nightly-ledger-capture — Claude Code skill: what it does, install
The nightly-ledger-capture Claude Code skill stages candidates for honesty, trust-decay, failure-mode, and decision-outcome records. It gathers local evidence from logs and Git; a human gate controls writes.
MIT ★ 26 updated 2026-11-16
npx skills add wrg32786/aigent-os --skill nightly-ledger-capture -a claude-codeWhat nightly-ledger-capture does
The skill searches local sources for evidence to support new ledger candidates. It reads the current day’s capsules, dated Session Log blocks, referenced Git commits and diffs, plus HONESTY_LEDGER.md, TRUST_DECAY.md, FAILURE_MODES.md, DECISION_LOG.md, and DECISION_OUTCOMES.md.
Candidates go to vault/memory/runtime/NIGHTLY_CAPTURE_CANDIDATES.jsonl before any human review. Mechanical claims need a current receipt, while judgment-based claims remain staged. A decision outcome can be appended directly only after an operator answer and checks for the decision, interval, and SHA-256. Local Node.js scripts handle writes; no external coordination service is required. An agent-authored entry cannot verify its own claim.
What it helps with
- stage ledger candidates from local evidence
- record testable claims about trust decay and failures
- match an operator’s answer to a decision outcome
Example prompts for the agent
- Capture tonight’s ledger candidates from today’s local evidence.
- Stage a failure-mode candidate using the verified cause and before-and-after receipts.
How to install nightly-ledger-capture
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill nightly-ledger-capture -a claude-code2Manually: put the files in place
~/.claude/skills/nightly-ledger-capture/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/nightly-ledger-capture/
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill nightly-ledger-capture -a codex2Manually: put the files in place
.agents/skills/nightly-ledger-capture/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill nightly-ledger-capture -a cursor2Manually: put the files in place
.cursor/skills/nightly-ledger-capture/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install wrg32786/aigent-os skills/nightly-ledger-capture2Manually: put the files in place
.github/skills/nightly-ledger-capture/SKILL.md1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill nightly-ledger-capture -a gemini-cli2Platform CLI
gemini skills install https://github.com/wrg32786/aigent-os --path skills/nightly-ledger-captureManually: put the files in place
.devin/skills/nightly-ledger-capture/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill nightly-ledger-capture -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about nightly-ledger-capture
How do I install nightly-ledger-capture in Claude Code?
Run npx skills add wrg32786/aigent-os --skill nightly-ledger-capture -a claude-code. The skill file is installed at ~/.claude/skills/nightly-ledger-capture/SKILL.md.
What does nightly-ledger-capture do?
It gathers local log and Git evidence for honesty, trust-decay, failure-mode, and decision-outcome ledger candidates. Candidates are staged for human review before writes.
Which sources does nightly-ledger-capture read?
It reads the current day’s capsules, dated Session Log blocks, referenced Git commits and diffs, and the honesty, trust, failure, and decision log files.
Source text
SKILL.md · MIT
---
name: nightly-ledger-capture
agent: none
description: "Stage missing honesty, trust-decay, failure-mode, and decision-outcome records from local evidence. Use when capturing nightly ledger candidates; writes require an oracle."
allowed-tools: Read, Write, Bash
user-invocable: true
status: PRODUCTION - stage first and never self-confirm
triggers:
- nightly ledger capture
- stage measurement candidates
- ledger capture
---
# /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 all are true:
1. exact authored text is `HELD | DRIFTED | REVERSED | STILL UNCLEAR`;
2. decision date and exact heading uniquely match one decision;
3. interval is exactly 30, 60, or 90 days and is due inside the documented
tolerance;
4. the interval is absent from the matching outcome entry; and
5. the pre-write SHA-256 still matches.
Invoke:
```text
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.
## Staging product
Append through the sole writer to:
`vault/memory/runtime/NIGHTLY_CAPTURE_CANDIDATES.jsonl`
```text
node daemons/nightly-ledger-stage.mjs --root <aigent-root> \
--date <YYYY-MM-DD> --candidate-json '<serialized object>'
```
Candidate fields:
```json
{
"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 mutation predicate
### Local hash-comparison Finding (Stage 1)
Opt in on the existing baseline attestation failure path:
```text
bash scripts/doctor.sh <aigent-root> --attest --finding
```
Only an undeclared required-file hash mismatch invokes capture, using the expected
hash from the baseline manifest; default attestation output stays unchanged.
