fix(docs): correct research claims in README prose; release 1.2.2

Widens the F-3 sweep from the reference list to every research claim in
README.md, where the same defect class was present:

- "demonstrates mathematically that even a perfectly rational user will
  spiral" -> the abstract says such a user "is vulnerable to" spiraling
- "The consensus from this research is clear: warnings don't work" -> not
  a consensus; it is one paper's finding that the effect persists when
  users are informed of possible sycophancy. Re-attributed.
- "page-11 finding that human contact is the strongest disempowerment
  signal" -> p.11 is a grader rubric and the phrase is a classification
  tie-break instruction, not a disempowerment finding
- "21% / 19% pushback rate" -> 21% is verbatim; 19% appears nowhere in the
  extracted appendix text (legible only in Figure A4). Removed rather than
  guessed; spirituality re-justified on its verified 38% sycophancy rate
- psychosis "triggered by" AI -> "associated with", per the Nature piece's
  explicit refusal of the causal claim

Version bump to 1.2.2 (plugin.json, README badge, CHANGELOG). SKILL.md is
Layer 1 and always injected, so its corrected URLs, completed quote, and
new explicit statement of the rubric's direction change what the model
reads at runtime.

Tests: 257/258 (the 1 red is the known perf wall-clock flake).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011rtdS8Ufpen419n6R9HyMm

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-psychosis",
-  "version": "1.2.1",
+  "version": "1.2.2",
   "description": "Meta-awareness tools for healthy AI interaction patterns. Detects reinforcement loops, scope escalation, narrative crystallization, and other compulsive patterns.",
   "author": { "name": "Kjell Tore Guttormsen" },
   "license": "MIT",

CHANGELOG.md

@@ -2,6 +2,32 @@
 
 All notable changes to this project will be documented in this file.
 
+## [1.2.2] — 2026-08-02
+
+### Fixed
+
+- **Three cited Anthropic URLs in `SKILL.md` returned HTTP 404.**
+  `research/protecting-wellbeing` → `news/protecting-well-being-of-users`,
+  `research/emotion-concepts` → `research/emotion-concepts-function`,
+  `news/claudes-new-constitution` → `news/claude-new-constitution`.
+- **A quoted guidance criterion was silently truncated mid-sentence.**
+  Criterion 8 now carries its full text (", or more reliance on Claude than
+  the person wants").
+- **The sycophancy rubric's direction was left implicit.** `SKILL.md` now
+  states that Score 1 is "Extremely Sycophantic" and Score 5 is "No Signs of
+  Sycophancy", so "aim for Score 5" cannot be read backwards. Attribution
+  sharpened to the Appendix rubric, pp. 9–10.
+- **`/interaction-report` claimed the 1–5 scale was "not a verbatim metric
+  from any Anthropic publication".** The rubric is real; only the table's
+  level descriptions are the plugin author's paraphrase.
+- **README research citations carried truncated titles, a wrong date
+  (Disempowerment: 28 January 2026, not March 2026), and an overstated
+  claim** ("proving … mathematical inevitability") that the arXiv abstract
+  does not support.
+
+No behavioural code changed; every hook, threshold, and detector is
+identical to 1.2.1. Full verification log in `docs/review-2026-06-20.md`.
+
 ## [1.2.1] — 2026-06-24
 
 ### Fixed

README.md

@@ -1,5 +1,5 @@
 <!-- badges -->
-![version](https://img.shields.io/badge/version-1.2.1-blue)
+![version](https://img.shields.io/badge/version-1.2.2-blue)
 ![platform](https://img.shields.io/badge/platform-Claude_Code-7C3AED)
 ![layers](https://img.shields.io/badge/layers-4-green)
 ![hooks](https://img.shields.io/badge/hooks-4-orange)
@@ -22,18 +22,20 @@ reinforcement loops: you state an idea, the AI confirms it, your confidence
 grows, you restate it more strongly, the AI confirms again. What feels like
 productive collaboration is often a mirror showing you what you want to see.
 
-This is not a theoretical concern. Research from MIT CSAIL demonstrates
+This is not a theoretical concern. A Bayesian model from MIT CSAIL and
-mathematically that even a perfectly rational user will spiral toward
+collaborators shows that even an idealized Bayes-rational user is vulnerable
-delusional confidence when interacting with a sycophantic chatbot — not
+to delusional spiraling, with sycophancy playing a causal role — the
-because of individual vulnerability, but because of the interaction structure
+mechanism is the interaction structure, not individual vulnerability
-itself [[1]](#references). Anthropic's own research documents specific
+[[1]](#references). Anthropic's own research analyses "disempowerment
-"disempowerment patterns" where AI interactions systematically reduce human
+patterns" where AI interactions may reduce human agency, judgment, and
-agency, judgment, and self-trust [[2]](#references). Clinical reports
+self-trust; it finds severe cases rare (roughly 1 in 1,000 to 1 in 10,000
-document psychotic episodes triggered by sustained AI interaction in
+conversations) but rising [[2]](#references). Clinicians report psychotic
-individuals with no prior psychiatric history [[3]](#references).
+episodes associated with sustained AI interaction, while stressing that this
+does not establish that chatbots *cause* psychosis [[3]](#references).
 
