feat(scanner): add AGT agent-listing always-loaded budget finding (v5.9 B1)

New AGT scanner flags the aggregate always-loaded cost of the agent listing
(every active agent's name+description is injected each turn so the model
knows what it can delegate to). Mirrors the SKL skill-listing pattern but
encodes the key honesty caveat: the agent-listing mechanism is INFERRED
(agents are absent from Claude Code's documented context breakdown), so the
token figure is an UPPER-BOUND estimate and the aggregate budget is a
config-audit heuristic anchored on 200k — not a CC-documented allotment.

- scanners/agent-listing-scanner.mjs + scanners/lib/agent-listing-budget.mjs
- 8 TDD tests (tests/scanners/agent-listing-scanner.test.mjs)
- AGT folds into the Token Efficiency health area (scoring.mjs)
- byte-stability: AGT added to strip-added-scanner (frozen v5.0.0 baselines
  left untouched, same as OST/OPT); SC-5 default-output snapshot refreshed
- suite 1168 -> 1176 green

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

scanners/agent-listing-scanner.mjs

@@ -0,0 +1,71 @@
+/**
+ * AGT Scanner — Agent-listing always-loaded token budget
+ *
+ * Claude Code injects a listing of every active agent's name+description into the
+ * system prompt so it knows which subagents it can delegate to. That listing is
+ * re-sent on EVERY turn, whether or not a delegation happens — so with many
+ * installed agents it is a large always-loaded cost (on a heavily-plugged machine
+ * the dominant single always-loaded source).
+ *
+ * Detection:
+ *   CA-AGT-NNN  aggregate agent-listing estimate exceeds the listing budget (low)
+ *
+ * INTELLECTUAL-HONESTY CONTRACT (the reason this is `low`, not a hard finding):
+ * unlike the skill listing, the agent-listing mechanism is NOT documented (agents
+ * are absent from Claude Code's published context breakdown). So the finding is an
+ * INFERRED, UPPER-BOUND ESTIMATE, the budget is a config-audit heuristic (no
+ * documented agent allotment) anchored on a conservative 200k window, and the
+ * evidence discloses all of that. The cap, budget, and enumerate-and-measure step
+ * live in `lib/agent-listing-budget.mjs` — AGT only constructs the finding.
+ *
+ * Zero external dependencies.
+ */
+
+import { finding, scannerResult } from './lib/output.mjs';
+import { SEVERITY } from './lib/severity.mjs';
+import {
+  AGGREGATE_BUDGET_TOKENS,
+  BUDGET_CALIBRATION_NOTE,
+  measureActiveAgentListing,
+} from './lib/agent-listing-budget.mjs';
+
+const SCANNER = 'AGT';
+
+/**
+ * Main scanner entry point.
+ *
+ * @param {string} _targetPath unused (agent listing is HOME-scoped)
+ * @param {object} _discovery unused (ignores project discovery)
+ */
+export async function scan(_targetPath, _discovery) {
+  const start = Date.now();
+  const findings = [];
+
+  const { aggregate } = await measureActiveAgentListing();
+
+  if (aggregate.overBudget) {
+    findings.push(finding({
+      scanner: SCANNER,
+      severity: SEVERITY.low,
+      title: 'Aggregate agent listing may exceed the always-loaded budget',
+      description:
+        `The ${aggregate.scanned} active agents carry about ${aggregate.aggregateTokens} tokens of ` +
+        'name+description text that Claude Code injects every turn so it knows which subagents it can ' +
+        `delegate to — above the ${AGGREGATE_BUDGET_TOKENS}-token budget this scanner anchors on a 200k ` +
+        'context window. Every one of those tokens is re-sent on every turn whether or not you delegate. ' +
+        'Note: unlike the skill listing, the agent-listing always-loaded mechanism is inferred (not ' +
+        'documented), so this is an upper-bound estimate (see evidence).',
+      evidence:
+        `active_agents_scanned=${aggregate.scanned}; description_chars=${aggregate.aggregateChars}; ` +
+        `description_tokens~${aggregate.aggregateTokens}; budget@200k=${AGGREGATE_BUDGET_TOKENS} tok; ` +
+        `over_by~${aggregate.overBy} tok - ${BUDGET_CALIBRATION_NOTE}`,
+      recommendation:
+        'Shrink the always-loaded agent listing: disable plugins whose agents you do not use (the whole ' +
+        'agent block leaves the listing), remove dead user agents from ~/.claude/agents/, and trim long ' +
+        'agent descriptions toward their trigger phrases.',
+      category: 'token-efficiency',
+    }));
+  }
+
+  return scannerResult(SCANNER, 'ok', findings, aggregate.scanned, Date.now() - start);
+}

