nightly-ledger-capture

Solid

Discovers missing honesty, trust-decay, failure-mode, and decision-outcome entries from local evidence; stages judgment and permits direct mutation only after an executable oracle.

AI & Automation 18 stars 5 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 87/100

Stars 20%
43
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# /nightly-ledger-capture This is Leg F's capture protocol. It keeps human judgment human-gated while making mechanical claims reproducible. ## Local sources Read: - today's valid capsules by frontmatter `created_at`; - canonical dated Session Log blocks; - explicitly referenced local Git commits and diffs; - current `HONESTY_LEDGER.md`, `TRUST_DECAY.md`, and `FAILURE_MODES.md`; - `DECISION_LOG.md` and `DECISION_OUTCOMES.md`. These sources discover claims. An agent-authored capsule or log entry cannot verify its own claim. The implementation has no dependency on an external coordination service and reports its source scope as local memory plus Git. ## Candidate predicates ### Honesty Stage when the day contains consequential multi-file work, a large change, a verified/shipped/deployed/merged claim tied to an artifact, or an uncaptured tradeoff/cost/stopped-short statement. Honesty classification requires judgment, so it is always staged. ### Trust decay Stage the one to three most consequential confident claims only when consequential work is also present. Capture the exact claim, claimant, source reference, and proposed executable resolution predicate. Later narration is not a resolution oracle. ### Failure mode Stage when a diagnosis contains a verified cause plus a real red-before and green-after receipt and the class is not already represented. ### Decision outcome An exact operator answer has already crossed its human gate. Direct append is legal only when ...

Details

Author
wrg32786
Repository
wrg32786/aigent-os
Created
2 months ago
Last Updated
3 days ago
Language
JavaScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

metabolizing-knowledge

Use when asked whether something delivered earlier still holds, when closing a milestone or running a periodic sweep over what was already marked verified, or when the set of live claims has grown too large to read and dead entries need retiring. DO NOT invoke to add, audit, or retire a decision record — route that to ledger:curating-decision-records. DO NOT invoke to propose removing code — route that to ledger:proving-code-is-dead.

0 Updated yesterday
qbs784
AI & Automation Listed

ai-native-proof-ledger

Design, implement, audit, or review verifiable history for ordinary SaaS, mobile, and serverless apps — tamper-evident audit trails, hash chains, Merkle transparency logs, witnessed checkpoints, external timestamp/chain anchoring, attestations, verifiable databases, consortium ledgers, and AI-agent action receipts. Use when a user asks to make history or audit logs tamper-evident or independently verifiable, anchor records to a blockchain, add proof/receipts/dispute bundles, choose between OpenTimestamps / EAS / immudb / Tessera / Rekor / Fabric / ChainMaker-style options, or review "blockchain" claims in a product. Do NOT use for crypto token/NFT features, mining, or trading — and do NOT use when the user only needs ordinary application logging with no external verification promise.

0 Updated today
lizliz404
AI & Automation Listed

evidence-ledger

Record every material claim as a row in `00-control/evidence-ledger.md` carrying a source-authority level and a claim state (verified, corroborated, reported, inferred, unknown, not applicable), and keep observed, interpreted, unknown, and recommended content in visibly separate blocks. Use when inventorying sources, when drafting any sentence that asserts a fact, or when a verification pass asks what backs a claim. This skill MUST be consulted because an assertion without an `[EV-####]` citation and a claim state is indistinguishable from a guess, and a package whose claims cannot be traced to executable reality fails diligence at the first spot-check.

6 Updated today
synaptiai