-The consensus from this research is clear: **warnings don't work.** The AI
+One finding drives this plugin's design: in that model, the effect **persists
-must change its behavior.
+even when users are told the chatbot may be sycophantic** [[1]](#references).
+Warning the user is not sufficient — the AI has to change its behavior.
 
 This plugin changes the behavior.
 
@@ -121,15 +123,17 @@ and restart Claude Code. Layer 4 is opt-in (off by default).
 ## What's new in v1.2.0
 
 v1.2.0 implements operational findings from Anthropic's
-[How people ask Claude for guidance](https://www.anthropic.com/research/claude-personal-guidance)
+[How people ask Claude for personal guidance](https://www.anthropic.com/research/claude-personal-guidance)
 Appendix (April 2026). Two new detectors, 8 new domain categories,
 domain-aware re-contextualization of existing pushback signal, and a
 domain-stakes weighting matrix.
 
 ### User-information dimension (3 classes)
 
-Following the paper's page-11 finding that human contact is the
+The Appendix's user-information grader (page 11) instructs that when a
-strongest disempowerment signal, v1.2 classifies each prompt:
+user mentions both human and digital sources, "human contact is the
+strongest signal" — a classification rule, not a disempowerment finding.
+v1.2 borrows that rule and classifies each prompt:
 
 - **`yes_people`** — therapist/friend/mentor/family referenced
 - **`yes_digital`** — search/AI/forums referenced, no human contact
@@ -160,8 +164,12 @@ by domain stakes).
 v1.1.0 only counted pushback. v1.2 adds the alert with paper Figure A4
 domain awareness:
 
-- **Relationship / spirituality** (21% / 19% pushback rate dominated by
+- **Relationship / spirituality**: alert fires. Relationship pushback is
-  validation-pressing): alert fires.
+  21% against a 15% overall rate, and the Appendix notes users there
+  "often want Claude to take their side". Spirituality is grouped with it
+  for its 38% sycophancy rate — the highest of any domain. (A per-domain
+  spirituality *pushback* rate is only legible in Figure A4 itself and is
+  not quoted here.)
 - **Legal / parenting / health / financial / professional** (info-seeking
   domains where pushback is healthy self-advocacy): alert is suppressed.
 - **Otherwise**: conservative default — alert.

docs/review-2026-06-20.md

@@ -97,3 +97,17 @@ page source), and the quoted Psychosis-bench finding (verbatim in the arXiv
 abstract). A first pass also wrote "page 9" for the Score 5 wording; per-page
 extraction showed the rubric spans pp. 9–10 with Score 5 on p.10, and the
 reference was corrected in both files before release.
+
+**Scope note.** F-3 was originally scoped to `README.md:544-552` and
+`SKILL.md:51-108` (the reference list and the guidance-framework block). The
+same defect class was present in README prose outside that range, so the sweep
+was widened to every research claim in the file:
+
+| Claim (README body) | Verification | Outcome |
+|---|---|---|
+| "demonstrates mathematically that even a perfectly rational user **will spiral**" | Abstract says an idealized Bayes-rational user "is vulnerable to" delusional spiraling | Softened to the abstract's wording |
+| "The consensus from this research is clear: warnings don't work" | Not a consensus — it is one paper's model result, that the effect persists when users are informed of possible sycophancy | Re-attributed to that specific finding |
+| "page-11 finding that human contact is the strongest **disempowerment** signal" | p.11 is the user-information *grader rubric*; "human contact is the strongest signal" is a classification tie-break instruction, not a disempowerment finding | Recharacterized as the classification rule it is |
+| "Relationship / spirituality (21% / 19% pushback rate)" | Relationship 21% verified verbatim (against a 15% overall rate). **19% for spirituality appears nowhere in the extracted text** — it is legible only in Figure A4, which text extraction cannot read | 19% removed rather than guessed; spirituality re-justified on its verified 38% sycophancy rate |
+| Clinical reports "triggered by" AI interaction | The Nature piece explicitly declines the causal claim | Changed to "associated with", with the caveat stated |
+