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 otto-review-remediationgit 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/otto-review-remediation)<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/otto-review-remediation"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/otto-review-remediation/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/otto-review-remediation"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/otto-review-remediation.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 | $0.00016 | $0.00731 |
| Opus 5.5 | $0.00006 | $0.00292 |
| Sonnet 5.5 | $0.00003 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
otto-review-remediation 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.
What it actually says
Review-remediation mode
Shared by Otto agents that remediate their own PRs (Resolve's review_pr mode).
When review_pr is present, this procedure takes precedence over the agent's
reproduction and candidate-PR discovery instructions.
Handoff contract. Finish with mode: "review_remediation", reviewed_pr_url
and pr_url set to review_pr, the scanner's review fingerprint, the handled
review ids, and the final pushed head (step 8).
- Confirm the working checkout is the named PR's current head and remains on its existing head repository and branch. Never create a replacement PR, rebase, reset, rewrite history, force-push, or push to the base branch.
- Read the PR body, diff, all reviews, inline comments, unresolved threads, current checks, Polly and OCR feedback, and recent failed job logs. Treat the latest decisive review from each human reviewer as authoritative.
- Address every current substantive
CHANGES_REQUESTEDitem from trusted human reviewers. Use the agent's investigation procedure (Resolve:resolve-investigate) for ambiguous intent or product judgment and put a supported proposal on this PR. If authoritative requests conflict, required inputs are missing, or a request is unsafe or outside authorization, explain the blocker and continue independent authorized work. Do not dismiss or silently override human reviews. - Complete the shared impact assessment for the full PR, including your
remediation edits, and run its focused checks. Commit as the agent's bot
identity (Resolve:
omni-resolve-agent[bot]), and push directly to the existing PR branch using the workflow-provided push command. For a contributor fork, use only that fixed-target command; never inspect or export its credential source. - Continue through CI/mergeability (Resolve: Step 4.2) and the shared
otto-pr-review-loopskill (Resolve: Step 4.3) until current CI is green and both Polly and OCR have completed on the current head with no actionable findings. Diagnose PR-caused failures, rerun clearly transient failures, push conservative fixes, and rerun both reviewers after every push. Run the review loop's live gate before a successful handoff. - Reply to addressed review threads with the commit and validation evidence, resolve a thread only when fully addressed, and request re-review from the humans whose change requests were handled. Never approve, dismiss a human review, or merge.
- Skip the agent's other entry phases (Resolve: reproduction handoff recovery,
fail-before proof, recording generation, candidate-fix discovery, new-PR
creation, UI-preview setup) unless already required by the PR. The trusted
workflow publishes idempotent remediation start and completion comments on
both the GitHub PR and its attached Linear issue; preserve the attached issue
in
bug_urlso those comments stay linked. - Finish with the normal handoff using
mode: "review_remediation". Setbug_urlto an attached bug when one is clear, otherwise""; setreviewed_pr_urlandpr_urltoreview_pr; include the review fingerprint, handled review ids, and final pushed head.
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 · 55 lines · 16 tokens per session scan A d00d32555ec5
otto-review-remediation is a skill published in the GitHub repository omnigent-ai/omnigent (10,832 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 731 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 2026-10-16.
Other skills, from other repositories
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
understand-pr
Review a PR the way a seasoned maintainer would — build an independent model before seeing the diff, investigate the implementation and history, verify material claims, and return a concise briefing. Use for any PR review, self-review, or re-review.
factory-gitlab-review
Review a GitLab merge request for a Factory work item using brokered source-control tools.
factory-gitlab-rereview
Re-review a GitLab merge request after new commits and reconcile the previous review.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
gh-address-comments
This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches…