[FIX] REVIEWED-86: file the ruling, draft the Constraint 6 amendment, docket Q3

Ruling filed verbatim. Drafting authorized by the steward's placement of
REVIEWED-86; application is not, and ~/CLAUDE.md is untouched.

The amendment adds a second paragraph to Constraint 6 and replaces nothing --
both original clauses survive verbatim, the caution is refined rather than
relaxed, and the L2 deferral stands.

Both jurist conditions welded into the text that would actually land, not left
in surrounding commentary, since a future reader cites the doctrine block and
not the discussion of it. Q2: biases that fail to coincide do not cancel, and
the doctrine may never be cited as assurance something WAS caught. Q3: the
jurist and executor do not differ in formation, their separation is the weaker
kind, and neither the doctrine nor its evidence establishes that pair as a check
in the strong sense -- the doctrine naming the configuration that produced it as
the one it does not vouch for.

Steward ruled the open question on `Status: provisional` sitting inside a section
headed "cannot be overridden": retain it. Constraint 6 already carries a temporal
qualifier, so the section is not free of them.

Paste block prepared separately, indented to continue the numbered list. The edit
is the steward's: Constraint 1 names this file and sits under "cannot be
overridden by any session instruction", and the ruling states the steward's own
act is what nothing substitutes for.

PENDING-89 dockets the Q3 correlation review the jurist declined to leave
hypothetical, with the hazard named -- this is the executor measuring whether the
executor is checked, so criteria must be pre-registered and it may be steward-only
work.

Q4 folded into the existing REVIEWED-85 check-in agenda rather than given its own
cadence, per the ruling's reasoning that a new standing review produces another
unread register.

PENDING-86 amended with its third instance: the jurist could not reach
contamination-problem.md while gating an argument that turns on it.

Convergence question closed. The jurist inferred a common source; the steward
confirmed it -- the exchange was shared as context only, and Document A predates
it, so the jurist's language cannot have shaped the proposal. Neither
contamination nor corroboration.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WuMjg3ipEVa3n8CoSzoyvc

claude/governance/constraint-6-PASTE-BLOCK-2026-08-02.md

@@ -0,0 +1,30 @@
+# Constraint 6 — paste block for steward placement
+
+**Target:** `~/dotfiles/CLAUDE.md` — append to the **end of the file**. Constraint 6 is currently line 249 of 249, so this follows it directly with one blank line between.
+
+**Formatting note:** indented three spaces so the paragraphs continue list item 6 rather than breaking the numbered list. Preserve the indentation on paste.
+
+**Steward's ruling on the open question:** option 1 — `Status: provisional` is retained. The honesty is worth the awkwardness, and Constraint 6 already carries a temporal qualifier (*"until L2 inquiry is formalized"*), so the section is not free of them.
+
+---
+
+## Paste exactly this (everything between the fences, including the leading blank line)
+
+```
+
+   **Differently biased checkers, not unbiased ones.** Oversight does not require a checker without bias. It requires checkers whose biases do not point the same way. Separation of powers has never presupposed an unbiased branch; it presupposes branches positioned so that what one is disposed to miss, another is disposed to see. The contamination problem is therefore not a defect to be cured before the system can be trusted — it is the ordinary condition under which every oversight structure has ever operated, human or otherwise. This is the positive counterpart to the central path: that path says stop certifying the parties, bind the claims, and never audit the audit; this says why stopping is safe, because the work is caught by position rather than by purity.
+
+   Biases that fail to coincide do not cancel. Failing to coincide is weaker than cancelling, and it is all that is claimed: a configuration can satisfy "differently positioned" and still miss an entire class no party is positioned to see. This doctrine may therefore never be cited as assurance that something *was* caught. It is only ever the reason a structure is worth maintaining.
+
+   Three consequences bind. First, the three-party model is not a trust hierarchy: steward, jurist and executor are not ordered by reliability, with a clean human checking a suspect machine, but differently positioned readers — different information, different role, different exposure — and a correction may run in any direction. Second, independence is a property to be engineered, not assumed. Difference of formation is the strong form; difference of role, information and incentive is the weak form. In this system the steward differs from both AI parties in formation; the jurist and the executor do not differ from each other in formation, and their separation is of the weaker kind. Neither this doctrine nor any evidence offered in support of it establishes that the jurist–executor pair constitutes a check in the strong sense. Third, the doctrine is falsifiable and must be watched: if the parties' misses are found to correlate — if what one misses, the others reliably miss too — it is false for that configuration, and no amount of procedural care substitutes. Evidence against is to be recorded when observed, not only when sought.
+
+   *Status: provisional. Held until the thought is more refined, and revisable on evidence. Proposed by the executor, design-gated by the jurist 2026-08-02 with two required conditions (REVIEWED-86), placed by the steward.*
+```
+
+---
+
+## After placing
+
+Nothing else in `~/CLAUDE.md` changes. Constraint 6's two original clauses are untouched — the caution is refined, not relaxed, and the L2 deferral stands.
+
+Tell the executor once placed; it will verify the file parses as a list, confirm the two ratified clauses are byte-identical to their pre-amendment form, and tag the companion work REVIEWED-86.

