Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
affaan-m avatar

Recursive Decision Ledger

  • 1.3k installs
  • 238k repo stars
  • Updated August 5, 2026
  • affaan-m/ecc

recursive-decision-ledger is a Claude Code skill that maintains an explicit, auditable decision trail for developers running agents through repeated rollouts, option exploration, or recursive reasoning workflows.

About

recursive-decision-ledger is a Claude Code skill from affaan-m/ecc for agents that must explore multiple options, run repeated trials, or perform recursive reasoning with a visible evidence trail. It preserves repeated rollouts, prior memory, fresh information, and explicit marks while avoiding false certainty from looping alone. The ledger contract records each roll's decisions and outcomes for stochastic optimization, local-optima exploration, ensemble comparison, and high-dimensional search tasks. Developers reach for recursive-decision-ledger when prompting agents through Prime Gauss-style recursive processes that need auditable marks instead of opaque iteration. Tools include Read, Write, Edit, Bash, Grep, and Glob.

  • Records every rollout with id, timestamp, prior winner, fresh information, search space size, trial counts, top candidat
  • Compares new winners against prior ledger entries and applies downgrade rules for drift, tail risk, or stale data
  • Preserves repeated trials, prior memory, and explicit marks while removing unsafe certainty claims
  • Supports JSONL for append-only ledgers and Markdown for human-readable summaries
  • Implements a bounded search + promotion gate loop that produces a visible evidence trail

Recursive Decision Ledger by the numbers

  • 1,255 all-time installs (skills.sh)
  • +84 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Ranked #914 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/affaan-m/ecc --skill recursive-decision-ledger

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1.3k
repo stars238k
Last updatedAugust 5, 2026
Repositoryaffaan-m/ecc

How do agents track decisions across recursive rollouts?

Maintain an explicit, auditable decision trail when an agent must explore multiple options, run repeated trials, or perform recursive reasoning.

Who is it for?

Agent authors running multi-trial searches, ensemble comparisons, or recursive reasoning that requires auditable decision history.

Skip if: Single-pass code generation or tasks that need deterministic output without exploratory rollouts or ledger overhead.

When should I use this skill?

User requests repeated rollouts, marked decision processes, ensemble comparison, or recursive reasoning with an evidence trail.

What you get

Explicit decision ledger with per-roll marks, prior memory, evidence trail, and compared option outcomes.

  • Decision ledger with per-roll marks
  • Documented evidence trail across rollouts

Files

SKILL.mdMarkdownGitHub ↗

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.

Related skills

FAQ

What problem does recursive-decision-ledger solve?

recursive-decision-ledger gives agents a structured ledger for repeated rollouts and option exploration. Each roll records decisions, prior memory, and fresh evidence so recursive prompting stays auditable without claiming false certainty.

When should recursive-decision-ledger be invoked?

recursive-decision-ledger fits stochastic optimization, local-optima exploration, ensemble comparison, and Prime Gauss-style recursive prompting. Skip it for single-pass tasks that do not need multi-trial marks or decision history.

AI & Agent Buildingagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.