diff --git a/plugins/config-audit/commands/tokens.md b/plugins/config-audit/commands/tokens.md
index 92e1342..54df519 100644
--- a/plugins/config-audit/commands/tokens.md
+++ b/plugins/config-audit/commands/tokens.md
@@ -29,6 +29,7 @@ Split `$ARGUMENTS` into a path and flags. Path is the first non-flag argument. D
 
 - `--global` — also include the user-level `~/.claude/` cascade
 - `--json` — emit raw JSON instead of rendered tables (power-user mode)
+- `--with-telemetry-recipe` — include `telemetry_recipe_path` in the JSON output, pointing to `knowledge/cache-telemetry-recipe.md`. Use this when you want to verify a structural fix actually improved cache hit rate (manual jq recipe, opt-in)
 
 ### Step 2: Run the CLI silently
 
@@ -105,6 +106,7 @@ rm -f "$TMPFILE"
 - **`/config-audit posture`** — overall health scorecard (Token Efficiency is the 8th area)
 - **`/config-audit fix`** — auto-fix deterministic issues (where applicable)
 - See `knowledge/opus-4.7-patterns.md` for the full pattern catalogue (CA-TOK-001 … 003)
+- **Verify cache hit rate after a fix:** rerun with `--with-telemetry-recipe` to surface the path to `knowledge/cache-telemetry-recipe.md` — a copy-paste `jq` recipe that reads cache hit rate from your session transcripts. Opt-in. The TOK scanner is structural; this recipe is the runtime escape hatch.
 ```
 
 ## Scope and limits
diff --git a/plugins/config-audit/knowledge/cache-telemetry-recipe.md b/plugins/config-audit/knowledge/cache-telemetry-recipe.md
new file mode 100644
index 0000000..a9d767f
--- /dev/null
+++ b/plugins/config-audit/knowledge/cache-telemetry-recipe.md
@@ -0,0 +1,114 @@
+# Cache Telemetry Recipe
+
+> Manual recipe for verifying prompt-cache hit rate from Claude Code session
+> transcripts. Opt-in. The TOK scanner is structural — it estimates token cost
+> from disk content but never reads runtime telemetry. This recipe closes that
+> gap when you need to confirm a structural fix actually improved cache reuse.
+>
+> Last verified 2026-05-01 against Claude Code transcript schema.
+
+## Synopsis
+
+Each turn in a Claude Code session is logged as a JSONL entry under
+`~/.claude/projects/<slug>/`. Anthropic's API response includes
+`cache_read_input_tokens` and `cache_creation_input_tokens` per turn, and Claude
+Code persists these in the transcript. Summing them gives a per-session cache
+hit rate without needing the API key or any external service.
+
+A high cache-read share (≥ 70%) means structural fixes are working. A low share
+(< 30%) means something at the top of the prompt is changing per turn —
+typically a CLAUDE.md timestamp, a rolling counter, or a deep `@import`
+boundary. Cross-reference with `/config-audit tokens` to find the culprit.
+
+## Recipe
+
+### 1. Locate the transcript
+
+```bash
+# Newest transcript for the current project
+PROJECT_SLUG=$(pwd | sed 's|/|-|g')
+TRANSCRIPT=$(ls -t ~/.claude/projects/${PROJECT_SLUG}/*.jsonl 2>/dev/null | head -1)
+echo "Transcript: $TRANSCRIPT"
+```
+
+If no transcript exists, run a few turns in Claude Code first.
+
+### 2. Sum cache tokens per turn
+
+```bash
+# Requires jq. Sums cache_read and cache_creation across all turns.
+jq -s '
+  [.[] | select(.type == "assistant" and .message.usage)]
+  | {
+      turns: length,
+      cache_read: ([.[] | .message.usage.cache_read_input_tokens // 0] | add),
+      cache_creation: ([.[] | .message.usage.cache_creation_input_tokens // 0] | add),
+      input_no_cache: ([.[] | .message.usage.input_tokens // 0] | add)
+    }
+  | . + {
+      total_input: (.cache_read + .cache_creation + .input_no_cache),
+      hit_rate: (if (.cache_read + .cache_creation + .input_no_cache) > 0
+                 then (.cache_read / (.cache_read + .cache_creation + .input_no_cache))
+                 else 0 end)
+    }
+' "$TRANSCRIPT"
+```
+
+Example output:
+
+```json
+{
+  "turns": 18,
+  "cache_read": 458320,
+  "cache_creation": 12440,
+  "input_no_cache": 5120,
+  "total_input": 475880,
+  "hit_rate": 0.9631
+}
+```
+
+### 3. Interpret
+
+| Hit rate | Reading |
+|----------|---------|
+| ≥ 0.85 | Cache structure healthy. Structural fixes are paying off. |
+| 0.50–0.85 | Cache works but something near the prefix is shifting. Inspect first 30 lines of CLAUDE.md and any `@import`-ed file. |
+| 0.20–0.50 | Cache is being broken most turns. Likely a volatile CLAUDE.md top-of-file (timestamp, session id, rolling activity log) or a `defaultMode` flip. Run `/config-audit tokens` to locate. |
+| < 0.20 | Cache is essentially disabled. Either the prefix is rewritten every turn, or the session is so short caching never warmed up. |
+
+### 4. Per-turn breakdown (for spotting the regression turn)
+
+```bash
+jq -c '
+  select(.type == "assistant" and .message.usage)
