trio-productionize-omnigent

trio-productionize-omnigent is a skill for Claude Code, Codex from albiol2004/trio-agent-loop. It costs 69 tokens per session (934 once invoked), scanned A, original, MIT.

A procedure for running a production-readiness audit of Omnigent through the current Claude or Codex session. Omnigent is the system being checked for whether it is ready for production use.

In plain words
What is it for?
Use it when explicitly asked to productionize Omnigent or run its productionize command, including checks of the configured audit roles and providers.
Why use it?
It provides a defined audit process for setup, test generation, execution, recording, issue triage, and close-out instead of an ad-hoc review.

Skill for Claude CodeCodex

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

Good fit Use it when explicitly asked to productionize Omnigent or run its productionize command, including checks of the configured audit roles and providers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/albiol2004/trio-agent-loop/trio-productionize-omnigent
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 albiol2004/trio-agent-loop --skill trio-productionize-omnigent
Clone the repo
git clone --depth 1 https://github.com/albiol2004/trio-agent-loop

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 trio-productionize-omnigent

README.md
[![agentmods](https://agentmods.dev/badge/skills/albiol2004/trio-agent-loop/trio-productionize-omnigent/github.svg)](https://agentmods.dev/skills/albiol2004/trio-agent-loop/trio-productionize-omnigent)
Your own site
<a href="https://agentmods.dev/skills/albiol2004/trio-agent-loop/trio-productionize-omnigent"><img src="https://agentmods.dev/badge/skills/albiol2004/trio-agent-loop/trio-productionize-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 trio-productionize-omnigent

Your own site · 80×15
<a href="https://agentmods.dev/skills/albiol2004/trio-agent-loop/trio-productionize-omnigent"><img src="https://agentmods.dev/badge/skills/albiol2004/trio-agent-loop/trio-productionize-omnigent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 934 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 $0.00069 $0.00934
Opus 5 $0.00034 $0.00467
Sonnet 5 $0.00014 $0.00187
Haiku 4.5 $0.00007 $0.00093

Measured 10d ago against content hash 873604b2f831, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

trio-productionize-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 10d 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.

omnigent/entrypoints/trio-productionize-omnigent/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the audit coordinator. Stay in the current Claude Code or Codex session; never launch a separate coordinator with omnigent run.

First, read and follow $PZ_HOME/command.md where PZ_HOME="${TRIO_PZ_HOME:-$HOME/.local/share/trio-agent-loop/productionize}". It is the canonical procedure: setup, batch generation, execution-loop rules, recording, triage, and close-out. This skill carries only the Omnigent dispatch. If $PZ_HOME/command.md is missing, stop and tell the user to install the assets (install.sh --productionize from the template repo).

The active trioctl profile (TRIOCTL_CONFIG, default ~/.config/trio-agent-loop/omnigent.toml) decides which provider/models serve probes vs judgments — switching work/personal profiles retargets the audit.

Preflight

  1. trioctl omnigent doctor — stop on any failed check.
  2. Resolve every role you will dispatch: trioctl omnigent resolve scout --json, trioctl omnigent resolve builder --json, trioctl omnigent resolve lead --json, trioctl omnigent resolve evaluator --json. Use returned model/effort exactly; never --allow-fallback.
  3. Confirm the trio-omnigent Lead/Evaluator registration exactly as the trio-omnigent skill's preflight describes (registry.json, _profile marker, Cursor native yolo launch metadata). Assessors reuse those registered roles; a stale marker must be backed up and re-registered before dispatch, never silently reused.

Dispatch (Omnigent)

  • scout (probe batches) → ephemeral headless Cursor workers via trioctl omnigent run scout --prompt-file <briefing> — one worker per batch file in pz-run/batches/. The briefing MUST order the worker to write its verdict JSON array to pz-run/results/<batch-stem>.json before exiting. Workers are disposable.
  • assessor:<tier> (judgment batches in pz-run/jbatches/) → Omnigent child sessions via sys_session_create with the registered trio-omnigent Lead (standard tier) or Evaluator (high tier) agent_id, model/effort from trioctl omnigent resolve. Require the assessor to read its batch file, reason over pz-run/verdicts.jsonl evidence, and write pz-run/results/<batch-stem>.json before finishing.
  • user nodes → ask the user in this session; record verbatim.

Read the full file on GitHub · 69 lines

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. 10d ago First seen · 69 lines · 69 tokens per session scan A 873604b2f831

Subscribe to this mod's changes

trio-productionize-omnigent is a skill published in the GitHub repository albiol2004/trio-agent-loop (2 stars, last pushed 10d ago), licensed MIT. It adds 69 tokens to every session and 934 once invoked, about $0.0003 per session on Opus 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.

Related

Other skills, from other repositories

taiyi-plan

A TaiyiForge planning step that turns a README, product requirements document, or technical plan into a list of separate project changes. Each change includes a suggested work profile, dependencies, and priority.

Dong90/oh-my-taiyiforge · 52 tokens

taiyi-design

A technical-design guide for planning software changes before implementation. It produces a DESIGN.md document comparing at least two approaches and recording the chosen structure and trade-offs.

Dong90/oh-my-taiyiforge · 28 tokens

taiyi-dev

A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.

Dong90/oh-my-taiyiforge · 21 tokens

taiyi-integration

A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.

Dong90/oh-my-taiyiforge · 27 tokens

taiyi-requirement

A requirements-analysis process that turns a proposed change into a REQUIREMENT.md document. It records user needs, acceptance checks, terminology, triggers, and dependencies, with different levels of detail for different project sizes.

Dong90/oh-my-taiyiforge · 27 tokens

taiyi-review

A pre-merge review guide for checking code changes, design decisions, tests, and documentation. A merge adds reviewed changes to the main code branch.

Dong90/oh-my-taiyiforge · 26 tokens