Capture never changes the measured attestation class; if storage fails, one detail
line says the Finding was not recorded, and NONCOMPLIANT still exits 1.
UNKNOWN and COMPLIANT attestations emit no Finding.
The predicate evaluator also supports explicit capture:
```text
node daemons/nightly-ledger-predicate.mjs --root <aigent-root> \
--type file_sha256_equals --path <relative-artifact> \
--expected <independently-pinned-sha256> --finding
```
The evaluator compares file bytes with the caller's pinned expectation. Source
bytes are never parsed as instructions, verdicts, targets, receipts, or authority.
The ordinary invocation remains read-only. A healthy comparison emits no Finding.
A readable mismatch emits `FAIL`; absent or unreadable file evidence emits
`UNKNOWN` with a HOLD statement. Missing or non-string targets, escaping paths,
and malformed expected hashes throw before writing. Both states remain observations. A hash
mismatch alone does not establish a product defect or a verified cause.
The existing `stageLedgerCandidate` append path stores one `trust_decay` row in
`NIGHTLY_CAPTURE_CANDIDATES.jsonl` under the resolved runtime directory. It reuses
`candidate_id`, `created_at`, `claim`, `source_refs`, `status=staged`, and
`dedupe_key`. A producer-owned `finding` extension supplies:
- `producer`, `product.name`, Node version, and exact SHA-256 identities of the
evaluator, writer, and their local dependency files;
- `subject` and `subject_root`, which anchor relative artifact references;
- `state`, the embedded evaluator `receipt`, `scope`, and `exclusions`.
`--root` selects the attested tree for hashing (including literal `memory/` paths), while the Finding row goes to the resolved runtime of the process's own state root selected by `AIGENT_STATE_HOME_DIR` when set.
Finding stdout contains only `duplicate`, `state`, and `receipt_hash`; the full
row and absolute paths remain in the local ledger.
`receipt:sha256=<hash>` resolves to the embedded `finding.receipt` using the
existing `receiptHash` function. A resolved file also retains the evaluator's
`file:<path>#sha256=<hash>` reference. The receipt records the observation time,
expected hash, measured hash, and exit status. Hashes identify evidence; they are
not signatures. Runtime observations are local data, not authorized instructions.
The producer stamps time; `--now` is ignored for Findings, and tests inject a clock
through the function argument. Subjects are normalized POSIX-relative paths and
expected hashes are lowercase; Node version remains metadata outside the dedupe key.
Receipt errors contain only an error code, never an absolute path.
Sequential replay of the same product, subject, expectation, and measured outcome
returns the original row, including its original observation time. Time changes
alone do not add counts. Changed outcomes or producer bytes get distinct identities.
An identical failure after a healthy run still returns the original row, so recurrence is not counted.
This retains the existing single-writer scope; concurrent writers are not supported.
Healthy later runs do not erase, resolve, or promote historical observations.
The row stays `evidence_class=judgment` with no resolution predicate. Its measured
comparison is factual, but interpreting it still requires judgment. Existing
mechanical candidates continue to require a reproduced green receipt. Candidate
JSON cannot supply `finding` metadata; only a fresh evaluator execution can.
There is no hook activation, external write, rule change, or model call.
Nightly review and capture postconditions count Findings separately from staged
candidate pressure.
Future adapter, read-only proposal: `findingToObligation` would first check
evidence admissibility, confidence, and duplicates before existing `boardCreate`
and transition fences. UNKNOWN, refuted, duplicate, or insufficient observations
must create no work. No adapter or organizational write is implemented here.
### Existing direct mutation gate
Direct ledger mutation is legal only when:
1. `daemons/nightly-ledger-predicate.mjs` executed it;
2. type is `file_sha256_equals`, `json_field_equals`, or
`git_commit_present`;
3. arguments are structured data rooted inside the selected root, never shell
text;
4. receipt hash, observed result, literal exit, and expected result match;
5. the artifact is external to the claim narration and directly decides it;
6. mutation delegates to the existing canonical ledger owner and embeds the
receipt.
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:
```text
LEDGER_CAPTURE PASS staged=<N> direct=<N> duplicates=<N> sources=local-memory,git
```
© wrg32786 · MIT · wrg32786/aigent-os