diff --git a/skills/audit-delta/SKILL.md b/skills/audit-delta/SKILL.md
index 0b2b483..87fabe0 100644
--- a/skills/audit-delta/SKILL.md
+++ b/skills/audit-delta/SKILL.md
@@ -22,6 +22,13 @@ allowed-tools:
 
 # /audit-delta — Incremental multi-axis code audit
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 Audit only what changed since the last run, on the axes the user picks.
 Per axis: **audit → approval gate → fix → re-verify → marker update**,
 strictly in that order, one axis fully closed before the next starts.
diff --git a/skills/bugfix/SKILL.md b/skills/bugfix/SKILL.md
index 21744d2..069d264 100644
--- a/skills/bugfix/SKILL.md
+++ b/skills/bugfix/SKILL.md
@@ -20,6 +20,10 @@ allowed-tools:
   - Agent
 ---
 
+MODEL GATE (blocking): run `$HOME/.claude/lib/model-gate.md` BEFORE loading
+the agent below. Verdict `small` → STOP — print the gate's remedy, end the
+turn, do not load the agent.
+
 Load and follow strictly:
 - $HOME/.claude/agents/bugfixer.md
 
diff --git a/skills/code-clean/SKILL.md b/skills/code-clean/SKILL.md
index 6175c1a..3aa8778 100644
--- a/skills/code-clean/SKILL.md
+++ b/skills/code-clean/SKILL.md
@@ -20,6 +20,10 @@ allowed-tools:
   - AskUserQuestion
 ---
 
+MODEL GATE (blocking): run `$HOME/.claude/lib/model-gate.md` BEFORE loading
+the agent below. Verdict `small` → STOP — print the gate's remedy, end the
+turn, do not load the agent.
+
 Load and follow strictly:
 - $HOME/.claude/agents/code-cleaner.md
 
diff --git a/skills/feat/SKILL.md b/skills/feat/SKILL.md
index 9e814d8..3839c80 100644
--- a/skills/feat/SKILL.md
+++ b/skills/feat/SKILL.md
@@ -20,6 +20,10 @@ allowed-tools:
   - Agent
 ---
 
+MODEL GATE (blocking): run `$HOME/.claude/lib/model-gate.md` BEFORE loading
+the agent below. Verdict `small` → STOP — print the gate's remedy, end the
+turn, do not load the agent.
+
 Load and follow strictly:
 - $HOME/.claude/agents/feater.md
 
diff --git a/skills/geo/SKILL.md b/skills/geo/SKILL.md
index 50773f6..1abc7bc 100644
--- a/skills/geo/SKILL.md
+++ b/skills/geo/SKILL.md
@@ -22,6 +22,13 @@ allowed-tools:
 
 # /geo — GEO (AI-search) audit + fix dispatcher
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 Dispatches the `geo-analyzer` subagent (audit + fix bundle), then applies
 the bundle from THIS main loop at **L1** — same shape as `/web-validate`
 and `/seo`. The analyzer never edits files: it emits a `## FIX BUNDLE`
diff --git a/skills/harden/SKILL.md b/skills/harden/SKILL.md
index b94706d..82da28c 100644
--- a/skills/harden/SKILL.md
+++ b/skills/harden/SKILL.md
@@ -22,6 +22,13 @@ allowed-tools:
 
 # /harden — web hardening audit
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 This skill orchestrates a narrow-scope hardening audit: TLS + security
 headers + redirects + canonical + custom 404 + server configs. It
 reuses the `seo-analyzer` agent with a **strict scope filter** to avoid
diff --git a/skills/init-project/SKILL.md b/skills/init-project/SKILL.md
index a9b39d7..617db97 100644
--- a/skills/init-project/SKILL.md
+++ b/skills/init-project/SKILL.md
@@ -7,6 +7,13 @@ allowed-tools: Read, Write, Edit, Bash, Grep, Glob
 
 # ORCHESTRATOR: INIT PROJECT
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 ## REQUEST
 $ARGUMENTS
 
diff --git a/skills/onboard/SKILL.md b/skills/onboard/SKILL.md
index 3be3c93..bf2caa2 100644
--- a/skills/onboard/SKILL.md
+++ b/skills/onboard/SKILL.md
@@ -7,6 +7,13 @@ allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Agent, Skill
 
 # ORCHESTRATOR: ONBOARD
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 ## REQUEST
 $ARGUMENTS
 
diff --git a/skills/seo/SKILL.md b/skills/seo/SKILL.md
index 00a3421..6a5078d 100644
--- a/skills/seo/SKILL.md
+++ b/skills/seo/SKILL.md
@@ -23,6 +23,13 @@ allowed-tools:
 
 # /seo — parallel SEO + GEO dispatcher
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 This skill orchestrates TWO specialist agents running in parallel, then
 merges their output into a single `.claude/audits/SEO.md` report. It is the main
 entry point for any SEO/GEO work on a web project.
diff --git a/skills/ship-feature/SKILL.md b/skills/ship-feature/SKILL.md
index ec3490e..33ecaaa 100644
--- a/skills/ship-feature/SKILL.md
+++ b/skills/ship-feature/SKILL.md
@@ -7,6 +7,13 @@ allowed-tools: Read, Write, Edit, Bash, Grep, Glob
 
 # ORCHESTRATOR: SHIP FEATURE
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 ## REQUEST
 $ARGUMENTS
 
diff --git a/skills/tour/SKILL.md b/skills/tour/SKILL.md
index ad3b357..1b9870f 100644
--- a/skills/tour/SKILL.md
+++ b/skills/tour/SKILL.md
@@ -23,6 +23,13 @@ allowed-tools:
 
 # /tour — grouped multi-axis sweep (clean + security + reconcile + doc)
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 One pipeline per project: **security → clean → re-verify → reconcile →
 doc → convergence re-audit**, looping until a full pass applies zero new
 fixes. Auto mode by design: fixes are committed on a dedicated
diff --git a/skills/web-validate/SKILL.md b/skills/web-validate/SKILL.md
index 193dc7a..03dc31b 100644
--- a/skills/web-validate/SKILL.md
+++ b/skills/web-validate/SKILL.md
@@ -21,6 +21,13 @@ allowed-tools:
 
 # /web-validate — web standards audit (W3C + WCAG)
 
+## MODEL GATE (blocking — run before any other step)
+
+Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
+judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
+gate prints the remedy; end the turn — no later step, no dispatch. Nominal
+(big) path is silent.
+
 This skill orchestrates a narrow-scope standards audit :
 
 - **W3C HTML validity** — validator.nu API (FULL) or `html-validate` /