Recursive Decision Ledger

SkillCloud & infra

The recursive-decision-ledger skill lets an AI agent run repeated rollouts while keeping an append-only decision ledger of trials, marks, coherence checks, and promotion gates. It records each bounded search rollout in a JSONL ledger plus a readable summary. Recursive confidence alone never auto-approves live trading, deploy, or destructive actions; explicit user approval is required.

Use Recursive Decision Ledger in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Recursive Decision Ledger and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Recursive Decision Ledger skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have a task where the user asks for repeated rollouts.

Recursive Decision LedgerStart free

What your AI can do with it

  • Run repeated bounded search rollouts
  • Record trial counts and candidate marks in an append-only JSONL ledger
  • Log coherence checks for each rollout
  • Enforce promotion gates so recursive confidence cannot auto-approve actions
  • Produce a readable summary alongside the ledger

Getting started

  1. Have a task where the user asks for repeated rollouts.
  2. Add the recursive-decision-ledger skill to your agent setup.
  3. Configure the ledger path for the append-only JSONL file and summary.
  4. Run the rollouts and review the ledger and summary before any promotion.

What this skill tells your AI

The instructions your AI receives, as published by affaan-m/ecc in skills/recursive-decision-ledger/SKILL.md and read by ahel’s review.

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.

Signals

GitHub stars
270k
Forks
40k
Last commit
Sep 2026

Questions

Does recursive confidence ever auto-approve live trading, deploy, or destructive actions?
No. The skill enforces promotion rules so recursive confidence alone never triggers live trading, deploys, or destructive operations without explicit user approval.
What does the ledger record?
It records trials, marks, coherence checks, and promotion gates in an append-only JSONL ledger, plus a readable summary.
When should I use this skill?
Use it when the user asks for repeated rollouts, so every trial and decision is logged and promotion stays gated.
What format is the ledger?
The ledger is an append-only JSONL file, accompanied by a readable summary.
Advanced
Item type
skill
Key
recursive-decision-ledger
Source
github.com/affaan-m/ecc