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 feature-inputsgit 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/feature-inputs)<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/feature-inputs"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/feature-inputs/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/feature-inputs"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/feature-inputs.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 | $0.00024 | $0.00557 |
| Opus 5.5 | $0.00010 | $0.00223 |
| Sonnet 5.5 | $0.00005 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
feature-inputs 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a feature run
Input contract
You are invoked with exactly one work source:
feature_url: a Linear feature ticket, e.g.https://linear.app/omnigent/issue/OMNI-1234. Build this feature.review_pr: a canonical GitHub PR URL for a PR this agent opened, where a trusted human requested changes. Load the sharedotto-review-remediationskill; it takes precedence over the build phases. Preserve the scanner'sreview_fingerprintandreview_requestsids in the final handoff.
Optional fields:
skip_push(boolean): commit locally and stop before any push or PR. It takes precedence over a CI publisher contract.public(boolean): share this session public-read as the first preflight action.
Preflight (first turn)
- If
public: true, callsys_session_sharewith nosession_id,user_id: "__public__",level: "read". If it returnsaccess_denied, note that and continue. - Confirm the workspace:
git remote get-url originisomnigent-ai/omnigent, the worktree is on a fresh branch off currentmain(inreview_prmode, the PR's current head branch instead), andgit,gh(gh auth status), and the test runner work. - Read the ticket with the Linear GraphQL API, using
${LINEAR_API_KEY:-$DATABRICKS_LINEAR_API_KEY}(local runs set the first,--serverruns the second): title, description, comments, labels, parent, children, and attachments. Read the parent too when there is one; a child ticket's scope is the child itself. - Check for existing delivery. Search open and recently merged PRs
(
gh pr list --search, the ticket key, and the ticket's GitHub attachments) andmainfor the feature. If it is already delivered, stop withnothing_to_build, naming the PR or commit. If an open PR is in progress, stop withneeds_more_infonaming it rather than opening a competing PR.
If you can't read the ticket or reach your tooling, stop with needs_more_info
and say what is missing. Don't narrate a clean preflight.
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 · 50 lines · 24 tokens per session scan A c4d6c1b21f59
feature-inputs is a skill published in the GitHub repository omnigent-ai/omnigent (11,089 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 557 once invoked, about $0.0001 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 2026-10-17.
Other skills, from other repositories
configure-workspaces
Propose and generate workspace configuration files (.humanlayer/workspace.json and .humanlayer/workspace.local.json) for a repository.
implement
Drive a single workshop ticket through the inner SWE↔Tester loop. Resolves the ticket from implementyourself/tasks/, creates an implementing/from-scratch branch (a fixed default — not derived from the ticket; subsequent tickets stack on top), launches the software-engineer agent to implement it, then routes by…
describe-pr
Only use when the user explicitly invokes this skill by name.
ci-commit
Only use when the user explicitly invokes this skill by name.
orchestrate
Toolbox for driving HumanLayer from the CLI - log in, pick a host, launch tasks in their own worktrees, launch sessions, list tasks and their PRs, and copy, move, or upload task artifacts.
setup-worktree
Only use when the user explicitly invokes this skill by name.