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 EZotoff/ez-omo-config --skill workflowgit 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/skills/ezotoff/ez-omo-config/workflow)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/workflow"><img src="https://agentmods.dev/badge/skills/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/skills/ezotoff/ez-omo-config/workflow"><img src="https://agentmods.dev/badge/skills/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 | $0.00034 | $0.01012 |
| Opus 5.5 | $0.00014 | $0.00405 |
| Sonnet 5.5 | $0.00007 | $0.00202 |
| 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 8d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workflow — the standardized end-to-end loop
Input (user_message): 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.
- 8d ago First seen · 47 lines · 34 tokens per session scan A f74a7d65c128
workflow is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 1,012 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 2026-10-08.
Other skills, from other repositories
launch
Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates — the yard gate (drydock audit) and the fog gate (an effort…
omc-plan
Strategic planning with optional interview workflow.
ask-navigator
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it…
harbor
Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence.…
project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions.
ultragoal
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session.