Skip to content
Skillpedia
Agents280k · #266

recursive-decision-ledger

Has your agent perform repeated tests safely. It records all decisions and checks, ensuring important actions are only approved after much confirmation.

What it does

This tool helps test and refine ideas repeatedly, recording every step. It ensures important decisions are only made after many checks and approvals, preventing mistakes.

When to use it

  • ✓When you want to test many variations of an idea.
  • ✓When searching for the best solution among many complex options.
  • ✓To ensure a decision is safe before actually applying it.

Example of what to ask your AI

“Test this marketing idea in 10 different variations and tell me which one works best, but don't publish it yet.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/affaan-m/ECC/blob/main/skills/recursive-decision-ledger/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/affaan-m/ECC/blob/main/skills/recursive-decision-ledger/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.
How it works

The tool runs your idea multiple times, noting what worked and what didn't in each attempt. It compares results with previous ones and only allows progress if everything is safe and approved.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add affaan-m/ECC --skill recursive-decision-ledger

Or download just the file:

curl -L https://raw.githubusercontent.com/affaan-m/ECC/main/skills/recursive-decision-ledger/SKILL.md -o SKILL.md
Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

Recursive Decision Ledger

Use this skill when the user is trying to force deeper computation through repeated rollouts or "Prime Gauss" style recursive prompting. Preserve the useful part: repeated trials, prior memory, fresh information, and explicit marks. Remove the unsafe part: pretending the loop proves certainty.

Ledger Contract

Every rollout should record:

  • rollout id and timestamp;
  • prior accepted winner and prior watchlist;
  • fresh information ingested;
  • search space size;
  • model families or heuristics used;
  • trial count and effective trial count;
  • top candidates;
  • decision marks;
  • coherence marks against the prior ledger;
  • promotion gate result.

Prefer JSONL for append-only ledgers and Markdown for human summaries.

Rollout Loop

  1. Load the prior ledger.
  2. Capture new information at time-step zero.
  3. Run the bounded search.
  4. Mark each candidate: accept, watch, reject, decay watch, or needs replay.
  5. Compare winners against prior winners and latest marked rollout.
  6. Downgrade candidates when drift, tail risk, stale data, or failed replay invalidates the previous mark.
  7. Append artifacts before summarizing.

Coherence Mark

Include a compact coherence mark:

Ensemble matches prior winner: true
Recursive matches prior winner: false
Latest rollout match: true
Live promotion allowed: false
Reason: replay and freshness gates not satisfied

Promotion Rules

For trading, capital allocation, production deploys, migrations, or destructive ops, recursive confidence is not approval.

Default to paper, dry-run, read-only, preview, or staged mode unless the user explicitly approves the live action and the repo/service gate supports it.

Promote only when:

  • the candidate beats the prior accepted winner on the chosen metric;
  • correctness and replay checks pass;
  • risk limits are explicit;
  • the evidence is durable;
  • the user has approved the live step when needed.

Summary Shape

Lead with the decision, not the drama:

Rollout 15 complete. The prior winner still holds, but edge deteriorated 17%.
Status: watch, not live. Next gate: 20 replay fills with fresh orderbook age
below threshold.
FAQ

What is 'Prime Gauss'?

It's a method of testing ideas repeatedly to find the best one, like a multi-stage test.

Why is it important to record everything?

Recording every step (the 'ledger') allows you to see the history, understand how a decision was reached, and ensure nothing dangerous is approved by mistake.

When can I apply a decision for real?

Only when the tool confirms the idea is safe, has passed all tests, risks are clear, and you explicitly approve the action.

Details

Original description by the author

Run repeated rollouts ("Prime Gauss" style recursive prompting) while keeping an append-only decision ledger of trials, marks, coherence checks, and promotion gates, so recursive confidence never auto-approves live trading, deploy, or destructive actions. Use when the user asks for repeated rollouts, marked decision processes, high-dimensional search, stochastic optimization, local-optima explorat

repo: affaan-m/ECC

Popularity

GitHub stars
280k
Ranking position
#266
License
MIT
Updated
10/15/2026

Is this skill useful?

0

Sign in to vote.

Comments

  • …

More skills from this repository

Similar skills