spec-review pass: correct FR-9.2's enforcement claims, close the disclosure gap it invented

An independent spec-quality review (spec-review) found real drift and one real
gap, but also overstated FR-9.2 as an unenforced 'discipline' when three of its
four prohibitions are already mechanical (filing-plan only files verdict=='file',
requires --existing so a failed marker search can't silently duplicate, and
stability-classify rewrites rather than re-asks). Only 'what the analyst writes
into the judgments JSON' is genuinely unchecked — narrowed the claim to that.

The review also asserted an obligation — 'a run that leans on a recalled
conclusion must say so in the summary' — that didn't exist in any procedure.
Rather than strip a good idea, implemented it: skills/offload-audit/SKILL.md §7
and agents/offload-analyst.md §5 now require exactly that disclosure.

Same class of error, caught independently: FR-7.3's new stability/tracker-
separation clause describes what the analyst's spoken report can do, not what
the rendered wiki page does — snapshot_candidate carries no stability field, and
findings from stability-classify never enter the snapshot. Documented the gap
and its mechanical cause (widening the snapshot schema, not the renderer) rather
than leaving the spec's claim wrong.

FR-6.5, the FR-9.3 wing/room table, and the Q1/Q3 resolutions the review added
were checked against the shipped code and are accurate; left unchanged.

Suite: 159 assertions, exit 0.

agents/offload-analyst.md

@@ -221,6 +221,11 @@ into an issue body on the target's repo; a hedge a reader can skip is not a gate
 - List drift notes under their own heading, with the documentation fix.
 - **Emit only shapes and counts.** Never copy transcript content, file contents,
   command arguments, or user prose into a report (FR-3.5).
+- **Say when you leaned on memory.** If something recalled in §1b changed how
+  you judged a candidate, name it. The gates are pure functions of the
+  judgments JSON you hand them, so nothing mechanical can tell a reasoned
+  overrule case from a remembered one — saying so is the only control there is
+  (FR-9.2).
 
 ### 6. "Nothing to offload here" is a complete answer
 

design/spec.md

@@ -102,8 +102,11 @@ crux — see `rubric.md`), and keep watching over time.
 - A **boundary classification** of each candidate against a published rubric.
 - **On-demand runs** that each persist a snapshot, so history accumulates and
   successive runs can be diffed.
-- Two output paths per run: tracked issues on the **target** plugin's repo, and a
-  durable summary on **this** plugin's own wiki.
+- Output paths per run: tracked issues on the **target** plugin's repo (FR-6), a
+  durable summary on **this** plugin's own wiki (FR-7), and durable context in
+  mempalace so a later run does not re-derive what an earlier one concluded
+  (FR-9). Findings about the *audit itself* go to this plugin's own tracker
+  instead of the target's (FR-6.5).
 
 ### 2.2 Out of scope for v1
 
@@ -317,8 +320,22 @@ data. Canonical store: wiki. Optional presentation: artifact.
 **FR-7.3** The summary states, in this order: attribution coverage and window;
 the composition headline (how much of the plugin's spend was mechanical); the
 ranked candidate table with boundary classification and value; the diff against
-the previous snapshot; the boundary questions (low-confidence candidates) posed
-to the user; and the issues filed or updated, in full `owner/repo#num` form.
+the previous snapshot; the boundary questions posed to the user — both the
+low-confidence candidates and any downgraded by the FR-4.5 stability gate, the
+latter marked as a defect in the auditor rather than a fact about the
+target; and the issues filed or updated, in full `owner/repo#num` form,
+separating those on the target's tracker (FR-6.1) from those on this plugin's
+own (FR-6.5).
+
+*Shipped as of v0.5.0, with one gap named rather than papered over:* the
+analyst's spoken report (`skills/offload-audit` §7) makes both distinctions, but
+the **rendered wiki page does not yet.** `audit-snapshot`'s summary renderer
+lists all boundary questions uniformly and shows only each candidate's own
+issue, because `snapshot_candidate` does not carry the `stability` field and
+stability findings never enter the snapshot at all — `stability-classify` emits
+them alongside it, which is why `memory-notes` takes `--stable` as a separate
+input (FR-9.1). Closing this means widening the snapshot schema, not editing a
+renderer; until then a self-filed finding reaches the page only via `--note`.
 
 ### FR-8 — Self-application
 
@@ -382,6 +399,35 @@ harder at the reasoning, not to short-circuit it — and a remembered "we filed
 this last time" is not a filing decision at all, because the tracker, not
 memory, is the FR-5.2 identity of record.
 