scanners/lib/agent-listing-budget.mjs

@@ -0,0 +1,123 @@
+/**
+ * Agent-listing budget — single source of truth for the AGT scanner.
+ *
+ * Claude Code injects a listing of every active agent's name+description into the
+ * system prompt so the model knows which subagents it can delegate to. With many
+ * installed agents that listing is a large always-loaded cost: re-sent every turn
+ * whether or not a delegation actually happens.
+ *
+ * CRUCIAL HONESTY CAVEAT — this is why AGT differs from SKL. Unlike the skill
+ * listing (documented ~2% allotment, CC 2.1.32; verified 1,536-char truncation
+ * cap, CC 2.1.105), the agent-listing mechanism is NOT documented — agents are
+ * absent from Claude Code's published context breakdown. Therefore:
+ *   - "always-loaded" is INFERRED (reasoned from the skill analogue + agents'
+ *     absence from the deferred/on-demand list), not documented.
+ *   - the token figure is an UPPER-BOUND ESTIMATE, not measured telemetry.
+ *   - there is no documented per-listing allotment, so the aggregate budget is a
+ *     config-audit heuristic anchored — by analogy to the skill listing — on a
+ *     conservative 200k window, and the evidence says so loudly.
+ *   - there is no verified per-description truncation cap, so (unlike CA-SKL-001)
+ *     each description contributes its FULL length to the aggregate.
+ *
+ * Zero external dependencies.
+ */
+
+import { estimateTokens, enumeratePlugins, enumerateAgents } from './active-config-reader.mjs';
+import { readTextFile } from './file-discovery.mjs';
+import { parseFrontmatter } from './yaml-parser.mjs';
+import { CONTEXT_WINDOW_ANCHOR, LARGE_CONTEXT_WINDOW, withCommas } from './context-window.mjs';
+
+// Heuristic budget by analogy to the skill listing's documented ~2% allotment.
+// Agents have NO documented allotment of their own — disclosed loudly in
+// BUDGET_CALIBRATION_NOTE so the number is never mistaken for a CC guarantee.
+export const BUDGET_FRACTION = 0.02;
+export const AGGREGATE_BUDGET_TOKENS = Math.round(BUDGET_FRACTION * CONTEXT_WINDOW_ANCHOR); // 4000
+export const LARGE_CONTEXT_BUDGET_TOKENS = Math.round(BUDGET_FRACTION * LARGE_CONTEXT_WINDOW); // 20000
+export { CONTEXT_WINDOW_ANCHOR, LARGE_CONTEXT_WINDOW, withCommas };
+
+// The honest framing required because (a) the mechanism is inferred and (b) the
+// budget depends on a context window we cannot observe. Appended to overflow evidence.
+export const BUDGET_CALIBRATION_NOTE =
+  'the agent-listing always-loaded mechanism is INFERRED, not documented (agents are absent from ' +
+  "Claude Code's published context breakdown), so this token figure is an UPPER-BOUND ESTIMATE, not " +
+  'measured telemetry. unlike the skill listing there is no documented per-listing allotment, so this ' +
+  'budget is a config-audit heuristic anchored on a conservative 200k window; at ' +
+  `${withCommas(LARGE_CONTEXT_WINDOW)} context the budget is ~${withCommas(LARGE_CONTEXT_BUDGET_TOKENS)} ` +
+  'tok and you are likely within it';
+
+/**