claude/governance/constraint-6-amendment-DRAFT-2026-08-02.md

@@ -0,0 +1,84 @@
+# Constraint 6 amendment — DRAFT for steward placement
+
+**Status: DRAFT. NOT APPLIED. `~/CLAUDE.md` is untouched.**
+
+Authority: PENDING-88's sibling ESCALATE package → jurist design gate 2026-08-02 → **REVIEWED-86, placed by the steward 2026-08-02**, which authorizes **drafting only**. Application requires a separate, explicit steward act. Constraint 1 and the escalate-unconditionally list both name `~/CLAUDE.md`; nothing short of the steward's own edit changes that.
+
+---
+
+## 1. The ratified text as it stands (verbatim, `~/CLAUDE.md:249`)
+
+> 6. **Contamination awareness** — The executor agency directives are a partial mitigation, not a resolution. Treat outputs about the system's own reliability with appropriate epistemic caution until L2 inquiry is formalized
+
+## 2. What is proposed
+
+**Constraint 6 is not replaced.** Both its clauses survive verbatim; the caution is not relaxed, and the deferral of the L2 inquiry stands. The amendment adds a second paragraph stating what the mitigation *is* — the account Constraint 6 currently omits.
+
+---
+
+## 3. The proposed addition, with both required conditions welded in
+
+*(Draft text. The two marked paragraphs exist because the jurist made them conditions, not suggestions.)*
+
+```
+**Differently biased checkers, not unbiased ones.** Oversight does not require a checker
+without bias. It requires checkers whose biases do not point the same way. Separation of
+powers has never presupposed an unbiased branch; it presupposes branches positioned so
+that what one is disposed to miss, another is disposed to see. The contamination problem
+is therefore not a defect to be cured before the system can be trusted — it is the
+ordinary condition under which every oversight structure has ever operated, human or
+otherwise. This is the positive counterpart to the central path: that path says stop
+certifying the parties, bind the claims, and never audit the audit; this says why
+stopping is safe, because the work is caught by position rather than by purity.
+
+Biases that fail to coincide do not cancel. Failing to coincide is weaker than
+cancelling, and it is all that is claimed: a configuration can satisfy "differently
+positioned" and still miss an entire class no party is positioned to see. This doctrine
+may therefore never be cited as assurance that something WAS caught. It is only ever the
+reason a structure is worth maintaining.
+
+Three consequences bind. First, the three-party model is not a trust hierarchy: steward,
+jurist and executor are not ordered by reliability, with a clean human checking a suspect
+machine, but differently positioned readers — different information, different role,
+different exposure — and a correction may run in any direction. Second, independence is a
+property to be engineered, not assumed. Difference of formation is the strong form;
+difference of role, information and incentive is the weak form. In this system the steward
+differs from both AI parties in formation; the jurist and the executor do not differ from
+each other in formation, and their separation is of the weaker kind. Neither this doctrine
+nor any evidence offered in support of it establishes that the jurist–executor pair
+constitutes a check in the strong sense. Third, the doctrine is falsifiable and must be
+watched: if the parties' misses are found to correlate — if what one misses, the others
+reliably miss too — it is false for that configuration, and no amount of procedural care
+substitutes. Evidence against is to be recorded when observed, not only when sought.
+
