oh-my-hermes is an operating layer for Hermes Agent that organizes requests into workflows for planning, research, creation, coding handoffs, operations, and project memory. Hermes users run these workflows through the desktop app, CLI, or messenger app, while the catalogue add-ons extend its native capabilities.
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 rlaope/oh-my-hermes --skill ulw-perfgit clone --depth 1 https://github.com/rlaope/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/rlaope/oh-my-hermes/ulw-perf)<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/ulw-perf"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/ulw-perf/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/rlaope/oh-my-hermes/ulw-perf"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/ulw-perf.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 | $0.00106 | $0.01863 |
| Opus 5.5 | $0.00042 | $0.00745 |
| Sonnet 5.5 | $0.00021 | $0.00373 |
| Haiku 4.5 | $0.00011 | $0.00186 |
Grade A, and why
ulw-perf 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 5d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultraperf
This is an OMH ultraperf workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
Why This Exists
ultraperf exists because most performance work starts unlocalized: something is slow, leaking, or expensive and nobody knows where. It forces measurement before edits, one hypothesis at a time, executor-owned changes, and a regression budget, so an optimization loop cannot end in unverified claims.
Do Not Use When
- The ask is to judge code quality, structure, or correctness rather than measured cost; use
omh-code-review. - The ask is to score model or agent output quality on a task suite.
- The request is a settings-only change, one bounded edit that is explicitly low-risk and has a direct owner and verification path, or one already-identified slow query or hotspot fix; handle it directly instead of opening a performance loop.
Examples
Good example:
- Prompt: $ultraperf checkout feels slow and the worker memory keeps climbing - find where and fix it
- Expected behavior: Audit the baseline, name the evaluator command, rank hot-path hypotheses, hand the smallest reversible fix to the selected executor, re-measure, and state the budget delta.
- Why: The problem is real but unlocalized across more than one domain.
Bad example:
- Prompt: $ultraperf make the recommender p95 under 200ms; baseline 340ms, benchmark is 'make bench'
- Expected behavior: Skip the discovery audit: record 340ms as the baseline and
make benchas the evaluator command, then hand the fix to the selected executor and re-measure against the 200ms target. - Why: A single declared measurable goal does not need a discovery loop.
Completion Checklist
- Baseline, workload, environment, and evaluator command are recorded before any edit is proposed.
- Each accepted fix names the measured hot path, the reversible change, and its owner.
- Re-measured deltas cite observed evidence; unmeasured steps stay not_observed.
- The regression budget and the gate that enforces it are stated with the tolerance.
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.
- 5d ago Changed · +1 lines dc30678d5e28
- 12d ago Changed · -1 lines c67d873b5c9a
- 14d ago Changed · +1 lines 9c6ce6b3b714
- 27d ago Changed · +3 lines 4189814b67cd
- 1mo ago Changed · -1 tokens per session eb4b3e4e58ac
- 1mo ago Changed · +9 tokens per session 248020ae2ca8
- 1mo ago Changed · +6 lines 1ae9136c6abe
- 1mo ago Changed 545b4e9dd8d8
- 1mo ago Changed · -11 lines 7d00c48839cc
- 1mo ago First seen · 134 lines · 98 tokens per session scan A 3a8e01a07176
ulw-perf is a skill published in the GitHub repository rlaope/oh-my-hermes (4,366 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,863 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
azure-diagnostics
Investigate AKS, VM, App Service, Functions and messaging incidents using scoped evidence.
kubernetes-specialist
Use when managing Kubernetes clusters, debugging Pods and workloads, designing Helm charts, reviewing manifests, or improving deployment, scaling, and observability practices.
python-performance
Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.
cloudflare-troubleshooting
Diagnose Cloudflare DNS, TLS, redirects, and configuration issues using live API settings and request evidence.
doubt-driven-development
Review high-risk or uncertain engineering decisions adversarially when independent verification can expose costly assumptions before implementation.
debugging-and-error-recovery
Diagnose failing tests, broken builds, and unexpected runtime behavior through reproduction, evidence, root-cause analysis, and focused recovery.