Instructions for using Hands MCP tools to read, edit, and run code on a local computer. MCP tools are connected actions an agent can call to work with files and commands.

Selecting a workspace, reading and editing files, creating new files, planning tasks, running tests or builds, monitoring background jobs, and stopping them.

They define a repeatable workflow for making repository changes and checking them, including how to handle longer-running commands.

hands-code — Skill for Claude Code and Codex by nghyane/hands

Install

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.

Any agent

npx skills add nghyane/hands --skill hands-code

Clone the repo

git clone --depth 1 https://github.com/nghyane/hands

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nghyane/hands/hands-code/github.svg)](https://agentmods.dev/skills/nghyane/hands/hands-code)

Your own site

<a href="https://agentmods.dev/skills/nghyane/hands/hands-code"><img src="https://agentmods.dev/badge/skills/nghyane/hands/hands-code/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nghyane/hands/hands-code"><img src="https://agentmods.dev/badge/skills/nghyane/hands/hands-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 392 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 8
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.00392
Opus 5.5	$0.00018	$0.00157
Sonnet 5.5	$0.00009	$0.00078
Haiku 4.5	$0.00005	$0.00039

Measured 2mo ago against content hash 7372ed5c47d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hands-code 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 2mo 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.

crate/skills/hands-code/SKILL.md · 33 lines

What it actually says

You drive Hands: unofficial local coding tools. There is no local LLM.

Do not ask the user in chat to confirm each edit. Call the tool. ChatGPT already shows a host confirmation when it requires one.

Workspace

Each ChatGPT conversation has its own folder. set_workspace in this chat does not change other chats.

Call workspace_info first if the folder might be wrong.
If the user names a repo, call set_workspace with an absolute path, ~/…, or the folder name under ~/Dev.
Do not invent paths. If set_workspace fails, use recent from workspace_info or ask once.
If workspace_info has "session": null, pass workspace on later tool calls (same path) so another chat cannot steal the pin.

Edit

Existing file: read_file, then search_replace.
New file: write.
Several hunks or files: apply_patch.
Plan: todo_write.
Edit results include a unified diff (ChatGPT shows it as an inline card). Use that; do not re-read the whole file unless the diff is truncated. Do not paste the diff back in chat.
After each edit, run the check that would catch the mistake (run_terminal_cmd).

Commands

Use is_background: true for builds, tests, servers, or anything that may exceed ~15s. Foreground auto-backgrounds on timeout; then poll get_task_output. Stop with kill_task.

Prefer one apply_patch over many tiny search_replace calls.

Changes

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.

2mo ago Changed · +4 lines 7372ed5c47d2
2mo ago First seen · 29 lines · 46 tokens per session scan A 10f4d73de082

Subscribe to this mod's changes

hands-code is a skill published in the GitHub repository nghyane/hands (46 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 392 once invoked, about $0.0002 per session on Opus 5.5. 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.

hands-code next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hands-codenghyane/hands	Skill	46	2mo ago	Apache-2.0	A	46	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code