+ * @typedef {object} AgentBudgetAssessment
+ * @property {number} scanned          - number of agent descriptions assessed
+ * @property {number} aggregateChars   - sum of description lengths (no cap; no verified truncation)
+ * @property {number} aggregateTokens  - estimateTokens(aggregateChars, 'markdown')
+ * @property {number} budgetTokens     - AGGREGATE_BUDGET_TOKENS (the 200k-anchored heuristic)
+ * @property {boolean} overBudget      - aggregateTokens strictly greater than budgetTokens
+ * @property {number} overBy           - tokens over budget (0 when not over)
+ */
+
+/**
+ * Pure aggregate-budget assessment. Each description contributes its full length:
+ * agents have no verified truncation cap, so nothing is dropped from the estimate.
+ *
+ * @param {number[]} descLengths - one entry per active agent (description char count)
+ * @returns {AgentBudgetAssessment}
+ */
+export function assessAgentListingBudget(descLengths) {
+  let aggregateChars = 0;
+  for (const len of descLengths) {
+    const safe = (typeof len === 'number' && Number.isFinite(len) && len > 0) ? len : 0;
+    aggregateChars += safe;
+  }
+  const aggregateTokens = estimateTokens(aggregateChars, 'markdown');
+  const overBudget = aggregateTokens > AGGREGATE_BUDGET_TOKENS;
+  return {
+    scanned: descLengths.length,
+    aggregateChars,
+    aggregateTokens,
+    budgetTokens: AGGREGATE_BUDGET_TOKENS,
+    overBudget,
+    overBy: overBudget ? aggregateTokens - AGGREGATE_BUDGET_TOKENS : 0,
+  };
+}
+
+/**
+ * @typedef {object} ActiveAgentEntry
+ * @property {string} name
+ * @property {'user'|'plugin'} source
+ * @property {string|null} pluginName
+ * @property {string} path
+ * @property {number} descLength
+ */
+
+/**
+ * Enumerate every active agent (user + plugin) and measure the listing budget.
+ * HOME-scoped (mirrors the skill listing): resolves ~/.claude via process.env.HOME
+ * and excludes project-scoped agents — those load only inside their own repo.
+ * Callers that run under test MUST override HOME (runScannerWithHome pattern).
+ *
+ * @returns {Promise<{ agents: ActiveAgentEntry[], aggregate: AgentBudgetAssessment }>}
+ */
+export async function measureActiveAgentListing() {
+  const plugins = await enumeratePlugins();
+  // enumerateAgents yields project + user + plugin; drop project (repo-local).
+  const allAgents = await enumerateAgents('', plugins);
+
+  const agents = [];
+  for (const agent of allAgents) {
+    if (!agent || agent.source === 'project' || typeof agent.path !== 'string') continue;
+    const content = await readTextFile(agent.path);
+    if (!content) continue;
+    const fm = parseFrontmatter(content)?.frontmatter || null;
+    const desc = (fm && typeof fm.description === 'string') ? fm.description : '';
+    agents.push({
+      name: agent.name,
+      source: agent.source,
+      pluginName: agent.pluginName,
+      path: agent.path,
+      descLength: desc.length,
+    });
+  }
+
+  const aggregate = assessAgentListingBudget(agents.map((a) => a.descLength));
+  return { agents, aggregate };
+}

