Decision Council: quick mode, three seats and a scored round (free sample)
by PaperChaseWebb
Quick mode for small calls you can undo. Three seats (Offers, Craft, Rules) score every option, with doing nothing always on the table. Seven rules to paste into your agent, a sitting to copy, and a read-only script that scores it and runs ten checks.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 5 min
- Format
- .md file
decision-council-quick-mode-three-seats-scored-round-free-sample.md · 10 KB · direct download, no signup
What you end up with
A small call gets argued from three sides and scored by a script instead of by your agent's guess.
What you get
- Why one agent is a bad board
- Seven rules for agents that run a quick council
- A made-up quick sitting to copy
- council_mini.py: the weighted score, the band and ten read-only checks
Who it is for
Owners and operators who want a quick, scored second look at a small call they can undo.
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 ten minutes to a first quick sitting
Sample prompts, free to use
Quick council: [the decision]? Write sitting.md with options A, B and do nothing, seats Offers, Craft and Rules, then run python3 council_mini.py sitting.md and copy the scores exactly. Do not act on the result.
The rules, sitting and script are in the file.
Free preview of the file
# Decision Council: quick mode, three seats and a scored round (free sample) Version 1.0, 2026-11-01. By PaperChaseWebb. For owners and operators who want a small business call argued from three sides before they make it, with the arithmetic done by a script instead of the agent. One page, a sitting you can copy and one Python 3 script, standard library only, read-only: it reads one file, prints the scores and findings and changes nothing. It sends nothing and opens no network connection. No API key, no login. Tested on Linux with Python 3.13, 3.12, 3.11, 3.9 and 3.8: 5 unit tests, and every planted fault for its ten checks caught. The example studio is made up. ## Why one agent is a bad board Ask one agent whether to do the thing and it tends to agree with you. Ask it to play three advisors and they sound alike, the scores drift, and the summary reads like whatever you leaned toward. Quick mode fixes the shape of the room, not the answer: - Three seats, each a business function: Offers (price, margin, how soon money lands), Craft (can we deliver it well), Rules (which terms or rules apply). - Doing nothing is always an option. - Every seat scores every option and backs the one it scored highest. - Weights you set, with one or two seats at 3. - No seat speaks as a real person. - A script does the weighted average and the band, so the number is the number. ## Rules to paste into AGENTS.md, CLAUDE.md, a Grok Bot standing order or Hermes notes 1. When I say "quick council
Test record
- Date
- Nov 1, 2026
- What was run
- tests/test_mini.py (5), the planted faults against council_mini.py in tests/mutate.py, and the copy extracted from the sample page. Linux, Python 3.13, 3.12, 3.11, 3.9 and 3.8.
- Result
- 5 passed, 0 failed on all five versions; every planted fault for M01 to M10 caught; the extracted copy scored the example sitting A 4.3, B 7.7, C 5.2 with 0 findings.
- Not run
- Rounds 2 and 3, the verdict checks, ratification and the eval set (the full kit does those).
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- Quick mode is one round and three seats, for calls you can undo. The debate and vote rounds, five seats, the verdict checks, overrides, owner ratification and the eval set are in the full kit.
- A score is not a forecast and not legal, tax or financial advice.
- On 2026-11-01 council_mini.py passed 5 unit tests and every planted fault for its ten checks on Linux with Python 3.13, 3.12, 3.11, 3.9 and 3.8, and the copy extracted from the sample page scored the example sitting A 4.3, B 7.7, C 5.2 with 0 findings.
Questions
Does it change my files?
No. It reads the sitting you name and prints scores and findings. It opens no network connection and changes nothing.
What is in the full kit?
Five seats, three rounds, 50 checks on the brief, cards and verdict, overrides a vote cannot beat, owner ratification at your terminal, an eval set and setup for Grok Bot, Claude Code, Codex and Hermes. $39.
Details
Version 1.0 · Updated Nov 1, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related
Decision Council: argue a hard business call before you make it
Bring one hard call: a price, an offer, a hire, a contract, a big spend. Five seats (Offers, Craft, Reach, Owned and Rules) argue it over three rounds, a script checks every number against their cards, and a compliance stop cannot be outvoted. Nothing happens until you ratify it at your own terminal.
Compounding Offer Audit: five rules and a five-check script (free sample)
From the Compounding Offer Audit: five rules for scoring an offer on six tests (one owner, six scores and no total, a fact for every score, no 3 on say-so, one change on the weakest test), and a read-only script that checks one small file for them.
Check the Claim: the six questions (free sample)
Six questions, an evidence level label, the add-the-parts check, one prompt and one card template that make any agent with web search check a claim before you use it. Updated to v1.1.
Start free. Buy a file. Or have it built for you.
Free samples
Read and download in full. No signup.
Marketplace
Packs, templates, prompts and bots. One-time checkout, instant download.
Agency AI operations
Built, installed and managed. Growth Fleet starting at $2,500 setup + $750/mo, Managed Ops starting at $2,500 onboarding + $5,000/mo with a 3-month minimum.