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 netil/oh-my-hi --skill omhgit clone --depth 1 https://github.com/netil/oh-my-hiWrote 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/netil/oh-my-hi/omh)<a href="https://agentmods.dev/skills/netil/oh-my-hi/omh"><img src="https://agentmods.dev/badge/skills/netil/oh-my-hi/omh/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/netil/oh-my-hi/omh"><img src="https://agentmods.dev/badge/skills/netil/oh-my-hi/omh.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 | $0.00055 | $0.00887 |
| Opus 5 | $0.00028 | $0.00443 |
| Sonnet 5 | $0.00011 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
omh 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 10d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
oh-my-hi
Oh, so that's what your coding agents have been doing!
Generates a full harness insights dashboard (Claude Code & Codex) and opens it in the browser.
Usage
/omh— Full build (parse data → build web-ui → start local HTTP server → open browser)/omh --data-only— Regenerate data files only (server continues serving updated files)/omh --enable-auto— Enable automatic rebuild on session end/omh --disable-auto— Disable automatic rebuild/omh --status— Check auto-refresh status/omh --update— Check and install latest version/omh --help— Show help
First Run Guide
If the console output after running the script shows auto-refresh not configured, ask the user:
Would you like to enable automatic dashboard data refresh on session end?
- If enabled, data is automatically refreshed at every session end, so the dashboard always shows the latest data.
- If disabled, you need to manually run
/omh --data-onlyor/omhto refresh data.
If the user chooses enable, run --enable-auto. If they choose disable, explain the manual refresh method.
Behavior
- Parses harness files from the Claude Code config directory
- Analyzes usage data (history.jsonl, transcript)
- Generates data files (
data-core.js,data-usage.js) andindex.html - Starts a local HTTP server (port 3939+) and opens browser
Architecture
- Local HTTP server:
scripts/serve.mjsservesoutput/over HTTP (port 8282, auto-detects next available); re-uses running instance on subsequent/omhcalls - --data-only: Regenerates data files only; server continues serving the updated files on next browser refresh
- Auto-refresh:
--enable-autoregisters a Stop hook — rebuilds data on every session end - Browser open: macOS
open, Windowsstart, Linuxxdg-open
Find and run the script (picks the latest version from cache, falls back to marketplaces):
PLUGINS_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/plugins"
# Pick the highest semver version from cache (sort -V handles semantic versioning)
SCRIPT=$(find "$PLUGINS_DIR/cache" -name "generate-dashboard.mjs" -path "*/scripts/generate-dashboard.mjs" 2>/dev/null \
| sort -V | tail -1)
# Fallback to marketplaces directory
if [ -z "$SCRIPT" ]; then
SCRIPT=$(find "$PLUGINS_DIR/marketplaces" -name "generate-dashboard.mjs" -path "*/scripts/generate-dashboard.mjs" -print -quit 2>/dev/null)
fi
if [ -z "$SCRIPT" ]; then
echo "oh-my-hi: ERROR — generate-dashboard.mjs not found. Try: /omh --update"
exit 1
fi
# Ensure claude CLI is findable for --update (plugin context may have a stripped PATH)
for _claude_candidate in \
"$HOME/.claude/local/claude" \
"/usr/local/bin/claude" \
"/opt/homebrew/bin/claude" \
"$HOME/.local/bin/claude" \
"/usr/bin/claude" \
"/Applications/Claude.app/Contents/Resources/bin/claude"; do
if [ -x "$_claude_candidate" ]; then
export PATH="$(dirname "$_claude_candidate"):$PATH"
break
fi
done
node "$SCRIPT" $ARGUMENTS
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.
- 10d ago First seen · 77 lines · 55 tokens per session scan A ac18df9befc4
omh is a skill published in the GitHub repository netil/oh-my-hi (56 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 887 once invoked, about $0.0003 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
deepseek-harness
Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.
steel-quench
All-angle verification meta-skill for near-complete artifacts. Turns vague design anxiety into structured challenger waves using fh-commons:quench-challenger, then drives defense and convergence until root weaknesses, residual risks, and added complexity are explicit. Covers standard attack/defense rounds, optional…
goal-quench
Wraps /goal with a tiered safety + orchestration ladder. core (default): a token budget gate (pre-run estimate), mid-run budget thresholds, and an automatic post-run quality verification via pipeline-conductor — closing /goal's two gaps (the runner's per-turn judge evaluates completion, pipeline-conductor evaluates…
preprep
A Korean-language presentation-preparation workflow that develops a topic through questions, proposes several story structures, and keeps slides, speaker notes, scripts, and related documents aligned.
install-wizard
Run when setting up a new project for the first time or onboarding after installing FH (first setup, initial configuration, onboarding start, configure project, help me set up). Performs environment detection → gap diagnosis → item-by-item suggestions → user approval → execution → acceleration baseline setup in…
phantom-quench
Input-tracing grounding audit for artifacts such as test cases, analysis reports, and design docs. Extracts proper nouns, numbers, citations, version claims, and branching conditions, then back-traces each to declared local files by grep or to external sources by fetch-and-support checks. Marks missing anchors as…