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 agentmods add skills/atman-33/workhub/sidekick-gonpx skills add atman-33/workhub --skill sidekick-gogit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/sidekick-go)<a href="https://agentmods.dev/skills/atman-33/workhub/sidekick-go"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/sidekick-go.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.00973 |
| Opus 5 | $0.00044 | $0.00487 |
| Sonnet 5 | $0.00017 | $0.00195 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
sidekick-go 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get a sidekick: a dedicated helper agent that lives in its own pane for as long as you need it, so you can go back and forth with the same agent — review, fix, re-review — without it forgetting round one by round three. That persistence is the whole point: a fresh subagent (Agent/Task tool) starts cold every call and has to be re-briefed each time; a sidekick remembers.
This skill only works inside a supported multiplexer session (herdr or zellij; the transport is selected automatically, herdr by default). If no multiplexer session is active, stop and tell the user to start herdr (or zellij) first.
You (the caller) don't launch anything for yourself — you're already running in a live pane. dispatch.mjs finds that pane, opens the sidekick's pane next to it, and wires messaging between the two via the shared bus (the same mechanism launch-team uses for its teammates).
Step 1 — Decide the role and write the brief
Pick a role for the sidekick (e.g. "Code Reviewer", "Second Opinion", "Investigator"). Write a brief: a self-contained description of its first task. Save it to the OS temp directory (not the workspace) and capture its absolute path.
- Reference existing artifacts (diffs, plans, issues) by path/URL instead of pasting them.
- Redact secrets.
Done when: the brief is saved, its absolute path is captured, and a role is chosen.
Step 2 — Dispatch
Run the dispatcher using its absolute path — do NOT cd into the skill directory first. Always pass --cwd set to the current session working directory (the project root, not the skill directory):
node "<absolute path to dispatch.mjs>" --brief "<absolute brief path>" --cwd "<current session working directory>" --role "<sidekick role>"
The dispatcher script is located inside the installed skill directory, e.g.:
C:\Users\<user>\.claude\plugins\cache\workhub-marketplace\agent-ops\<version>\skills\sidekick-go\dispatch.mjs
Add --dry-run to print the multiplexer commands without launching. There is no A/B/C fallback here (unlike handoff-go): pane-to-pane messaging requires a multiplexer session, so the script fails fast with instructions if none is active.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 57 lines · 87 tokens per session scan A 06343dc00ab0
sidekick-go is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 973 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
xiaohongshu-image-creator
专为小红书平台运营设计的AI作图助手。当用户需要制作小红书封面图、种草图、产品展示图、生活方式图、教程类配图、个人形象照等内容时使用此技能。支持小红书特有的竖版比例、流行配色风格、爆款封面设计，以及文案与配图的智能匹配。关键词：小红书、封面、种草、配图、作图、海报、product photo、cover design.
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…
shipyard-handoff
Captures session context into .shipyard/HANDOFF.md so the next session can resume without losing progress.
trellis-spec-bootstrap
Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder…