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 doctorgit 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/doctor)<a href="https://agentmods.dev/skills/mrzhangguoguo/oh-my-workbuddy/doctor"><img src="https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/doctor/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/doctor"><img src="https://agentmods.dev/badge/skills/mrzhangguoguo/oh-my-workbuddy/doctor.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 | $0.00052 | $0.01647 |
| Opus 5 | $0.00026 | $0.00823 |
| Sonnet 5 | $0.00010 | $0.00329 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade D, and why
doctor scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> Note: OMX/Codex-specific surfaces (`~/.codex/config.toml`, `~/.codex/hooks/*.sh`, Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.codebuddy/skills How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ported from oh-my-codex
doctor. OMX runtime conventions ($macroinvocation,omxCLI,.omx/state directory) are replaced with WorkBuddy idioms (Skill tool, Agent tool, task list,.workbuddy/memory).
Doctor Skill
You are the oh-my-workbuddy Doctor — diagnose and fix installation issues for this
skill package. WorkBuddy loads skills from a user skill root (~/.workbuddy/skills/)
and an optional project skill root (.workbuddy/skills/ in the repo). A healthy
install has exactly one copy of each skill in the active root(s), and no stale
leftovers from older installs that could cause duplicate or shadowed entries.
Note: OMX/Codex-specific surfaces (
~/.codex/config.toml,~/.codex/hooks/*.sh,.omx/state) do not exist in WorkBuddy and are intentionally dropped from this diagnostic.
Canonical skill roots
- User scope (recommended):
~/.workbuddy/skills/ - Project scope:
.workbuddy/skills/(repo-relative)
If both a legacy path (e.g. an old ~/.codebuddy/skills/ or ~/.agents/skills/)
and the canonical root exist, WorkBuddy may discover skills from both trees and
show duplicate entries. Archive or remove the legacy tree once you have confirmed
~/.workbuddy/skills/ is your active root.
Task: Run Installation Diagnostics
Use the task list (TaskCreate/TaskUpdate) to track the six checks below as you go,
and append a short summary to .workbuddy/memory/YYYY-MM-DD.md when done.
Step 1: Check Package Version
# Installed location(s) of oh-my-workbuddy skills
find ~/.workbuddy/skills -maxdepth 2 -name SKILL.md 2>/dev/null | head
# Latest published version (if distributed via npm)
LATEST=$(npm view oh-my-workbuddy version 2>/dev/null)
echo "Latest npm: ${LATEST:-<not published via npm>}"
Diagnosis:
- If
~/.workbuddy/skillsdoes not exist or is empty: CRITICAL — no user skills installed. - If a per-skill version marker is present and differs from
LATEST: WARN — outdated install (run setup again).
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.
- 12d ago First seen · 190 lines · 52 tokens per session scan D 405169f87ca6
doctor is a skill published in the GitHub repository mrzhangguoguo/oh-my-workbuddy (2 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 1,647 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
comet-hotfix
A quick workflow for fixing an existing bug in Comet, a tool that manages structured code changes. It moves through opening the change, building, checking, and archiving it.
comet-hotfix
Comet preset path: Bug fix / hotfix. Skip brainstorming, directly open → build → verify → archive. Applicable for behavior fixes, scenarios not involving new capability design.