+  | {
+      ts: .timestamp,
+      cache_read: (.message.usage.cache_read_input_tokens // 0),
+      cache_creation: (.message.usage.cache_creation_input_tokens // 0)
+    }
+' "$TRANSCRIPT" | head -20
+```
+
+Look for turns where `cache_read` drops sharply and `cache_creation` spikes —
+that's a cache invalidation event. Whatever changed in CLAUDE.md, settings.json,
+or the active `@import` chain at that moment is the cause.
+
+## Why this is a recipe, not a scanner
+
+Parsing transcripts as a core scanner feature was rejected during v5 planning:
+
+1. Transcripts are user-private session data. Bundling parsing logic implies
+   the plugin reads transcripts by default, which crosses a privacy boundary.
+2. Transcript schema is undocumented and may change without notice. A scanner
+   would silently drift.
+3. The recipe form (jq one-liner) is auditable in 30 seconds. A bundled parser
+   is not.
+
+Surface area stays read-only and structural. This file is the escape hatch
+when structural signal alone isn't enough.
+
+## See also
+
+- `knowledge/opus-4.7-patterns.md` — structural patterns the TOK scanner detects (CA-TOK-001..005)
+- `knowledge/configuration-best-practices.md` — CLAUDE.md cache-stability guidance
+- `/config-audit tokens --with-telemetry-recipe` — surfaces a pointer to this file in JSON output
diff --git a/plugins/config-audit/scanners/token-hotspots-cli.mjs b/plugins/config-audit/scanners/token-hotspots-cli.mjs
index 4b75106..31028ce 100755
--- a/plugins/config-audit/scanners/token-hotspots-cli.mjs
+++ b/plugins/config-audit/scanners/token-hotspots-cli.mjs
@@ -6,27 +6,34 @@
  *
  * Usage:
  *   node token-hotspots-cli.mjs [path] [--json] [--output-file <path>] [--global]
+ *                               [--with-telemetry-recipe]
  *
  * Exit codes: 0=ok, 3=unrecoverable error.
  * Zero external dependencies.
  */
 
-import { resolve } from 'node:path';
+import { resolve, dirname, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
 import { writeFile, stat } from 'node:fs/promises';
 import { discoverConfigFiles } from './lib/file-discovery.mjs';
 import { resetCounter } from './lib/output.mjs';
 import { scan } from './token-hotspots.mjs';
 
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const TELEMETRY_RECIPE_PATH = resolve(__dirname, '..', 'knowledge', 'cache-telemetry-recipe.md');
+
 async function main() {
   const args = process.argv.slice(2);
   let targetPath = '.';
   let outputFile = null;
   let jsonMode = false;
   let includeGlobal = false;
+  let withTelemetryRecipe = false;
 
   for (let i = 0; i < args.length; i++) {
     if (args[i] === '--json') jsonMode = true;
     else if (args[i] === '--global') includeGlobal = true;
+    else if (args[i] === '--with-telemetry-recipe') withTelemetryRecipe = true;
     else if (args[i] === '--output-file' && args[i + 1]) outputFile = args[++i];
     else if (!args[i].startsWith('-')) targetPath = args[i];
   }
@@ -58,6 +65,10 @@ async function main() {
     counts: result.counts,
   };
 
+  if (withTelemetryRecipe) {
+    payload.telemetry_recipe_path = TELEMETRY_RECIPE_PATH;
+  }
+
   const json = JSON.stringify(payload, null, 2);
 
   if (outputFile) {
diff --git a/plugins/config-audit/tests/scanners/token-hotspots-cli.test.mjs b/plugins/config-audit/tests/scanners/token-hotspots-cli.test.mjs
index ef97a94..f6bfde5 100644
--- a/plugins/config-audit/tests/scanners/token-hotspots-cli.test.mjs
+++ b/plugins/config-audit/tests/scanners/token-hotspots-cli.test.mjs
@@ -42,6 +42,30 @@ describe('token-hotspots-cli', () => {
       await unlink(out).catch(() => {});
     }
   });
+
+  it('omits telemetry_recipe_path when --with-telemetry-recipe is absent', async () => {
+    const { stdout } = await exec('node', [CLI, FIXTURE, '--json'], {
+      timeout: 30000,
+      cwd: REPO,
+    });
+    const json = JSON.parse(stdout);
+    assert.equal(json.telemetry_recipe_path, undefined,
+      'telemetry_recipe_path must NOT appear without the flag');
+  });
+
+  it('includes telemetry_recipe_path when --with-telemetry-recipe is passed', async () => {
+    const { stdout } = await exec('node', [CLI, FIXTURE, '--json', '--with-telemetry-recipe'], {
+      timeout: 30000,
+      cwd: REPO,
+    });
+    const json = JSON.parse(stdout);
+    assert.equal(typeof json.telemetry_recipe_path, 'string');
+    assert.ok(json.telemetry_recipe_path.length > 0, 'expected non-empty path');
+    assert.ok(
+      json.telemetry_recipe_path.endsWith('cache-telemetry-recipe.md'),
+      `expected path to end with cache-telemetry-recipe.md, got ${json.telemetry_recipe_path}`
+    );
+  });
 });
 
 describe('scan-orchestrator integration — TOK hotspots survive envelope', () => {