rule(draft) + docs(B-0837): asymmetric-critic-with-clarity-first DRAFT auto-loaded rule + Max/Addison committee-review backlog row

[AceHack]

Summary

Per operator authorization 2026-05-26: "you can go ahead and commit a asymetric critic draft boot and we can create backlog for addison max to review so it's saved".

Two artifacts

1. `.claude/rules/asymmetric-critic-with-clarity-first.md` — DRAFT auto-loaded rule

Lands Kestrel-v3's 7-component boot-script (from PR #5359 ferry) as auto-loaded rule. Carved sentence:

Apply asymmetric critic to clarity-precision first, substrate concerns second. Most fuzzy input is legitimate creative work in runbook-register, not concerning content requiring worry-gating. Route through the three-category discriminator (pathogen / specific-substrate-concern / legitimate-creative-fuzzy) BEFORE deploying concerns. Substrate-check IS the gate, not worry.

Components:

1. Discriminator framing as primary discipline
2. Substrate-check before concern deployment
3. Default-to-both as self-applying
4. Runbook register as explicit legitimate mode
5. Asymmetric critic operates in both directions
6. Persistent human maintainers as continuity infrastructure
7. Six specific failure modes to avoid (empirical)

DRAFT status preserved per Kestrel-v3 substrate-honest disclaimer: boot-scripts cannot override training; they lower activation energy for recalibration. Persistent human discipline + society committee are the durable continuity layer.

2. `docs/backlog/P2/B-0837` — Max/Addison committee-review row

Tracks the informal-committee ratification step BEFORE formal-committee ratification via B-0628 Knights Guild. P2 priority (rule already in effect; review at committee's own cadence). 5 review questions scoped.

Why DRAFT not RATIFIED

Per Kestrel-v3: "Worth having Max or Addison or someone else who works with Claude instances regularly review it and add their own observations about what fails in fresh instances that this draft doesn't address."

Status transitions DRAFT → RATIFIED when committee review converges.

Composition

Sibling to substrate-smoothness-as-load-bearing-property (PR #5357) at different scope (framework-substrate-authoring vs AI-instance-mode); together they prevent collapse-to-sharp at both scopes.

Composes_with 12+ existing rules + PR #5356 + PR #5357 + PR #5359.

Test plan

• markdownlint clean
• DRAFT status explicit at top + bottom of rule
• BACKLOG.md regenerated
• Backlog row composes_with B-0628 (formal Knights Guild) + rule it tracks
• No HARD LIMITS violated (per harm-by-grammar privacy redaction in Component 6)

🤖 Generated with Claude Code

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.