Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
실행 점수 미검증
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
This is Leg F's capture protocol. It keeps human judgment human-gated while making mechanical claims reproducible.
Read:
created_at;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.
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.
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.
Stage when a diagnosis contains a verified cause plus a real red-before and green-after receipt and the class is not already represented.
An exact operator answer has already crossed its human gate. Direct append is legal only when all are true:
HELD | DRIFTED | REVERSED | STILL UNCLEAR;Invoke:
node daemons/nightly-decision-outcome.mjs --root <aigent-root> \
--as-of <YYYY-MM-DD> --decision-date <YYYY-MM-DD> \
--decision-title "<exact heading>" --interval <30|60|90> \
--outcome "<enum>" --operator-text "<exact enum>" \
--operator-source "<durable direct operator ref>" \
--expected-file-sha "<pre-read sha256>"
The writer compare-and-swaps, appends one check, verifies it, and dedupes replay. Ambiguity remains staged.
Append through the sole writer to:
vault/memory/runtime/NIGHTLY_CAPTURE_CANDIDATES.jsonl
node daemons/nightly-ledger-stage.mjs --root <aigent-root> \
--date <YYYY-MM-DD> --candidate-json '<serialized object>'
Candidate fields:
{
"candidate_id": "nc-YYYYMMDD-NN",
"ledger": "honesty|trust_decay|failure_modes|decision_outcomes",
"claim": "...",
"source_refs": ["..."],
"evidence_class": "judgment|mechanical",
"predicate_proposal": {
"type": "file_sha256_equals|json_field_equals|git_commit_present",
"args": {},
"expected": "..."
},
"predicate_receipt": null,
"status": "staged",
"created_at": "ISO"
}
The writer allocates max suffix plus one, hashes normalized content for
dedupe, forces status=staged, serializes JSON, and re-parses the complete
file. Mechanical evidence requires a current green receipt; judgment may carry
only a proposed predicate.
Direct ledger mutation is legal only when:
daemons/nightly-ledger-predicate.mjs executed it;file_sha256_equals, json_field_equals, or
git_commit_present;Otherwise stage. Never flip a prose resolution based on self-confirmation.
After capture, run daemons/nightly-ledger-review.mjs. Its literal
FRIDAY_MEASUREMENT receipt reports the weekly counts without applying any
judgment-bearing proposal.
Return:
LEDGER_CAPTURE PASS staged=<N> direct=<N> duplicates=<N> sources=local-memory,git
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generate a structured delegation brief for any task
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.