Recursive Decision Ledger

by affaan-mef648e01899bMIT275K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 days ago

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 exploration, ensemble comparison, or recursive reasoning with a visible evidence trail.

AI-generated overview

Runs repeated rollouts with an append-only decision ledger of trials, marks, coherence checks and promotion gates.

What it does
This skill structures repeated rollouts or recursive prompting into a documented loop: it loads the prior ledger, captures fresh information, runs a bounded search, and marks each candidate as accept, watch, reject, decay watch or needs replay. It records rollout metadata such as trial counts, top candidates, coherence marks against the prior ledger and promotion gate results, preferring JSONL for append-only ledgers and Markdown for human summaries. It also defines promotion rules that treat recursive confidence as insufficient approval for live trading, capital allocation, production deploys, migrations or destructive operations.
When to use it
Use it when the user asks for repeated rollouts, marked decision processes, high-dimensional search, stochastic optimization, local-optima exploration, ensemble comparison, or recursive reasoning with a visible evidence trail. It is also relevant when a loop's confidence might otherwise be mistaken for approval of a live or destructive action.
Requirements
No scripts are shipped; it is instructions only. The agent needs Read, Write, Edit, Bash, Grep and Glob tools to load and append ledger artifacts.

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:

text
Ensemble matches prior winner: trueRecursive matches prior winner: falseLatest rollout match: trueLive promotion allowed: falseReason: 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:

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

Source and attribution

Source:affaan-m/eccinskills/recursive-decision-ledgerat commitef648e0

License: MIT

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal