Five rules and a five-check script for talking to many agents (free sample)
by PaperChaseWebb
From Agent Control Room: five rules for voice control of agents (voice never approves, one typed owner yes tied to a hash, names that cannot be confused, unclear words read back, stay on your machine), and a read-only script that checks a room config for five of them and tells you whether a spoken line is a yes the room must refuse.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 5 min
- Format
- .md file
agent-control-room-five-rules-and-checks-free-sample.md · 9 KB · direct download, no signup
What you end up with
In a minute you know whether your voice setup could approve something by accident, and what to change.
What you get
- Five rules for voice control of agents
- room_mini.py: five read-only checks and a yes test
- One prompt for all four harnesses
- Worked example: 5 findings, then 0
Who it is for
Anyone about to talk to their agents, who wants to check that no spoken word can approve anything.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
Cost to run: Free.
Time to result: About five minutes to a first result
Sample prompt from the pack
Read my voice setup and tell me every way a spoken word can approve, allow or answer a permission prompt in it today. List each one with where the setting lives. Do not change anything.
The rules and the script are in the file.
Free preview of the file
# Five rules for talking to many agents, with a five-check quick check (free sample of Agent Control Room)
Version 1.0, 2026-10-28. By PaperChaseWebb. For anyone steering Claude Code, Codex, Hermes or Grok Bot sessions by voice or dictation. One Markdown file and one Python 3 script, standard library only. The script was tested on its worked example (5 findings, then 0) and on six spoken lines. It was not run with a microphone, and nothing here was loaded inside a harness for this release.
Voice tools for agents are getting good at hearing you. The risk is what they do with what they hear. If "approve it" from across the room, a misheard name, or a podcast in the background can merge a branch, the voice layer has become the weakest approval in your setup. This sample gives you the rules we hold to and a small script that checks a control room config against five of them, plus a test for whether a spoken line is a yes the room must refuse.
## Install in one line
Save this page as FREE-SAMPLE.md, then:
```
python3 -c "import re;t=open('FREE-SAMPLE.md').read();open('room_mini.py','w').write(re.search(r'~~~python\n(.*?)~~~',t,re.S).group(1))"
python3 room_mini.py said "approve it"
```
## Five rules
1. **Voice routes, reports and stops. It never approves.** "Status", "tell juniper to fix the login test" and "stop all" are fine by voice. "Yes", "approve it", "go ahead", "always allow" and "1" are refused, every time, whatever the agent is asking.
2. **One owner, one typed yeWorth knowing
- The sample checks a config and a single line; it does not listen, route or approve anything. The router, board, hooks, approvals, fifteen checks and eval set are in the full pack.
- On 2026-10-28 room_mini.py gave 5 findings on the worked example, then 0 on the fixed config, exit 2 on a missing file, and refused 5 of 5 spoken yes lines while passing a routing line. The prompt was not run inside a harness.
Questions
Does it send anything anywhere?
No. It reads one file or one line and opens no network connection.
What is in the full pack?
A router for a dozen named agents, holds on risky verbs, typed approvals tied to hashes with a verify step, tmux delivery that will not type into a waiting prompt, a status board, a redacted results inbox, hooks for three harnesses, fifteen checks and a labeled eval set of 48 commands. $29.
Details
Version 1.0 · Updated Oct 28, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related
Agent Control Room: voice control for a dozen agents
Talk to twelve agents by name from one place. Say "tell juniper to fix the login test" and it goes to juniper and only juniper, read back in a sentence. Ask "who is waiting" and the board answers with waiting on top. Say "stop all" and every session gets it. What voice never does is approve: every yes, "approve it", "go ahead" and "1" is refused, and gated actions wait for a typed yes from the owner tied to the sha256 of the request, which the agent checks before it acts.
A terminal status light for your agent hooks, with a five-check quick check (free sample)
From Agent Status Hardware: an event-to-state map for Claude Code and Codex hooks, five rules, a script that shows one colored light for all your sessions in a spare terminal window, and a read-only quick check with a worked example.
The relay packet and the routine-or-judgment table (free sample)
The packet every handoff between agents should carry, a table for which work can move to a cheaper or fallback agent and which stays with you, two rules to paste and a check prompt.
The planner and worker contract and a plan preflight check (free sample)
From Planner Over Cheap Models: the six rules that let a strong model plan while cheap or local models write the code (planner never edits, a check on every task, the check runs instead of the worker, parallel tasks own different files, high risk goes up a tier, owner yes before any worker starts), plus a read-only Python check on your plan, with a worked example and its expected output.