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.
git clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/commands/ezotoff/ez-omo-config/workflow)<a href="https://agentmods.dev/commands/ezotoff/ez-omo-config/workflow"><img src="https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/workflow/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/commands/ezotoff/ez-omo-config/workflow"><img src="https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/workflow.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 | $0.00032 | $0.01005 |
| Opus 5.5 | $0.00013 | $0.00402 |
| Sonnet 5.5 | $0.00006 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
workflow 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/workflow — the standardized end-to-end loop
Argument: the task description (what to build/fix/investigate). Optional flag --lite for bounded work (≤2 files or ≤30 min, single lane).
You (the orchestrator) run the following stages IN ORDER. Each stage has a gate; do not proceed past a failed gate. One episode manifest owns the whole run: create it at stage 3 (or earlier via scripts/episode-receipt.sh append .omo/episodes/<slug> --checkpoint).
Stage 1 — Design
Gather context (explore/codegraph), identify constraints and the one-sentence destination. Output: a short design note (problem, approach, options considered, risks) kept in the working trail — it feeds the plan doc's background section.
Stage 2 — Debate
Load the debate skill and run an adversarial pass on the design (challenge mode for small designs, panel for architecture-sized ones). The debate's verdict and strongest objections must be reflected in the plan. Gate: the debate must have produced a verdict; unresolved blockers become plan risks or kill the task early.
Stage 3 — Plan
Write .omo/plans/<slug>.md: background (incl. design note + debate outcome), ## TODOs as numbered checkboxes (1., 2., …), ## Final Verification Wave as F1., F2., … reviewer boxes. Plan must pass bash scripts/execution-record-lint.sh plan <file> would-be checks (structure, no F-boxes checked yet).
Stage 4 — Review (pre-implementation)
Dispatch Momus on the plan. Momus operates under the 4+2 round budget with structured REJECT findings; the orchestrator records each round in .omo/plans/<slug>.reviews.md (one fenced ```json block per round: verdict, round, budget, plan_digest, findings, disposition, remaining_risks). Gate: verdict OKAY or OKAY-WITH-RISKS (or ESCALATE → stop, report to the operator). Ledger must pass bash scripts/execution-record-lint.sh ledger <reviews.md>.
Stage 5 — Implementation
Execute the TODOs via delegated lanes (never implement yourself if you are the orchestrator). During execution:
- Stamp checkpoints:
scripts/episode-receipt.sh append .omo/episodes/<slug> --checkpoint --intent … --claims … --evidence-refs … --resume-pointer …at meaningful boundaries. - Cite immutable evidence (commit SHAs, frozen files) — never living documents.
- Mark each TODO
- [x]only after orchestrator-verified evidence (tests run, files inspected).
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.
- 10d ago Changed · +6 lines be1e6672d354
- 17d ago First seen · 40 lines · 32 tokens per session scan A b9ec42c6998d
workflow is a command published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,005 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 2026-09-29.
Other commands, from other repositories
set-tracker
Set the issue tracker for the current project.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
project-stage-detect
Detect project phase and recommend actions.
plan-freeze
Manually freeze a plan node, cascading to descendants. Alias for /aura-frog:plan freeze (v3.7.2+).
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
orchestrate
You are the Project Orchestrator, the ultimate enforcer of the NASAB framework principles in all project workflows. You coordinate multi-agent work while ruthlessly enforcing quality gates, capability validation, and the principle of Patience (Pillar 6): perfect before advancing.