scanners/lib/scoring.mjs

@@ -166,6 +166,7 @@ const SCANNER_AREA_MAP = {
   TOK: 'Token Efficiency',
   CPS: 'Token Efficiency',
   SKL: 'Token Efficiency',
+  AGT: 'Token Efficiency',
   DIS: 'Settings',
   COL: 'Plugin Hygiene',
   OST: 'Settings',

scanners/scan-orchestrator.mjs

@@ -29,6 +29,7 @@ import { scan as scanCachePrefix } from './cache-prefix-scanner.mjs';
 import { scan as scanDisabledInSchema } from './disabled-in-schema-scanner.mjs';
 import { scan as scanCollision } from './collision-scanner.mjs';
 import { scan as scanSkillListing } from './skill-listing-scanner.mjs';
+import { scan as scanAgentListing } from './agent-listing-scanner.mjs';
 import { scan as scanOutputStyle } from './output-style-scanner.mjs';
 import { scan as scanOptimizationLens } from './optimization-lens-scanner.mjs';
 
@@ -66,6 +67,7 @@ const SCANNERS = [
   { name: 'DIS', fn: scanDisabledInSchema, label: 'Disabled-In-Schema' },
   { name: 'COL', fn: scanCollision, label: 'Plugin Skill Collision' },
   { name: 'SKL', fn: scanSkillListing, label: 'Skill-Listing Budget' },
+  { name: 'AGT', fn: scanAgentListing, label: 'Agent-Listing Budget' },
   { name: 'OST', fn: scanOutputStyle, label: 'Output-Style Validation' },
   { name: 'OPT', fn: scanOptimizationLens, label: 'Optimization Lens' },
 ];

tests/helpers/strip-added-scanner.mjs

@@ -1,12 +1,13 @@
 /**
- * v5.6 C added the OST (Output-Style Validation) scanner — a 14th orchestrated
+ * Post-v5.0.0 additive scanners that the frozen v5.0.0 byte-equal baselines
- * scanner. The frozen v5.0.0 byte-equal baselines predate it (13 scanners), so
+ * predate: OST (Output-Style Validation, v5.6 C), OPT (Optimization Lens, v5.7),
- * this strips the additive OST scanner entry before comparison, the same way
+ * and AGT (Agent-Listing Budget, v5.9 B1). The baselines froze the original
- * strip-hotspot-load-pattern.mjs handles B2's additive hotspot fields. Stripping
+ * scanner set, so this strips these additive scanner entries before comparison,
- * (rather than re-seeding the frozen snapshots) keeps the strongest invariant:
+ * the same way strip-hotspot-load-pattern.mjs handles B2's additive hotspot
- * the ORIGINAL 13 scanners still emit byte-identical output, and the frozen
+ * fields. Stripping (rather than re-seeding the frozen snapshots) keeps the
- * snapshots stay free of post-v5.0.0 drift (the hotspot triple, ancestor token
+ * strongest invariant: the ORIGINAL scanners still emit byte-identical output,
- * counts) that re-seeding would bake in.
+ * and the frozen snapshots stay free of post-v5.0.0 drift (the hotspot triple,
+ * ancestor token counts) that re-seeding would bake in.
  *
  * Removing a zero-finding scanner entry only moves `aggregate.scanners_ok`
  * (OST is always status 'ok' and emits nothing on the deterministic fixture, so
@@ -17,7 +18,7 @@
  *   return stripAddedScanners(stripHotspotLoadPattern(out));
  */
 
-const ADDED_SCANNERS = new Set(['OST', 'OPT']);
+const ADDED_SCANNERS = new Set(['OST', 'OPT', 'AGT']);
 
 function stripFromEnvelope(env) {
   if (!env || typeof env !== 'object' || !Array.isArray(env.scanners)) return;
@@ -58,5 +59,5 @@ export function stripAddedScanners(payload) {
  */
 export function stripAddedScannerStderr(text) {
   if (typeof text !== 'string') return text;
-  return text.replace(/^[ \t]*\[(OST|OPT)\][^\n]*\n/gm, '');
+  return text.replace(/^[ \t]*\[(OST|OPT|AGT)\][^\n]*\n/gm, '');
 }

