dotfiles/claude/memory/skill-harvest-fix-lane-index.md

# Skill-harvest FIX-lane index

**Append-only.** One line per skill change applied under the `/wrap-up` §1.6 FIX lane. This
is the record the steward–jurist check-in reads; a FIX applied without a line here is a
governance failure, not a shortcut.

**Authority:** PENDING-88 → jurist design gate PASSED with conditions → REVIEWED-85
(steward-placed 2026-08-02). The lane is **PROVISIONAL** until that check-in — after the
first batch or one month, whichever comes first.

**A change belongs in the lane only if** it clears the two-clause test (*does this change
what the executor may do without asking, or what a governed artifact asserts?* — either
clause yes → PROPOSAL) **and** the hard floor. When in doubt, propose.

| # | Skill | What changed | Date | Batch |
|---|---|---|---|---|
| 1 | `symmetria` §4 (ledger template) | Added a standing `## What held` section — instruments that fired prospectively, lessons that transferred to a failure class they were not built for. Entry format: *banked-lesson → what it caught → what it would have cost*. Without it the ledger can only record debits; six hand-added `## Progress` headings were the practice compensating for the schema gap. | 2026-08-02 | 1 |
| 2 | `/wrap-up` §5 (KG append) | Added a `prevention` predicate — `{subject: <banked lesson>, predicate: "prevention", object: <the failure it stopped, and where>}`. Distinct from `drift-pattern-good-direction`: that records a good move, this records **transfer**, which the schema could not previously capture. | 2026-08-02 | 1 |
| 3 | `/wake-up` §2.b.2 | Surface one `prevention` alongside the drift-patterns, one line each way. The wake previously grepped only `drift-pattern`, so every session opened by re-reading what went wrong and never what compounded. | 2026-08-02 | 1 |
| 4 | `/wrap-up` §1 (literal question) | Retired the self-report framing of the standing question. `contamination-problem.md` names direct self-report the most contaminated form of inquiry; the guidance now prefers the checkable form the same evidence answers — *does a lesson banked from one failure prevent a different failure later?* | 2026-08-02 | 1 |

## Check-in agenda — what the steward–jurist review must cover

Batch 1 is complete, so the check-in is **due**. Two items, the second added by a later ruling:

1. **The lane itself** — do the four batch-1 changes hold up as class (i)? Was the two-clause test applied honestly, or rationalised around? Should the lane move from provisional to settled, be narrowed, or be withdrawn?

2. **The retrieval obligation** (REVIEWED-86 Q4). The jurist directed this be folded into *this* check-in rather than given a standalone cadence, on the explicit grounds that a new standing review is the shape of thing that produces another unread register. The obligation: **the record is not just written, it is read.** Its evidence is the eighteen-month gap between the steward recording *"May smooth over tensions"* (2025-01-20, in the right words, in a durable indexed file) and it reaching the doctrine that needed it. Recording was not the failure; retrieval was. The check-in should therefore ask *what banked record bears on what we are about to decide, and who reads it* — not merely confirm that things were written down.

## Batch 1 — classification note

All four were raised by the steward on 2026-07-29 and dispositioned as the first FIX-lane
batch by REVIEWED-85 itself, so their classification was ruled rather than self-assessed.
Each is class (i) — a change to what a skill **records**, not to what it **permits or
requires**. None touches an authorization boundary, gate criteria, Constraint 1, or the
escalate list. None removes, defers, or narrows the visibility of an open item; #3 and the
`prevention` predicate *widen* what reaches the steward.

**Not in this index, deliberately:** the §1.6 edit that created the lane. That change altered
what the executor may do without asking, so it was `[PROPOSAL]` by its own test — filed as
PENDING-88, design-gated by the jurist, authorized by the steward as REVIEWED-85. A lane
cannot authorize its own construction.
- 2026-08-02 · ARC `CLAUDE.md` · removed `js/ # JavaScript (theme toggle)` from the asset-structure tree — directory absent, toggle retired Stage M 2026-06-01; replaced with a retirement note. Mechanical freshness; no latitude or assertion change.
- `/wrap-up` §8 — added standing **Instruments** field (N run · M with a control written before first execution · K duplicating something already banked). Converts the 2026-08-07 one-off literal question into a series, and turns the steward's "do we need so many single-use items?" into a measured K column rather than a standing worry. — 2026-08-08
- 2026-08-24 · `/wrap-up` §7.5 + `daybook-ensure.py` SKELETON · added a standing `## Corrections` section to the daily-note format, with the rule that an empty Corrections on a working day is itself a claim · **applied on direct steward instruction, reasoning from the jurist (REVIEWED-126)** — recorded here rather than in the lane proper, since it was authorized rather than executor-classified. Changes what the note *records*, not what any party may do.