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 witt3rd/oh-my-hermes --skill omh-triage-drivergit clone --depth 1 https://github.com/witt3rd/oh-my-hermesWrote 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/witt3rd/oh-my-hermes/omh-triage-driver)<a href="https://agentmods.dev/skills/witt3rd/oh-my-hermes/omh-triage-driver"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-triage-driver/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/witt3rd/oh-my-hermes/omh-triage-driver"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-triage-driver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.01859 |
| Opus 5 | $0.00011 | $0.00929 |
| Sonnet 5 | $0.00004 | $0.00372 |
| Haiku 4.5 | $0.00002 | $0.00186 |
Grade A, and why
omh-triage-driver 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMH Triage Driver — Driving a Triage Run
v0.1 status: Like the worker skill (
omh-triage), this dispatcher's playbook is deliberately small. Pitfalls accumulate through lived rounds. Theomh-ralplan-driverskill is the structural model — that one shipped to 25 numbered pitfalls only after multiple real runs surfaced each failure mode. This one starts at T1–T6 and grows.
When You Are the Orchestrator
You are the orchestrator if you are dispatching omh-triage against a backlog and intending to land verdicts (closures, recasts, version targeting) on real issues.
You are not the orchestrator if you are running omh-triage as an experiment to see what the skill produces (no execution intent). For experiments, skip the user sign-off gate and just observe — but mark the run as exploratory in any output doc.
Pre-flight Discipline
Before invoking omh-triage:
Audit the backlog state
- Issue count. If <10 open issues, you probably don't need triage; just decide manually. If >100 open issues, the backlog has rotted; do a manual first-pass cull before invoking.
- Time since last grooming. If <2 weeks AND no major refactor landed, may not be worth a round.
- Project board state (if any). Cards in "Won't ship" / staging columns should be drained by a triage round, not left to accumulate.
- Recent migrations or refactors. This is the load-bearing pre-flight check — what surfaces have moved since issues were filed? If the answer is "many," triage is high-leverage. If the answer is "none," triage is low-leverage.
Audit the trigger
What's the actual reason for this run?
- "About to cut version vN+1, want to know what's in scope" → triage will inform version-cut planning. Output should target the project's version field.
- "Just shipped a major migration, several issues may be stale" → triage is a cleanup pass. Output is mostly closures.
- "Backlog feels heavy, want to prune" → Skeptic's pressure dominates; Maintainer is supporting. Frame the goal accordingly.
- "Periodic hygiene, no specific motivator" → low-priority; consider deferring until a triggering reason exists.
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 · 126 lines · 22 tokens per session scan A 321dfadf83cf
omh-triage-driver is a skill published in the GitHub repository witt3rd/oh-my-hermes (322 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,859 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.