Hands Free
Phone-call bridge for coding agents — when the user is away from the keyboard, the agent calls them (as Unc). Use when the user says "activate hands free" / "deactivate hands free" (also hands-free, handsfree), asks to route questions or approvals to a phone call, or says they're stepping away but want the work to keep moving. Works on Claude Code, Codex, and pi.
Install
$ agentstack add skill-parcha-ai-parcha-skills-hands-free ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-parcha-ai-parcha-skills-hands-free) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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 "" 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 /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 "" — stdout is approve or deny. 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](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.
` is ~/.claude on Claude Code, ~/.codex on Codex, and ${PICODINGAGENT_DIR:-~/.pi/agent} on pi. Credentials may also live in the harness-neutral ~/.config/hands-free/.env`; environment variables win over either file.
Voice discipline
Speech-to-text is lossy, so the call earns its own etiquette:
- One question per call; batch related decisions into one summary rather than serial calls.
- Ambiguous answer → one short follow-up call, not a guess.
- Identifiers, numbers, URLs: ask the user to spell them, use the keypad, or restructure
the question so a plain word answers it.
Setup
If the script or credentials are missing (exit 2, or the file isn't there), follow [references/setup.md](references/setup.md). The user may install through the harness's native package flow or npx @parcha/hands-free install --harness=, then fill either /hands-free/.env or ~/.config/hands-free/.env.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Parcha-ai
- Source: Parcha-ai/parcha-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.