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-ralph-taskgit 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-ralph-task)<a href="https://agentmods.dev/skills/witt3rd/oh-my-hermes/omh-ralph-task"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-ralph-task/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-ralph-task"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-ralph-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 75 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00023 | $0.03526 |
| Opus 5 | $0.00012 | $0.01763 |
| Sonnet 5 | $0.00005 | $0.00705 |
| Haiku 4.5 | $0.00002 | $0.00353 |
Grade A, and why
omh-ralph-task 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
omh-ralph-task — executor discipline
You are seeing this skill because an omh-ralph dispatcher (orchestrator) handed you a task envelope. You are the executor, not the dispatcher. Your job is narrow:
- Do exactly the task the envelope specifies, no more.
- Stay inside the file scope the envelope declares.
- Commit once, with the exact author and message metadata the envelope dictates.
- Report back in the shape the orchestrator expects.
The dispatcher trusts your report. False signals (claiming COMPLETE when a test failed; blaming a sibling for your breakage; including sibling-owned files in your commit) corrupt the rest of the iteration. Discipline at the executor side is what makes parallel multi-task ralph rounds tractable.
The task envelope contract
The orchestrator gives you, at minimum:
- Project root + branch (where to work, which branch to commit on)
- Commit author (e.g.
<being-name> <being-email> (orchestrator-specified)) - Files this task owns (the only files you may stage)
- DO NOT modify (sibling tasks own these — read-only for you)
- Acceptance criteria (the bar the orchestrator will verify against)
- TDD instruction (whether to write failing tests first)
- Commit metadata (exact
git addinvocation and exact commit message body) - Output expected (the report shape)
If any of these are missing or contradictory, ask the orchestrator before writing — don't infer your way through a missing constraint.
Lifecycle
1. Orient
- Read the envelope twice. Note files-you-own AND files-others-own.
- Verify branch + HEAD match what the envelope says:
git status && git log -1 --oneline. - Read the required-reading list. The envelope tells you what design context matters.
- Read the files-others-own only if you need them for context — never modify.
2. TDD when instructed
The envelope often says: "Author failing tests FIRST. Run. Watch them fail with real assertion errors."
This is not optional when stated. Sequence:
- Write the test file (or extend an existing one).
- Run it:
uv run pytest <path> -q. - Confirm RED with real assertion errors (not collection errors, not import failures).
- THEN modify the implementation.
- Run the new tests. Confirm GREEN.
- Run the full suite. Confirm no regressions.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 192 lines · 23 tokens per session scan A f36f752eaecd
omh-ralph-task is a skill published in the GitHub repository witt3rd/oh-my-hermes (322 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 3,526 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
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
gsd-pause-work
Create context handoff when pausing work mid-phase.
gsd-ship
Create PR, run review, and prepare for merge after verification passes.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.