Catalog
affaan-m/recursive-decision-ledger

affaan-m

recursive-decision-ledger

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.

NewUpdated Sep 27, 2026

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.
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

78/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

82

Quality

75

Clarity

80

Completeness

72

Summary

This skill provides a framework for structuring recursive decision-making processes through repeated rollouts while maintaining an append-only decision ledger. It documents a "Ledger Contract" specifying what each rollout should record, coherence marks, and promotion rules that explicitly prevent recursive confidence from auto-approving live trading, deploys, or destructive operations. The skill emphasizes evidence trails, downgrade gates, and conservative defaults (paper/dry-run/preview mode).

Detected Capabilities

file readfile write (append-only ledgers)decision loggingstructured data generation (JSONL/Markdown)

Trigger Keywords

Phrases that agents use to match this skill to user intent.

recursive rollout comparisondecision ledger logginghigh-dimensional searchensemble validation gatestrading strategy backtestingdeployment confidence gatesrepeated trial tracking

Risk Signals

WARNING

Ledger used for trading strategy decisions without explicit risk limits enforcement

Promotion Rules section
INFO

Recursive confidence framing could enable overconfidence if user conflates repeated trials with statistical certainty

Rollout Loop and Summary Shape sections
WARNING

Promotion gate default (paper/dry-run) is documented but relies on user compliance; no technical enforcement of gate

Promotion Rules section

Use Cases

  • Optimize trading strategies through repeated backtests with marked decision history
  • Compare multiple high-dimensional search results across model families with confidence tracking
  • Validate deployment candidates through recursive rollouts before promoting to production
  • Audit recursive reasoning chains with visible evidence trails and coherence marks
  • Prevent auto-approval of destructive operations by enforcing explicit user gates

Quality Notes

  • Strengths: Clear contract specifying mandatory ledger fields reduces ambiguity about what constitutes a complete rollout
  • Strengths: Coherence mark format provides explicit evidence against overconfidence bias
  • Strengths: Concrete promotion rules with explicit gate conditions (replay checks, risk limits, metric comparison)
  • Strengths: Realistic summary shape example models how to lead with decision, not noise
  • Weakness: No explicit guidance on search space bounds or trial complexity limits—skill mentions 'bounded search' but does not specify how to bound it
  • Weakness: Downgrade criteria (drift, tail risk, stale data) are named but lack quantitative thresholds or decision procedures
  • Weakness: Replay checks and freshness gates are mentioned but no validation logic or examples provided
  • Weakness: No error handling guidance for when coherence marks fail or no candidate passes promotion gates
Model: claude-haiku-4-5-20251001Analyzed: Sep 27, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v2.0

    Contract changed: description

    ✦ AIAdds explicit guard against auto-approving live trading, deploy, or destructive actions without ledger review; tightens activation scope.

    triggering2026-09-27

    LATEST
  2. v1.2

    Content updated

    ✦ AIAdds MIT license attribution.

    license2026-09-09

    View This Version
  3. v1.1

    Content updated

    ✦ AINo behavioral changes detected.

    2026-07-14

    View This Version
  4. v1.0

    2026-05-25

    View This VersionInitial version

Use affaan-m/recursive-decision-ledger in your dev environment

Command Palette

Search for a command to run...