recursive-decision-ledger

Use it when:: You ask for repeated rollouts, recursive reasoning, stochastic or high-dimensional search, or ensemble comparisons and want a visible evidence trail.
It does:: Loads the prior ledger, adds fresh information, runs a bounded search, and marks each candidate accept, watch, reject, decay watch or needs replay.
You get:: An append-only JSONL ledger, a Markdown summary that leads with the decision, and a coherence mark comparing this run's winner with earlier ones.
Won't:: Treat recursive confidence as approval for trading, deploys, migrations or destructive actions; it defaults to paper, dry-run or read-only mode.

TL;DR

Some users try to force deeper computation by having the agent repeat the same search over and over, which the skill calls "Prime Gauss" style recursive prompting. It keeps the useful parts, repeated trials, memory of earlier runs, fresh information and explicit marks, and drops the pretence that the loop proves certainty. Each rollout, one pass of the search, records its id and time, the prior accepted winner and watchlist, new information, search-space size, methods used, trial counts, top candidates, decision marks, coherence against the prior ledger and the promotion gate result. Candidates are downgraded when drift, tail risk, stale data or a failed replay undoes an earlier mark, and artifacts are appended before anything is summarized. A candidate is promoted only when it beats the prior winner on the chosen metric, passes correctness and replay checks, has explicit risk limits and durable evidence, and, for a live step, has your approval.

Summarizes the skill at d2ef268.

npx skills add https://github.com/affaan-m/ecc --skill recursive-decision-ledger

skills.sh page Source on GitHub All skills from affaan-m/ecc

Total Downloads: 5,200 on skills.sh, Nov 9, 2026
Repo stars: 299,776 affaan-m/ecc
First seen: May 25, 2026 on skills.sh

Weekly Downloads

437

+68% over the 8 weeks to Nov 9

Weekly values

Week to	Installs
Sep 21	260
Sep 28	160
Oct 5	146
Oct 12	230
Oct 19	408
Oct 26	398
Nov 2	467
Nov 9	437

Category	category:agents category:software-engineering Build agents, orchestrate workers and give agents memory. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type	type:workflow A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:none Instructions only. Works in any agent that supports skills.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	agent-workflows memory guardrails

SKILL.md

From affaan-m/ecc at d2ef268. Checked daily, last changed Nov 6, 2026.

Frontmatter

name: recursive-decision-ledger
description: 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.
license: MIT
metadata:
  origin: ECC
tools: Read, Write, Edit, Bash, Grep, Glob

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.

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.