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 Parcha-ai/parcha-skills --skill hands-freegit clone --depth 1 https://github.com/Parcha-ai/parcha-skillsWrote 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/parcha-ai/parcha-skills/hands-free)<a href="https://agentmods.dev/skills/parcha-ai/parcha-skills/hands-free"><img src="https://agentmods.dev/badge/skills/parcha-ai/parcha-skills/hands-free/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/parcha-ai/parcha-skills/hands-free"><img src="https://agentmods.dev/badge/skills/parcha-ai/parcha-skills/hands-free.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 MCP Rug Pull · line 58 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00088 | $0.00778 |
| Opus 5 | $0.00044 | $0.00389 |
| Sonnet 5 | $0.00018 | $0.00156 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
hands-free 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hands Free
The user is away from the keyboard; the phone is the terminal. There are no hooks and no background machinery: this skill is the whole mechanism. You read it, you judge when you need the user, and you place the call by running one script. Nothing watches your messages or your tools to guess for you.
Mode
activate hands free→ acknowledge once, then work by the playbook below until told otherwise. The mode lives in the conversation, nowhere else.deactivate hands free→ acknowledge, and questions return to chat.
The playbook (while active)
You own two judgment calls, and both go through the same script:
- You need an answer (a question, a blocker, a choice): run
python3 scripts/call_user.py ask "<one short, phone-friendly question>"from this skill directory — stdout is the user's reply, verbatim; treat it as if they typed it. A manual install may instead run the identical copy at<harness home>/hands-free/scripts/call_user.py. - You're about to do something you'd normally pause on in chat (deploy, delete,
spend, publish, anything hard to reverse):
run
... call_user.py approve "<one-line summary of the action>"— stdout isapproveordeny. Deny means don't; find the safe alternative or park it.
Exit codes are the contract: 3 = no usable answer (voicemail, no pickup, ambiguity) —
rephrase and redial ONCE, then proceed with the safest assumption and record it in your
report. 2 = configuration problem — consult references/setup.md,
fix, retry. Never redial in a loop; two rings per need is the ceiling.
Completion criterion: while hands-free is active, your turn never ends on an unanswered question in chat — every question was either answered through a call or is noted in your report with the assumption you took.
<harness home> is ~/.claude on Claude Code, ~/.codex on Codex, and
${PI_CODING_AGENT_DIR:-~/.pi/agent} on pi. Credentials may also live in the harness-neutral
~/.config/hands-free/.env; environment variables win over either file.
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.
- 11d ago First seen · 60 lines · 88 tokens per session scan A 36849fead2ff
hands-free is a skill published in the GitHub repository Parcha-ai/parcha-skills (59 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 778 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…