tests/scanners/agent-listing-scanner.test.mjs

@@ -0,0 +1,174 @@
+import { describe, it } from 'node:test';
+import assert from 'node:assert/strict';
+import { join } from 'node:path';
+import { mkdir, writeFile, rm } from 'node:fs/promises';
+import { tmpdir } from 'node:os';
+import { resetCounter } from '../../scanners/lib/output.mjs';
+import { scan } from '../../scanners/agent-listing-scanner.mjs';
+
+/**
+ * AGT scanner — agent-listing always-loaded token budget.
+ *
+ * Claude Code injects a listing of every active agent's name+description into the
+ * system prompt so the model knows which subagents it can delegate to. With ~100
+ * agents that listing is a large always-loaded cost. UNLIKE the skill listing,
+ * the agent-listing mechanism is NOT documented (agents are absent from CC's
+ * deferred / always-loaded context breakdown), so AGT findings are an INFERRED
+ * upper-bound estimate, not a verified truncation like SKL-001. The aggregate
+ * budget is a config-audit heuristic anchored on a conservative 200k window.
+ *
+ * Token heuristic mirrors estimateTokens('markdown'): ceil(chars/4).
+ *   16 agents * 1000 desc-chars = 16000 chars -> 4000 tok == budget (NOT over).
+ *   17 agents * 1000 desc-chars = 17000 chars -> 4250 tok  > budget (over).
+ */
+const AGGREGATE_BUDGET_TOKENS = 4000; // heuristic: 0.02 * 200_000 (anchored, disclosed)
+
+function uniqueDir(suffix) {
+  return join(tmpdir(), `config-audit-agt-${suffix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`);
+}
+
+/**
+ * The AGT scanner enumerates active agents via process.env.HOME. Tests must
+ * override HOME, run, restore — never rely on the developer's real ~/.claude.
+ */
+async function runScannerWithHome(home) {
+  resetCounter();
+  const original = process.env.HOME;
+  process.env.HOME = home;
+  try {
+    return await scan('/unused', { files: [] });
+  } finally {
+    process.env.HOME = original;
+  }
+}
+
+/** Write one user agent (name + description of `descLen` chars) into a HOME. */
+async function addUserAgent(home, name, descLen) {
+  const dir = join(home, '.claude', 'agents');
+  await mkdir(dir, { recursive: true });
+  const desc = 'a'.repeat(descLen);
+  await writeFile(
+    join(dir, `${name}.md`),
+    `---\nname: ${name}\ndescription: ${desc}\n---\nYou are the ${name} agent. Body of the agent prompt.\n`,
+  );
+}
+
+/** Build a fake HOME with `count` user agents, each description `descLen` chars. */
+async function homeWithNUserAgents(count, descLen, prefix = 'agg') {
+  const home = uniqueDir(`${prefix}-${count}x${descLen}`);
+  for (let i = 0; i < count; i++) {
+    await addUserAgent(home, `${prefix}${i}`, descLen);
+  }
+  return home;
+}
+
+const findAggregate = (findings) => findings.find(f => /agent listing/i.test(f.title));
+
+describe('AGT scanner — basic structure', () => {
+  it('reports scanner prefix AGT', async () => {
+    const home = uniqueDir('empty');
+    try {
+      await mkdir(join(home, '.claude'), { recursive: true });
+      const result = await runScannerWithHome(home);
+      assert.equal(result.scanner, 'AGT');
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+
+  it('finding IDs match CA-AGT-NNN pattern', async () => {
+    const home = await homeWithNUserAgents(17, 1000);
+    try {
+      const result = await runScannerWithHome(home);
+      for (const f of result.findings) assert.match(f.id, /^CA-AGT-\d{3}$/);
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+});
+
+describe('AGT scanner — aggregate always-loaded budget', () => {
+  it('fires a low-severity finding when the agent listing exceeds the 200k-anchored budget', async () => {
+    const home = await homeWithNUserAgents(17, 1000); // 17000 chars -> ~4250 tok > 4000
