check that a change covers every listed entry point. It can run a server, test runner, and mock model with separate data and settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/omnigent-ai/omnigent/verify-omnigent
View source ↗ omnigent-ai/omnigent omnigent.ai
About the project

Omnigent is an open-source orchestration layer for running and coordinating different AI coding agents through one system. It is for developers who want to combine agents, apply policies and sandboxing, and continue sessions across devices. The catalogue add-ons extend its agent workflows.

omnigent-ai/omnigent · 11,383 stars · on GitHub · omnigent.ai

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 omnigent-ai/omnigent --skill verify-omnigent
Clone the repo
git clone --depth 1 https://github.com/omnigent-ai/omnigent

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-omnigent

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/verify-omnigent"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/verify-omnigent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,691 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 $0.00100 $0.01691
Opus 5.5 $0.00040 $0.00676
Sonnet 5.5 $0.00020 $0.00338
Haiku 4.5 $0.00010 $0.00169

Measured 26d ago against content hash 3de707343c14, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-omnigent 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 26d 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.

feature-map/skills/verify-omnigent/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Omnigent

Use this skill to see a behavior happen in the real app and to prove a change, not to reason about it from code. It has two parts:

  • An isolated instance. scripts/verify-env wraps python -m dev.repro_env: a server, runner, and mock model server on private ports, with their own config, data, Claude, and Codex directories. It never touches ~/.omnigent, a running host daemon, or another developer server.
  • A feature map. feature map lists each user-facing feature's entry points, the tests that drive them, and the traps. A fix is verified only when every entry point listed for its feature has proof.

Run all commands from the repository root. Put scripts/ on your path or call feature-map/skills/verify-omnigent/scripts/verify-env directly.

Launch

  1. Install dependencies, Chromium, and build the web UI for the checkout:

    uv sync --frozen --extra all --group test
uv run --no-sync playwright install --with-deps chromium
pnpm install --frozen-lockfile --filter web && pnpm --filter web run build

  2. Start an instance and load its paths:

    verify-env start          # waits until the runner is online, about 10 seconds
eval "$(verify-env paths)"

    start writes VERIFY_ROOT to .omnigent/verify/current, so later shells find the same instance. The instance stops itself after its lease (default 90 minutes; --lease SECONDS, 60 to 21600).

Ready means the server answers, the runner reports online, and the mock model server answers. start fails with the environment's error and log path otherwise.

Ready does not check browser launch. Use the Chromium version installed by this checkout's Playwright package; if the environment provides it through PLAYWRIGHT_BROWSERS_PATH, keep that path available to the test process. --ui-skip-build reuses the existing bundle, so rebuild after frontend edits. Native-terminal journeys also need the relevant CLI and terminal prerequisites (such as tmux); a browser installation alone does not provide them.

Read the full file on GitHub · 144 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 26d ago Changed · +10 lines 3de707343c14
  2. 1mo ago Changed · +2 lines 6afed87512c7
  3. 1mo ago Changed · +20 lines dbe352ac4d38
  4. 1mo ago First seen · 112 lines · 100 tokens per session scan A 8d098ed894b3

Subscribe to this mod's changes

verify-omnigent is a skill published in the GitHub repository omnigent-ai/omnigent (11,383 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 1,691 once invoked, about $0.0004 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 2026-10-01.

DebuggingE2E testingLLMTestingagentsaiai-agentsdeveloper-toolsml
Related

verify-omnigent compared with skills from other repositories

verify-omnigent next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verify-omnigentomnigent-ai/omnigentSkill11ktodayApache-2.0A100Claude Code, Codex
reproduce-buggoogleapis/mcp-toolboxSkill17kyesterdayApache-2.0A130Claude Code, Codex
credit-note-fixeropenai/openai-agents-pythonSkill31ktodayMITA21Claude Code, Codex
iterate-implementationhumanlayer/humanlayerSkill13ktodayApache-2.0A16Claude Code, Codex
playwright-cliVoltAgent/voltagentSkill11k8d agoMITA52Claude Code
trulens-diagnosistruera/trulensSkill3.7kyesterdayMITA17Claude Code, Codex
smiles-validationsynthetic-sciences/openscienceSkill4.4ktodayApache-2.0A24Claude Code, Codex