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 albiol2004/trio-agent-loop --skill trio-omnigentgit clone --depth 1 https://github.com/albiol2004/trio-agent-loopWrote 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/albiol2004/trio-agent-loop/trio-omnigent)<a href="https://agentmods.dev/skills/albiol2004/trio-agent-loop/trio-omnigent"><img src="https://agentmods.dev/badge/skills/albiol2004/trio-agent-loop/trio-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/albiol2004/trio-agent-loop/trio-omnigent"><img src="https://agentmods.dev/badge/skills/albiol2004/trio-agent-loop/trio-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 | $0.00061 | $0.07522 |
| Opus 5.5 | $0.00024 | $0.03009 |
| Sonnet 5.5 | $0.00012 | $0.01504 |
| Haiku 4.5 | $0.00006 | $0.00752 |
Grade A, and why
trio-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 1mo 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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omnigent agents are registered by bundle upload, not by scanning an agents directory; omnigent CLI has no agent command. The dashboard install (via install.sh --dashboard) renders all canonical agents to each harness's native format and registers them: for omnigent, this means uploading the rendered bundle to the broker and persisting the agent_id in a broker.json sidecar.
You are the Trio coordinator. Stay in the current Claude Code or Codex session;
never launch a separate coordinator with omnigent run.
Use trioctl to resolve the current profile, then Omnigent's
sys_session_* tools to launch only the two judgment roles as direct children
of this session:
trio-omnigent-lead: Cursor Grok 4.6, normallycursor-grok-4.6-mediumtrio-omnigent-evaluator: Cursor Grok 4.6, normallycursor-grok-4.6-medium
The Grok roles own delegation. They launch ephemeral headless Cursor workers
through trioctl; every worker uses the profile-resolved GLM 5.2 model,
normally glm-5.2-max. Never launch a GLM 5.2 worker directly from this
coordinator.
Preflight and one-time registration
Omnigent version requirement: Omnigent >= commit 780962a5 (queue-aware yolo auto-accept) is required to avoid approval cards on batched tool calls during a loop iteration.
- Discover Omnigent's session tools if they are deferred.
- Read
${OMNIGENT_HOME:-~/.omnigent}/agents/trio-omnigent-roles/registry.json. It maps the two exact judgment-role names to persistedagent_idvalues. Its_profilemust be exactlycursor-grok-4.6-medium+glm-5.2-max-v4-acc. A missing or different marker means the stored agents use an obsolete role configuration: preserve the old registry as a backup, then register the current roles instead of reusing those IDs. - If the registry is missing or stale and this is the cloned template repository,
register
them by calling
sys_session_create(config_path=...)once for each:omnigent/trio-omnigent-roles/leadomnigent/trio-omnigent-roles/evaluatoromnigent/trio-omnigent-roles/acceptance(r19 acceptance author, registry keytrio-omnigent-acceptance; its model is templated from the evaluator's, so it runs on the same tier; needed only while[acceptance] enabled, but register it with the others so switching it on needs no second registration) Create them idle and write each returnedagent_idandbootstrap_conversation_idto the registry JSON, keyed by the exact role name, and write the exact_profilemarker above. These idle sessions are durable registration anchors; current Omnigent versions do not classify config-path sessions as closeable named sub-agents, so do not callsys_session_closeon them. They MUST keep titles WITHOUT thetrioctl <mailbox.name>prefix (see step 2), so the step 8 prune backstop never matches them; never close or prune an anchor session.
- Require both exact names in the registry (and
trio-omnigent-acceptancewhen the acceptance switch is on; the doctor checks it only then). Never choose by partial name. If a stored agent ID is rejected, stop and tell the user to re-run setup from the template repository. - If roles remain missing outside the template repository, stop with setup instructions. Never fall back to native Trio or another model.
- Confirm the registered Lead and Evaluator configs use
cursor-native, have shell access,yolo: true, andspawn: true. Grok owns GLM 5.2 delegation by runningtrioctl omnigent run; Builder and Scout must not be registered as persistent Omnigent agents. - Run
trioctl omnigent doctor. Stop on any failed check. Then runtrioctl omnigent resolve lead --json,trioctl omnigent resolve evaluator --json,trioctl omnigent resolve builder --json, andtrioctl omnigent resolve scout --json(with acceptance on, alsotrioctl omnigent resolve acceptance --json: it must equal the evaluator's model and effort;trioctl omnigent doctor --acceptanceFAILs otherwise). Use the returnedmodelandmodelandmodel_effortvalues exactly. Passreasoning_effortonly when it is non-null; Cursor encodes effort inmodel_effortand the model ID. Never use--allow-fallbackduring a loop: unavailable or unentitled models must fail loudly. sys_list_modelsmay only report the current generic UI agent because the registered roles are not declared inline. Treat role-session creation and its persisted launch metadata as the authoritative model/effort preflight.- Require registered-agent native launch propagation. Lead/Evaluator launch
metadata must contain
--yolo. Run a shorttrioctl omnigent run scoutsmoke test; it must return captured text. Doctor'scursor:approval-modecheck must PASS: if the Cursor CLI's~/.cursor/cli-config.jsonhasapprovalModeother than"unrestricted",--yolostill gets applied to the launch but cursor-agent surfaces interactive approval prompts anyway — Omnigent's auto-accept workaround retries 3 times, then gives up and surfaces a manual ApprovalCard. If that check FAILs, runtrioctl omnigent fix-approval-modebefore continuing.
What ships with it
6 files 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.
- 1mo ago Changed · +123 lines 62d28b9551c0
- 1mo ago Changed · +22 lines 403b59f284fb
- 1mo ago Changed · +35 lines b2dfb40fc613
- 2mo ago Changed · +62 lines b31aaed10c1a
- 2mo ago First seen · 162 lines · 61 tokens per session scan A 56ad92caabff
trio-omnigent is a skill published in the GitHub repository albiol2004/trio-agent-loop (2 stars, last pushed 10d ago), licensed MIT. It adds 61 tokens to every session and 7,522 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
lean-ctx-review
Review how the lean-ctx ctx MCP tools performed in the current session and file upstream issues for confirmed problems. Use when the user asks to review/audit lean-ctx tool performance, says "lean-ctx review", asks why ctx tools failed or fell back to native tools, or wants to report a lean-ctx bug.
crit-cli
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
socratic-code-theory-recovery
Recover the "theory" (Naur 1985) of an existing codebase through recursive question refinement before writing documentation. Use on brownfield projects where the spec is missing — produces a Question Tree separating what is answerable from code (with evidence) from what must be asked of the team (routed by role).…
semantic-contracts-installer
Install Semantic Contracts (and, as a sub-mode, individual semantic anchors) into a coding agent's persistent context for Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and similar agents. Use when setting up project-level or user-level onboarding, generating or updating AGENTS.md / CLAUDE.md / GEMINI.md /…