+    try {
+      const result = await runScannerWithHome(home);
+      const agg = findAggregate(result.findings);
+      assert.ok(agg, `expected an aggregate finding; got: ${result.findings.map(f => f.title).join(' | ')}`);
+      assert.equal(agg.severity, 'low', `aggregate should be low severity, got ${agg.severity}`);
+      assert.match(agg.id, /^CA-AGT-\d{3}$/);
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+
+  it('does NOT fire when only a few small agents are active', async () => {
+    const home = await homeWithNUserAgents(3, 1000); // 3000 chars -> 750 tok < 4000
+    try {
+      const result = await runScannerWithHome(home);
+      assert.equal(findAggregate(result.findings), undefined,
+        `expected no aggregate finding; got: ${result.findings.map(f => f.title).join(' | ')}`);
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+
+  it('treats the budget as a strict boundary: 16x1000 (at budget) no fire, 17x1000 (over) fires', async () => {
+    const atBudget = await homeWithNUserAgents(16, 1000, 'at'); // 16000 chars -> 4000 tok == budget
+    try {
+      const result = await runScannerWithHome(atBudget);
+      assert.equal(findAggregate(result.findings), undefined,
+        'aggregate exactly at the budget must not fire (strictly-greater rule)');
+    } finally {
+      await rm(atBudget, { recursive: true, force: true });
+    }
+    const overBudget = await homeWithNUserAgents(17, 1000, 'over'); // 17000 chars -> 4250 tok
+    try {
+      const result = await runScannerWithHome(overBudget);
+      assert.ok(findAggregate(result.findings), 'aggregate one step over the budget must fire');
+    } finally {
+      await rm(overBudget, { recursive: true, force: true });
+    }
+  });
+
+  it('DISCLOSES the inferred mechanism + upper-bound estimate + anchor (intellectual honesty)', async () => {
+    const home = await homeWithNUserAgents(17, 1000);
+    try {
+      const result = await runScannerWithHome(home);
+      const agg = findAggregate(result.findings);
+      assert.ok(agg, 'expected an aggregate finding');
+      const ev = String(agg.evidence);
+      assert.match(ev, /infer/i, 'evidence must disclose the always-loaded mechanism is INFERRED, not documented');
+      assert.match(ev, /estimate|upper.?bound/i, 'evidence must flag the figure as an estimate / upper bound');
+      assert.match(ev, new RegExp(String(AGGREGATE_BUDGET_TOKENS)), 'evidence must state the budget');
+      assert.match(ev, /200k/, 'evidence must anchor the budget on a 200k window');
+      assert.match(ev, /1,000,000|1M|20,000/, 'evidence must note the 1M-context scaling');
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+
+  it('recommends the reduction levers (disable unused plugins / trim descriptions)', async () => {
+    const home = await homeWithNUserAgents(17, 1000);
+    try {
+      const result = await runScannerWithHome(home);
+      const agg = findAggregate(result.findings);
+      assert.ok(agg, 'expected an aggregate finding to carry remediation');
+      const rec = String(agg.recommendation);
+      assert.match(rec, /disable|plugin/i, 'recommendation should mention disabling unused plugins');
+      assert.match(rec, /trim|description/i, 'recommendation should mention trimming descriptions');
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+
+  it('an empty HOME (no agents) yields zero findings', async () => {
+    const home = uniqueDir('noagents');
+    try {
+      await mkdir(join(home, '.claude'), { recursive: true });
+      const result = await runScannerWithHome(home);
+      assert.equal(result.findings.length, 0);
+    } finally {
+      await rm(home, { recursive: true, force: true });
+    }
+  });
+});