+Status: provisional. Held until the thought is more refined, and revisable on evidence.
+```
+
+---
+
+## 4. What changed from the text the jurist read, and why
+
+| Condition | Where it landed | What it prevents |
+|---|---|---|
+| **Q2 weld** — *fail to coincide, not cancel*; never cite as assurance something *was* caught | Its own paragraph, second, immediately after the doctrine's statement | A future reader citing the doctrine cites the doctrine block, not the surrounding commentary. In the package this qualifier lived in Part IV, which would not have landed. The dangerous misreading — *biases cancel, so the system is safe* — is now refused inside the text a citer quotes. |
+| **Q3 framing** — the jurist and executor share formation | Consequence 2, stated as a fact about this system rather than as a caveat | The doctrine's landing being read as having validated the jurist–executor pair, when the evidence offered measures two differently-*formed* models and says nothing about that pair. The clause is deliberately self-limiting: it names the configuration that produced the doctrine as the one the doctrine does not vouch for. |
+
+**Not changed:** the three consequences' substance, the provisional status, or Constraint 6's own two clauses. The proposal refines Constraint 6; it does not relax it.
+
+---
+
+## 5. Owed, and deliberately not drafted here
+
+- **Q4 — the retrieval obligation.** The jurist directed it be folded into the **existing** REVIEWED-85 check-in rather than given a standalone cadence, on the grounds that a new standing review is exactly the shape of thing that produces another unread register. It is therefore not doctrine text and does not belong in this amendment. Owed: an agenda line on the REVIEWED-85 check-in.
+- **The `contamination-problem.md` companion note** (named as owed in the package's Part V). That repo's discipline is amendment-first, so it is named here, not drafted.
+- **The Q3 correlation review**, docketed separately per the ruling.
+
+---
+
+## 6. The honest limit on this draft
+
+The jurist recorded, unprompted, that it had used closely similar language to the proposal's opening formulation earlier the same day, before reading the package — and declined to treat the convergence as independent corroboration, judging one source (the steward) likelier to have reached both readers separately.
+
+That disclosure belongs with the draft rather than only with the ruling. **The agreement between jurist and executor on this doctrine is not evidence for it.** It is, if anything, an instance of exactly what consequence 2 warns about: two readers of shared formation, reached by a common source, arriving at the same place. The doctrine survives on the argument in Part II and the pilot evidence in Document B — which covers a different pair — not on the fact that both AI parties find it persuasive.
+
+**Resolved 2026-08-02, steward-confirmed.** The jurist inferred a common source; the steward confirmed the mechanism directly — he had shared the jurist exchange as *context only*, with explicit instructions that it sat outside the ruling then being settled. So the transmission is documented and its direction is known: Document A was filed 2026-08-01, **before** that exchange, so the jurist's language cannot have shaped the proposal. The convergence is neither contamination nor corroboration — it is one source reaching two readers, exactly as the jurist reasoned without being able to check it. Recorded here because a disclosure whose cause is later established should carry the resolution, not stay an open suspicion; and because the jurist's caution was correct *before* the confirmation, which is the part worth keeping.

