Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mrzhangguoguo/oh-my-workbuddynpx agentmods add skills/mrzhangguoguo/oh-my-workbuddy/omx-setupWrote 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/mrzhangguoguo/oh-my-workbuddy/omx-setup)<a href="https://agentmods.dev/skills/mrzhangguoguo/oh-my-workbuddy/omx-setup"><img src="https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/omx-setup/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/mrzhangguoguo/oh-my-workbuddy/omx-setup"><img src="https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/omx-setup.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 | $0.00043 | $0.01448 |
| Opus 5.5 | $0.00017 | $0.00579 |
| Sonnet 5.5 | $0.00009 | $0.00290 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade B, and why
omx-setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
OMX/Codex surfaces such as `~/.codex/config.toml`, `~/.codex/hooks.json`, and How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ported from oh-my-codex
omx-setup. OMX runtime conventions ($macroinvocation,omxCLI,.omx/state directory) are replaced with WorkBuddy idioms (Skill tool, Agent tool, task list,.workbuddy/memory).
oh-my-workbuddy Setup
Use this skill when the user wants to install or refresh the oh-my-workbuddy skill package for the current project and/or the user-level skill root.
Command
./omw setup [--force] [--merge-agents] [--dry-run] [--verbose] [--scope <user|project>]
If you only want lightweight AGENTS.md scaffolding for an existing repo or subtree,
edit/seed AGENTS.md directly instead of running full setup.
Supported setup flags:
--force: overwrite/reinstall managed artifacts where applicable.--merge-agents: ifAGENTS.mdalready exists, preserve user-authored content and only insert/refresh oh-my-workbuddy-managed sections between explicit<!-- OMW:AGENTS:START -->/<!-- OMW:AGENTS:END -->markers.--dry-run: print actions without mutating files.--verbose: print per-file/per-step details.--scope: choose install scope (userorproject).
Canonical skill roots
WorkBuddy loads skills from:
- User scope (recommended):
~/.workbuddy/skills/ - Project scope:
.workbuddy/skills/(repo-relative)
Legacy paths from other tools (e.g. ~/.codebuddy/skills, ~/.agents/skills) are
not valid WorkBuddy roots; if they exist alongside the canonical root, remove them to
avoid duplicate skill entries (see the doctor skill).
What setup actually does
- Resolve scope:
- explicit
--scopevalue, else - a persisted preference (when present), else
- interactive prompt on TTY (default
user), else defaultuser(safe for CI). On a TTY with a persisted choice, summarize it and ask keep / review-change / reset before proceeding.
- explicit
- Create the target skill-root directories if missing.
- Copy/refresh the bundled skills into the resolved root:
- user scope →
~/.workbuddy/skills/<name>/ - project scope →
.workbuddy/skills/<name>/
- user scope →
- Optionally seed
AGENTS.md/ project guidance (only when selected/allowed, or with--merge-agentsto refresh managed sections idempotently). - Create the memory directory (
.workbuddy/memory/) if missing so skills that use durable notes have a home.
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.
- 1mo ago First seen · 137 lines · 43 tokens per session scan B 2e5409b1428b
omx-setup is a skill published in the GitHub repository mrzhangguoguo/oh-my-workbuddy (2 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,448 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
lambchat-documents
Read and create Word and PDF documents with checked outputs.
lambchat-presentations
Turn your material into a clear, editable slide deck.
lambchat-spreadsheets
Clean tables, analyze data and create spreadsheets and charts.
lambchat-coding
Read existing code, make focused changes and verify behavior.
lambchat-research
Find sources, verify claims and write a cited research report.
lambchat-writing
Draft, rewrite, translate and summarize for your audience.