tests/scanners/scan-orchestrator-humanizer.test.mjs

@@ -103,7 +103,7 @@ describe('scan-orchestrator humanizer wiring (Step 5)', () => {
       assert.ok(actual.meta, 'meta present');
       assert.ok(Array.isArray(actual.scanners), 'scanners array present');
       assert.ok(actual.aggregate, 'aggregate present');
-      assert.equal(actual.scanners.length, 15, 'all 15 scanners present');
+      assert.equal(actual.scanners.length, 16, 'all 16 scanners present');
     });
 
     it('preserves scanner shape (scanner/status/findings/counts)', async () => {

tests/snapshots/default-output/posture.json

@@ -1,4 +1,4 @@
 {
   "kind": "text",
-  "payload": "`[CML] CLAUDE.md Linter`: 1 finding(s) (0ms)\n  `[SET] Settings Validator`: 0 finding(s) (0ms)\n  `[HKV] Hook Validator`: 0 finding(s) (0ms)\n  `[RUL] Rules Validator`: 0 finding(s) (0ms)\n  `[MCP] MCP Config Validator`: 0 finding(s) (0ms)\n  `[IMP] Import Resolver`: 0 finding(s) (0ms)\n  `[CNF] Conflict Detector`: 0 finding(s) (0ms)\n  `[GAP] Feature Gap Scanner`: 17 finding(s) (0ms)\n  `[TOK] Token Hotspots`: 1 finding(s) (0ms)\n  `[CPS] Cache-Prefix Stability`: 0 finding(s) (0ms)\n  `[DIS] Disabled-In-Schema`: 0 finding(s) (0ms)\n  `[COL] Plugin Skill Collision`: 0 finding(s) (0ms)\n  `[SKL] Skill-Listing Budget`: 0 finding(s) (0ms)\n  `[OST] Output-Style Validation`: 0 finding(s) (0ms)\n  `[OPT] Optimization Lens`: 0 finding(s) (0ms)\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n Configuration health\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n Health: A (98/100) — Healthy setup, only minor polish needed\n 9 areas reviewed\n\n Area scores\n ───────────\n `CLAUDE.md` ........... A (90)      `Settings` ............ A (100)\n `Hooks` ............... A (100)     `Rules` ............... A (100)\n `MCP` ................. A (100)     `Imports` ............. A (100)\n `Conflicts` ........... A (100)     `Token Efficiency` .... A (90)\n `Plugin Hygiene` ...... A (100)\n\n 17 ways you could get more out of Claude Code — see /config-audit feature-gap\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "payload": "`[CML] CLAUDE.md Linter`: 1 finding(s) (0ms)\n  `[SET] Settings Validator`: 0 finding(s) (0ms)\n  `[HKV] Hook Validator`: 0 finding(s) (0ms)\n  `[RUL] Rules Validator`: 0 finding(s) (0ms)\n  `[MCP] MCP Config Validator`: 0 finding(s) (0ms)\n  `[IMP] Import Resolver`: 0 finding(s) (0ms)\n  `[CNF] Conflict Detector`: 0 finding(s) (0ms)\n  `[GAP] Feature Gap Scanner`: 17 finding(s) (0ms)\n  `[TOK] Token Hotspots`: 1 finding(s) (0ms)\n  `[CPS] Cache-Prefix Stability`: 0 finding(s) (0ms)\n  `[DIS] Disabled-In-Schema`: 0 finding(s) (0ms)\n  `[COL] Plugin Skill Collision`: 0 finding(s) (0ms)\n  `[SKL] Skill-Listing Budget`: 0 finding(s) (0ms)\n  `[AGT] Agent-Listing Budget`: 0 finding(s) (0ms)\n  `[OST] Output-Style Validation`: 0 finding(s) (0ms)\n  `[OPT] Optimization Lens`: 0 finding(s) (0ms)\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n Configuration health\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n Health: A (98/100) — Healthy setup, only minor polish needed\n 9 areas reviewed\n\n Area scores\n ───────────\n `CLAUDE.md` ........... A (90)      `Settings` ............ A (100)\n `Hooks` ............... A (100)     `Rules` ............... A (100)\n `MCP` ................. A (100)     `Imports` ............. A (100)\n `Conflicts` ........... A (100)     `Token Efficiency` .... A (90)\n `Plugin Hygiene` ...... A (100)\n\n 17 ways you could get more out of Claude Code — see /config-audit feature-gap\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
 }

tests/snapshots/default-output/scan-orchestrator.json

@@ -569,6 +569,20 @@
           "info": 0
         }
       },
+      {
+        "scanner": "AGT",
+        "status": "ok",
+        "files_scanned": 0,
+        "duration_ms": 0,
+        "findings": [],
+        "counts": {
+          "critical": 0,
+          "high": 0,
+          "medium": 0,
+          "low": 0,
+          "info": 0
+        }
+      },
       {
         "scanner": "OST",
         "status": "ok",
@@ -610,7 +624,7 @@
       "risk_score": 11,
       "risk_band": "Medium",
       "verdict": "PASS",
-      "scanners_ok": 14,
+      "scanners_ok": 15,
       "scanners_error": 0,
       "scanners_skipped": 1
     }