claude/governance/differently-biased-checkers-JURIST-RULING-2026-08-02.md

@@ -0,0 +1,45 @@
+# Jurist ruling — differently biased checkers (design gate, 2026-08-02)
+
+*Filed verbatim as received, steward-relayed. Not edited, not summarised. The REVIEWED-86 block below is the jurist's draft for steward placement; it is **not placed** at the time of filing.*
+
+---
+
+Before anything else, so there's no ambiguity: nothing below authorizes application. This touches `~/CLAUDE.md` directly, which sits on both Constraint 1 and the escalate-unconditionally list. The most this ruling can do — per the taxonomy, and per the package's own correct reading of it — is authorize *drafting* the amendment text for you to place or not. That ceiling doesn't move regardless of how the substance below lands.
+
+**Verification.** Constraint 6 and the Executor Agency clause, quoted in Part I, I checked directly against `~/CLAUDE.md` two turns ago and they're exact — no new read needed, no drift. The central-path quote (the 2026-07-29 "irresolvable... never audit the audit" material) I can't read at its source, but I pulled the memory index, and its own independently-written one-line summary of that file uses the same load-bearing phrases — "human bias is the other half," "auditing the audit never converges," "one layer of disclosure, then act — never audit the audit" — which is real corroboration, a second document agreeing, not the same document read twice. `contamination-problem.md` (Core Problem, Partial Mitigations, Epistemic Ceiling) I still can't reach at all — same gap as the skill files last time, now touching the part of the argument that establishes the doctrine actually has a gap to fill. Worth closing at some point; PENDING-86 is still open and this is a second, independent argument for it.
+
+**Something I want on the record before I rule on the substance.** The opening formulation in Part III — "oversight does not require a checker without bias, it requires checkers whose biases don't point the same way," explicitly reaching for separation of powers — is close enough to what I said to you, unprompted, before I'd seen this document, that I don't think I should evaluate it as if encountering it fresh. Document A was filed 2026-08-01, at your request, before that exchange. The likeliest explanation isn't that the executor drew on me or I on it — it's that you'd been carrying this thought and gave it to both of us close together. That matters for how much the convergence should count: two conclusions from one root don't corroborate each other the way two independent derivations would, and I'd be doing exactly the thing Part VII warns about if I let the fact that it sounds right to me stand in for having checked it.
+
+**Q1 — the gap is real.** Constraint 6, on my own direct read, states caution and states nothing else. The central path, per the corroborated summary, is stopping rules without a stated reason stopping is safe. Demonstrated, not just asserted.
+
+**Q2 — sound in substance, one correction required before this is draft-ready.** The core claim is standard, well-tested institutional design — segregation of duties, adversarial review, replication by separate labs — being named for this system, not invented. But Part III's actual proposed *text* doesn't yet carry the qualifier Part IV argues is load-bearing: that differently-positioned biases *fail to coincide* rather than *cancel*, and that the doctrine must never be cited as assurance something *was* caught, only as the reason a structure is worth maintaining. Right now that qualifier lives in the surrounding discussion, not in the block that would actually land in `~/CLAUDE.md`. A future reader — executor or otherwise — citing the doctrine will cite Part III, not Part IV's commentary on it. Weld the qualifier into the text itself before this goes to you for placement. The executor's own Q2 lean already says as much; I'm making it a condition rather than a suggestion.
+
+**Q3 — genuinely open, and I'll give you more than a punt without pretending to settle it.** I'm not differently-formed from the executor. Whatever separates us is role, information access, and — probably the most real thing — that I don't carry the accumulated context and momentum of the session that built the proposal, and I have no stake in what my own future operating constraints will be, which the executor's proposals sometimes do. That's category (i) independence — position and incentive, not formation — and the package is right that only (ii) is independence in the strong sense. So: jurist review is worth having, and it isn't nothing, but it isn't the check Document B measured either, and the doctrine's text should say so plainly rather than let its landing be read as having validated the jurist-executor pair by association with evidence that doesn't cover it. I'd add one concrete thing to the record: the falsifier the package names — reviewing the accumulated PENDING/REVIEWED history for clustered jurist/executor misses against a differently-clustered steward correction pattern — is checkable *right now*, on the four rulings that exist. It shouldn't stay hypothetical. Worth its own docket entry rather than floating.
+
