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.
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 omnigent-ai/omnigent --skill verify-omnigentgit clone --depth 1 https://github.com/omnigent-ai/omnigentWrote 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/omnigent-ai/omnigent/verify-omnigent)<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.
<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>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 | $0.00100 | $0.01231 |
| Opus 5.5 | $0.00040 | $0.00492 |
| Sonnet 5.5 | $0.00020 | $0.00246 |
| Haiku 4.5 | $0.00010 | $0.00123 |
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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 112 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-envwrapspython -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
-
Install dependencies and build the web UI once per checkout:
uv sync --frozen --group test pnpm install --frozen-lockfile --filter web && pnpm --filter web run build -
Start an instance and load its paths:
verify-env start # waits until the runner is online, about 10 seconds eval "$(verify-env paths)"startwritesVERIFY_ROOTto.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.
In CI, the repro workflow already runs this environment. Use
python -m dev.repro_env exec -- ... there instead of starting another.
Doctor
Run verify-env doctor before the first drive, after any failed drive, and
whenever something looks off. It checks that the instance is ready, that its
supervisor is alive, that the runner and model server answer, and it warns when
the checkout has moved since launch. A warning about a moved checkout means the
instance runs old code: stop it and start a new one.
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.
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.
- today First seen · 112 lines · 100 tokens per session scan A 8d098ed894b3
verify-omnigent is a skill published in the GitHub repository omnigent-ai/omnigent (10,378 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 1,231 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.
Other skills, from other repositories
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against…