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 mrzhangguoguo/oh-my-workbuddy --skill hudgit clone --depth 1 https://github.com/mrzhangguoguo/oh-my-workbuddyWrote 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/hud)<a href="https://agentmods.dev/skills/mrzhangguoguo/oh-my-workbuddy/hud"><img src="https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/hud/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/hud"><img src="https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/hud.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 | $0.00663 |
| Opus 5 | $0.00028 | $0.00331 |
| Sonnet 5 | $0.00011 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
hud scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ported from oh-my-codex
hud. OMX runtime conventions ($macroinvocation,omxCLI,.omx/state directory) are replaced with WorkBuddy idioms (Skill tool, Agent tool, task list,.workbuddy/memory).
HUD (progress inspection)
In OMX, the HUD was a TUI statusline plus an omx hud CLI that read .omx/state/*
files. WorkBuddy has a built-in status display — there is no separate HUD to
configure, and no .omx/ state to read. This skill is a short guide to inspecting
progress using WorkBuddy-native surfaces.
How to inspect progress
1. Task list (primary, real-time)
The task list is the canonical "HUD" for any multi-step or autonomous work.
- Use TaskList to see every tracked task with its status
(
pending/in_progress/completed/deleted) and owner. - Use TaskGet on a specific task id to see its full description, dependencies
(
blockedBy), and any notes. - Use TaskUpdate to flip a task to
in_progressorcompletedas work advances.
This replaces OMX's "modes / turns / activity" HUD entirely — each workflow phase is a task row you can watch update live.
2. Memory (durable, cross-session)
For state that must survive across sessions or be summarized for the user, append to:
.workbuddy/memory/YYYY-MM-DD.md
Use this for: last completed milestone, current phase, open decisions, and handoff
notes. It is the durable analogue of OMX's .omx/state/*.json.
3. Built-in status display
WorkBuddy's own UI already shows model, current directory, and session context. No
configuration (no config.toml [tui] status_line, no .omx/hud-config.json) is
needed or available.
Color / severity heuristic
When summarizing progress for the user, reuse a simple traffic-light convention:
- Green — on track / healthy.
- Yellow — caution (e.g. a task >70% through its budget, or a slow step).
- Red — blocked / critical (a task is blocked, or a step failed).
What this skill does NOT do
- It does not run any
omx hudcommand (no such command exists in WorkBuddy). - It does not read or write
.omx/state (that directory does not exist here).
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 · 64 lines · 55 tokens per session scan A 603a1c1385da
hud is a skill published in the GitHub repository mrzhangguoguo/oh-my-workbuddy (2 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 663 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 2026-08-31.
Other skills, from other repositories
kill-the-standup
Reads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing / blockers), and posts it to Slack. Use when asked to write a standup, generate a standup update, post to the standup channel, summarize yesterday's work, or automate the daily standup. Trigger when a…
session-handoff-resume
Skill to save ultra-compact project checkpoints and seamlessly resume work across accounts or new chat sessions with minimum token consumption / Skill untuk menyimpan checkpoint proyek yang super ringkas dan melanjutkan pekerjaan secara efisien saat ganti akun/sesi tanpa boros token.
outlook-calendar
A skill for managing Microsoft Outlook and Microsoft 365 calendar events through a connected account.
p-daily-report
Use when reviewing what you worked on, creating standups, writing status updates, tracking daily/weekly progress, or asking "what did I do today".
daily-briefing
Daily orientation and chief-of-staff briefing. Pulls from Slack (saved items), Gmail (important/starred), Google Calendar (today's events), Jira CLI (configured projects), and Todoist CLI, validates every action item, synthesizes a prioritized briefing using three consequence-based tiers, then produces a decisive…
email-to-calendar
Extract calendar events and deadlines from emails and create calendar entries. Two modes: monitor your inbox directly, or process emails you forward to a dedicated address. Trigger when a user asks to scan emails for events, mentions an event in an email, or wants to add something from an email to their calendar.