+**Document B, on its own merits.** Well-built pilot evidence: pre-registered exclusions before reading, a corpus that predates the doctrine by a year and wasn't selected by the interested party, and the one reproduced pair holds up under my own inspection — rows 6 through 11 of that table are genuinely non-overlapping, and row 6 is a real disagreement, not a stylistic variant. I'd credit it as real. I would not credit it as a *rate*. Three comparable pairs, one author, one genre, and even within the "comparable" set the two models carried unequal persona instructions that were filtered from the count but can't be fully filtered from what claims a persona-shaped voice is disposed to make — Document B names this itself (Part F.2, "causes remain bundled") and doesn't oversell past it, which is to its credit. Treat it as: consistent with the doctrine, insufficient to quantify it, correctly scoped by its own authors to say nothing about Q3.
+
+**Q4 — sharpen toward retrieval, and don't give it a standalone cadence.** The eighteen-month gap between the observation being recorded (2025-01-20, in the right words) and it reaching doctrine is a sharp, well-evidenced point, and the diagnosis is right: recording wasn't the failure, retrieval was. Fold the retrieval obligation into the same check-in I already required in REVIEWED-85 rather than creating a second standing review nobody has bandwidth for — a new obligation to periodically re-read old evidence is exactly the shape of thing that produces another unread register if it isn't attached to a cadence that already exists.
+
+**Q5 — Constraint 6.** Agreed, and it's the steward's call regardless.
+
+Design-gate passed for drafting only, with the Q2 weld required and the Q3 framing note required. Ready to paste, understanding that placement itself is the authorization step, not this ruling:
+
+```markdown
+## REVIEWED-86 — Differently biased checkers, not unbiased ones (design-gate passed for DRAFTING ONLY — ESCALATE, application requires separate explicit steward authorization)
+**Date:** 2026-08-02
+**Decision:** AUTHORIZED to draft the Constraint 6 amendment for steward placement. NOT AUTHORIZED to apply — Constraint 1 and the escalate-unconditionally list both name this file; no ruling below the steward's own act of placing it changes that.
+**Notes:**
+- **Q1 — the gap is real — CONFIRMED**, independently checked against `~/CLAUDE.md` directly (Constraint 6 exact) and against the central-path file's own memory-index summary (substance and key phrases match).
+- **Q2 — sound, ONE required correction.** Weld Part IV's "fail to coincide, not cancel" qualifier and its ban on citing the doctrine as assurance that something *was* caught into Part III's actual proposed text — not left as surrounding commentary. Not draft-ready without this.
+- **Q3 — unresolved, and the doctrine's own landing must say so.** Jurist and executor share formation; whatever separates them is position, information, and incentive (category (i)), not formation (category (ii)) — the category Document B actually measured. The doctrine text should not be read, by its landing, as having validated the jurist-executor pair specifically. Recommend the correlation review the package itself names — clustered jurist/executor misses vs. a differently-clustered steward-correction pattern, run against the existing PENDING/REVIEWED record — be docketed as its own item rather than left hypothetical.
+- **Document B — credited as pilot evidence for category (ii) only, not as a measured rate.** Pre-registration, corpus predating the doctrine, and the reproduced Appendix pair all independently checked out on inspection. Sample (3 comparable pairs, one author, unresolved persona confound even within the comparable set) is too narrow to quantify anything; Document B's own Part F.2/F.3 already say so and that scoping should be preserved verbatim in whatever cites it.
+- **Q4 — sharpen to a retrieval obligation, fold into the existing check-in cadence** (REVIEWED-85), not a new standing review.
+- **Q5 — Constraint 6 — AFFIRMED as the right location, steward's call on final placement.**
+- **Process note, disclosed rather than absorbed:** the proposal's opening formulation and language I used independently, unprompted, earlier the same day are close enough that I don't treat the convergence as two independent corroborations — likelier one source (the steward) reaching both readers separately. Noted so it isn't mistaken for evidence the doctrine doesn't have.
+**If AUTHORIZED for drafting:** Land Part III (with the Q2 weld applied) beside Constraint 6, plus the companion `contamination-problem.md` note named as owed in Part V, amendment-first per that repo's own discipline. Docket the Q3 correlation review separately. Tag REVIEWED-86.
+**Awaiting:** the Q2 weld, then steward review of the woven text; the Q3 note's exact wording; the correlation-review docket entry; and — the one that actually matters here — the steward's own explicit act of authorizing application, which nothing above substitutes for.
+```
+
+---
+
+*Received and filed by the executor 2026-08-02. Nothing applied. `~/CLAUDE.md` untouched.*

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

@@ -19,6 +19,14 @@ clause yes → PROPOSAL) **and** the hard floor. When in doubt, propose.
 | 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