+Note honestly what kind of requirement this is, clause by clause — the mix is
+not uniform, and calling the whole of FR-9.2 unenforced would be as wrong as
+calling it a gate.
+
+Three of its four prohibitions **are** mechanical, and recall cannot reach them:
+
+- *file something the gates rejected* — `bin/filing-plan` emits `action: file`
+  only for `verdict == "file"`, and skips everything else with the verdict named
+  in the reason;
+- *skip the FR-6.3 marker search* — `filing-plan plan` makes `--existing`
+  required precisely so that a search which never ran cannot default to
+  "nothing exists";
+- *re-grade a returned verdict* — the verdict is `boundary-classify`'s output,
+  and `stability-classify` rewrites rather than re-asks it.
+
+What is left unenforced is the one clause that matters most and is the hardest
+to watch: **what the analyst writes into the judgments JSON that those gates
+then consume.** The gates are pure functions of their input, so recall cannot
+corrupt a verdict directly — it can only corrupt the evidence handed to them, by
+softening a determinism test or supplying an overrule case remembered rather
+than reasoned. No script can see that, because the whole value of the read is
+that it influences judgment; a read that could not move the judgments JSON would
+be a read with no purpose.
+
+An audit trail is therefore the only available control, and it is a real
+obligation, not a hope: **a run that leans on a recalled conclusion says so in
+its report**, so a human can see the lean and discount it. That is why FR-9.2 is
+written as prohibitions rather than thresholds.
+
 **FR-9.3 — Two placements, for two different readers.**
 
 | | Wing | Room | Read | Write |
@@ -648,7 +694,10 @@ another plugin's `${CLAUDE_PLUGIN_ROOT}`. Options: (a) require `cc-tokens` on
 (c) vendor a copy. Recommendation: (a) with (b) as fallback, and **never** (c) —
 a vendored copy silently diverges on exactly the two traps that are hardest to
 notice. Better still: contribute `cc-tokens attribute --by skill|plugin --json`
-upstream to `token-budget`, so the money math has one home. *Decision needed.*
+upstream to `token-budget`, so the money math has one home. **Resolved (TASKS
+0.1): (a) with (b) as fallback**, never (c). `bin/offload-scan` tries `PATH`,
+then the cache glob, then fails loudly with an install hint. The upstream
+contribution remains optional (TASKS 8.3).
 
 **Q2 — Attribution coverage may be thin.** `attributionSkill` appears only when a
 Skill was formally invoked. Hook-driven work, agent work started without a Skill
@@ -663,6 +712,8 @@ which needs no repo access. But FR-6 files issues on the target's repo, which
 does. For `oleks/*` plugins this is fine. For third-party or official-marketplace
 plugins there is no writable tracker, and the audit degrades to summary-only
 (FR-6.4). Confirm that degradation is acceptable rather than an error.
+**Resolved (TASKS 0.2): yes** — `filing: unavailable` with the reason recorded,
+and the run summary still written.
 
 **Q4 — False positives are the real failure mode.** Recommending a script where
 judgment is needed produces something worse than the status quo: a fast,

design/tasks.md

@@ -26,45 +26,45 @@ These block design, not just code. Answers go into `Methodology/Calibration.md`.
       (`imagex:*`) plugins are excluded from the shared wiki entirely.
 - [ ] **0.4** Resolve Q5: build the Goodhart counter-metric (wontfix/revert rate)
       in v1, or note it as a manual check?
-- [ ] **0.5** Confirm the plugin name `inference-arbitrage` (vs. keeping the
-      placeholder `token-offload-audit`). The directory name must equal the
-      manifest name, so this decision also fixes the checkout path.
-- [ ] **0.6** Choose the Gitea **org**: `oleks` or `kotkan`. Not derivable from
-      the name. `kotkan` already holds `token-budget`, `worktree-discipline`, and
-      `anti-patterns` — the three closest relatives — which argues for `kotkan`.
+- [x] **0.5** Confirm the plugin name `inference-arbitrage` (vs. keeping the
+      placeholder `token-offload-audit`). **Resolved: `inference-arbitrage`**;
+      directory renamed to match the manifest name.
+- [x] **0.6** Choose the Gitea **org**: `oleks` or `kotkan`. **Resolved:
+      `kotkan`** — `kotkan/claude-plugin-inference-arbitrage`, alongside
+      `token-budget`, `worktree-discipline`, and `anti-patterns`.
 
 ## Phase 1 — Repo scaffold
 
-- [ ] **1.1** Rename `~/projects/claude-plugins/token-offload-audit/` to match the
+- [x] **1.1** Rename `~/projects/claude-plugins/token-offload-audit/` to match the
       confirmed manifest name (workspace convention: directory == manifest
       `name`), and build out the PLAN §2 layout: `plugin.json` v0.1.0, MIT
       LICENSE, `.gitignore` with `.cache/`, `.claude/`, `*.log`. The four spec
       files move with the directory and stay in-tree as the design record.
-- [ ] **1.2** `git init -b main` **inside the plugin subdir** (the workspace root
+- [x] **1.2** `git init -b main` **inside the plugin subdir** (the workspace root
       is deliberately not a repo), create `<org>/claude-plugin-<name>` on Gitea
       with no auto-init (via `cluster:gitea-agent`), push `main`.
-- [ ] **1.2b** Verify `bin/` scripts carry the executable bit
+- [x] **1.2b** Verify `bin/` scripts carry the executable bit
       (`git ls-files -s` → `100755`) — three shipped scripts make this a live
       concern. Re-check `git status` after every push: the global pre-push hook
       auto-formats markdown/JSON and may append its own commit.
-- [ ] **1.2c** Register in the local `oleks-local` marketplace
+- [x] **1.2c** Register in the local `oleks-local` marketplace
       (`~/projects/claude-plugins/.claude-plugin/marketplace.json`,
       `"source": "./<name>"`) so Phases 2–7 can test via `@oleks-local` without
       publishing anything publicly.
 - [ ] **1.3** Initialize its wiki with `Methodology/Rubric.md` (rubric.md
       verbatim, v1.0.0) and empty `Audits/` + `Data/` scaffolding.
-- [ ] **1.4** `.woodpecker/test.yaml` running `tests/run-all.sh`. **CI verifies;
+- [x] **1.4** `.woodpecker/test.yaml` running `tests/run-all.sh`. **CI verifies;
       nothing heavy runs on emmett.**
 
