Recursive Decision Ledger

When you need to run multiple search passes, compare candidates across trials, and keep a visible audit trail of what won and why, this gives you the structure. It pushes you to log each rollout with timestamps, prior winners, search parameters, and explicit accept/watch/reject marks. The coherence check compares new results against previous ledgers so you can spot drift or staleness. Promotion rules are strict: paper mode by default, and you only go live when the new candidate beats the prior winner, passes replay checks, and gets explicit user approval. Built for trading models, config migrations, or any high stakes optimization where recursive confidence alone is not proof.

skills.sh installs: 801
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/everything-claude-code --skill recursive-decision-ledger --agent claude-code

Installs into .claude/skills of the current project.

Files

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

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