git:20261021.c4baa52 to git:20261021.c4f7236

+ Compose the report over the user's numbers. Lead with what the gates caught, not with how often they say "needs changes". Sections:

+ 1. **TL;DR** — three lines. (a) **Errors caught**: falsified premises per run (`PROSPECT_YIELD` `fals` ÷ `runs`) and retrospect fixes absent from the bundle (`RETRO_BUNDLE` `not_in_bundle` of `cand`). (b) **Fixed cost**: `FIXED_COST_BYTES`÷4 tokens — when that line carries `partial`, call the figure a **lower bound** (the rules digest was unmeasured, so only skill discovery is counted). (c) **User-rules digest, opt-in**: `USER_RULES_DIGEST_BYTES`÷4 tokens, reported on its own line and never added to the fixed cost.

+ 2. **Errors caught** — from `PROSPECT_YIELD <runs> <cand> <val> <fals> <nm> <nm_cap> <nm_struct>`: print `runs`, candidates, validated, falsified, and falsifications per run. Report the near-miss (`nm`) count and, when the split is non-zero (`nm_struct` ≠ `nm`), the **settled share** `(cand−nm)/cand` and the **addressable-settled share** `(cand−nm)/(cand−nm_struct)` — the second excludes near-misses that no step could have addressed. From `RETRO_BUNDLE <cand> <verified> <not_in_bundle>` and `RETRO_CLAIMS <cand> <validated> <partial> <invalidated>`: how many fixes were verified, how many were absent from the bundle, and the claim outcomes. Print every `n`.

+ 3. **Cost surface** — `FIXED_COST_BYTES` (÷4 ≈ tokens; "lower bound" when `partial`), `RULES_DIGEST_BYTES` (`unmeasured` is not zero), `SKILL_DISCOVERY_BYTES`, `SKILL_COUNT`, per-session floor note: the universal fixed cost every session pays (mostly cache-eligible if the session stays warm). Then the opt-in `USER_RULES_DIGEST_BYTES` surface on its own line, labelled opt-in. Also `PATTERN_COUNT` and each `PATTERN_LIB` file with its count.

+ 4. **Verdict distribution** — prospect table with `n = PROSPECT_TOTAL` (PWC/clean/hold) and the retrospect outcome table (`RETRO_CLOSED`/`PARTIAL`/`MIXED`/`UNRESOLVED`) plus per-fix-verdict rate. State beside the table: **it measures how much the gate finds, not plan quality** — a high needs-changes rate can mean sharp gates or weak plans, and a low one the reverse. Do not rank or grade the user on it.

+ 5. **Trends** — month tables only for **falsifications per run** and **premises per run** (`PROSPECT_YIELD_MONTH <ym> <runs> <cand> <fals> <nm>`), **only for months whose runs ≥ 10 logs**. Any month below 10: omit and note "insufficient sample — directional only." If NO month clears 10, print "Not enough history for a trend yet (need ≥10 logs in a month)." — no table. The verdict mix is never trended.

+ 6. **Conditions** — one line from `GATE_MODEL` and `GATE_EFFORT` (value and `n` each; `absent` means the log carried no field). These are prospect logs only; a different model or effort level changes what a gate finds, so say so before any comparison across periods.

+ 7. **Confounds + limits** — always include the standing caveats: author-learning, the tool trains its own user, work-mix shift; and the N=1 limit (this is the user's own corpus, not a controlled study — no counterfactual proof that uncorrected plans would have shipped wrong).

+ Say "improving over time" only for falsifications per run or premises per run, and only when at least two months each clear the ≥10 threshold AND the direction is monotonic. Otherwise say "directional only."

+ Print a 3-4 line inline summary (errors caught: falsified premises per run and fixes absent from the bundle; fixed-token cost from `FIXED_COST_BYTES`, "lower bound" when `partial`; the opt-in user-rules digest on its own line; the `GATE_MODEL`/`GATE_EFFORT` conditions) and "Full report written to {knowledge_folder}/references/usage-analysis.md".

+ - **Errors caught lead; the verdict rate is not quality** — never present needs-changes or clean rate as plan quality, and never add `USER_RULES_DIGEST_BYTES` to the fixed cost.