 ## Phase 2 — Static pass
 
-- [ ] **2.1** `bin/plugin-inventory`: target resolution (path or name, semver
+- [x] **2.1** `bin/plugin-inventory`: target resolution (path or name, semver
       pick, skip `.orphaned_at`), frontmatter parsing (~30 lines, no PyYAML).
-- [ ] **2.2** Signal extraction: procedural density, verb ratio, command-block
+- [x] **2.2** Signal extraction: procedural density, verb ratio, command-block
       signatures, rule tables, script coverage, hook/prose drift.
-- [ ] **2.3** `references/signals-catalog.md` with the verb lexicons and
+- [x] **2.3** `references/signals-catalog.md` with the verb lexicons and
       thresholds, loaded at runtime — tuning must be a reviewable diff.
-- [ ] **2.4** `tests/inventory.test.sh` against a fixture plugin tree.
+- [x] **2.4** `tests/inventory.test.sh` against a fixture plugin tree.
 - [ ] **2.5** **Calibration run** against `token-budget`, `worktree-discipline`,
       `anxious`, `memory`. Record the actual numbers in
       `Methodology/Calibration.md` and tune thresholds until the ordering matches
@@ -72,19 +72,19 @@ These block design, not just code. Answers go into `Methodology/Calibration.md`.
 
 ## Phase 3 — Dynamic pass
 
-- [ ] **3.1** `bin/offload-scan` skeleton: streaming JSONL reader, attribution
+- [x] **3.1** `bin/offload-scan` skeleton: streaming JSONL reader, attribution
       filter, `(message.id, requestId)` de-dup — delegating token/cost arithmetic
       to `cc-tokens` per decision 0.1. **Do not reimplement the pricing table or
       the streaming-snapshot max.**
-- [ ] **3.2** Invocation reconstruction (contiguous attributed runs per session).
-- [ ] **3.3** Turn classification: mechanical / judgment / retry, with the
+- [x] **3.2** Invocation reconstruction (contiguous attributed runs per session).
+- [x] **3.3** Turn classification: mechanical / judgment / retry, with the
       mechanical tool set and the output-token threshold in the signals catalog.
-- [ ] **3.4** Tool-signature normalization and masking (also satisfies FR-3.5).
-- [ ] **3.5** N-gram mining: recurring sequences ≥3 long in ≥3 invocations.
-- [ ] **3.6** Metrics: MTR, `offload_waste`, read amplification, retry density,
+- [x] **3.4** Tool-signature normalization and masking (also satisfies FR-3.5).
+- [x] **3.5** N-gram mining: recurring sequences ≥3 long in ≥3 invocations.
+- [x] **3.6** Metrics: MTR, `offload_waste`, read amplification, retry density,
       judgment density, fan-out multiplier, composite `offload_value`.
-- [ ] **3.7** Attribution coverage computation (FR-3.4).
-- [ ] **3.8** `tests/scan.test.sh` against **synthetic** fixture transcripts with
+- [x] **3.7** Attribution coverage computation (FR-3.4).
+- [x] **3.8** `tests/scan.test.sh` against **synthetic** fixture transcripts with
       hand-computed expected metrics. Do not test against real transcripts —
       they contain private content and they change.
 - [ ] **3.9** Verify runtime and memory on the real history: one process,

skills/offload-audit/SKILL.md

@@ -316,6 +316,18 @@ previous snapshot → boundary questions, as questions → drift notes, with the
 documentation fix → issues filed or updated, in full `owner/repo#num` form →
 the wiki page path.
 
+Two distinctions the rendered wiki page cannot yet make, and you must: mark any
+boundary question that got there via the FR-4.5 stability gate as **a defect in
+this auditor, not a fact about the target**, and list issues on this plugin's
+own tracker (FR-6.5) separately from those on the target's (FR-6.1).
+
+**Say when you leaned on memory.** If a step 2b result changed how you judged a
+candidate — you weighed a determinism test differently, or reached for a
+remembered overrule case — name it in the report. Nothing mechanical can catch
+this (FR-9.2): the gates are pure functions of the judgments JSON you hand them,
+so the only control on a recalled conclusion quietly becoming evidence is that
+you say it out loud where a human can discount it.
+
 Rank by measured `offload_value` and say that you are doing so. Name skills and
 agents, **never UUIDs or session ids**. Emit **only shapes and counts** — no
 transcript content, file contents, command arguments, or user prose ever enters