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 inbound-triage.tmpgit 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/inbound-triage.tmp)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/inbound-triage.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/inbound-triage.tmp/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/inbound-triage.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/inbound-triage.tmp.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 | $0.00069 | $0.00982 |
| Opus 5.5 | $0.00028 | $0.00393 |
| Sonnet 5.5 | $0.00014 | $0.00196 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
inbound-triage 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 11d 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.
This is a copy
100% identical to inbound-triage — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbound triage — raw input to decision-ready items
Triggers: a raw feedback/transcript paste ("Here are today's messages from Veran chat:", "Some feedback from Mauro:", "comments from the PR"), /triage, "triage this", "process the feedback", "triage the inbox"
The acceptance boundary (non-negotiable)
- Nothing dispatches without selection. No implementation threads, backlog writes, replies, or session spawns until the operator picks numbered items.
- Uncertain dedup is surfaced, never silenced. A "probably seen already" item is shown with its uncertainty, not auto-marked processed.
Input sources (in priority order)
- Direct paste (primary) — raw text in the conversation, any channel, any format. This is the operator's real habit; NEVER redirect them to files. Record
sourceas a short label likepaste:mauro-chat-2026-08-28. - Inbox files (optional, for automation later) —
<project>/.omo/inbox/*.md. Process unclaimed files (a file is consumed when a registry entry cites its name + content hash). A scheduled worker may use this dir eventually; the human never has to touch it.
- Registry:
<project>/.omo/inbox/registry.jsonl— one JSON object per item ever triaged, regardless of input source. The registry is the dedup memory; it is written by you at the selection checkpoint, not by the operator.
Workflow
1. Collect
Take the raw input from the paste above (or one inbox file at a time). If the paste is ambiguous about channel or sender, ask one clarifying question — otherwise proceed.
2. Parse to items
Split the dump into atomic items. Each item gets: id, source (file + channel), type (bug|request|concern|idea|decision), quote (verbatim, ≤200 chars), category, priority (P0–P3), feature attribution, context pointers. Items that are pure noise (greetings, logistics) are marked skipped with a one-line reason — never silently dropped.
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.
- 11d ago First seen · 59 lines · 69 tokens per session scan A ecfde2639a4c
inbound-triage is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 982 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to inbound-triage, differing in 0 lines, and is treated as a copy.
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.