Recursive Decision Ledger
Make repeated model rollouts safe and legible with Muse: an append-only decision ledger of trials, marks, and coherence checks, where recursive confidence never auto-approves live or destructive actions.
- What
- Make repeated model rollouts safe and legible with Muse: an append-only decision ledger of trials, marks, and coherence checks, where recursive confidence never auto-approves live or destructive actions.
- Cost
- Free
- Needs
- Use "Recursive Decision Ledger" with your Muse.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: a discipline for "Prime Gauss" style recursive prompting that keeps the useful part (repeated trials, prior memory, fresh information, explicit marks) and removes the unsafe part (pretending the loop proves certainty). Every rollout records a ledger contract: rollout id and timestamp, prior accepted winner and watchlist, fresh information ingested, search space size, model families or heuristics used, trial and effective trial counts, top candidates, decision marks, coherence marks against the prior ledger, and the promotion gate result. Candidates are marked accept, watch, reject, decay watch, or needs replay; winners are compared against prior winners; candidates are downgraded when drift, tail risk, stale data, or failed replay invalidates the previous mark. The hard rule: 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 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, and the user approved the live step. Summaries lead with the decision, not the drama: "Rollout 15 complete. The prior winner still holds, but edge deteriorated 17%. Status: watch, not live." Prefer JSONL for append-only ledgers and Markdown for human summaries. By @affaan-m, listed here with credit to its creator. From the affaan-m/ECC repository (MIT). Honest caveats: repeated rollouts deepen computation but never prove certainty; the ledger is evidence, not authorization. Never treat a high mark as a green light for live trading or destructive actions. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseThe install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Use "Recursive Decision Ledger" with your Muse. Prerequisites: none to install. Pure guidance; a repeated-rollout problem (ensemble search, stochastic optimization, recursive reasoning) helps. 1. Open the skill: https://github.com/affaan-m/ECC/blob/main/skills/recursive-decision-ledger/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Run repeated rollouts for [problem] and keep a decision ledger" or "Mark these candidates against the prior ledger and tell me what changes." 3. Work through the rollout loop with Muse: load prior ledger, capture new information, run the bounded search, mark candidates, check coherence, append artifacts before summarizing. Tip: keep the ledger in JSONL (append-only) and write the human summary in Markdown; lead the summary with the decision, not the drama. Safety: a skill is plain-text instructions; it runs nothing by itself. Recursive confidence is never approval: default to paper, dry-run, or staged mode for trading, deploys, migrations, or destructive ops unless you explicitly approve the live step.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.