@event4u/agent-config 9.0.0 → 9.1.0

package/dist/agent-src/skills/token-optimizer/SKILL.md

@@ -64,10 +64,15 @@ INTENT
 │     → cite [agent-handoff](../../../.claude/skills/agent-handoff/SKILL.md)
 │       (structured handoff envelope; resume in fresh chat)
 │
-└── Cost-aware decision (model pick, budget, stop-criterion)
-      → cite /cost:report (when shipped) — until then, fall back to
-        [token-efficiency](../../rules/token-efficiency.md) and
-        [direct-answers § Brevity by Default](../../rules/direct-answers.md)
+├── Cost-aware decision (model pick, budget, stop-criterion)
+│     → cite /cost:report (when shipped) — until then, fall back to
+│       [token-efficiency](../../rules/token-efficiency.md) and
+│       [direct-answers § Brevity by Default](../../rules/direct-answers.md)
+│
+└── API-bill lever (stable prefix reused across calls · non-interactive
+    bulk cohort · model/effort pick against the paid Anthropic bill)
+      → cite [api-cost-levers](../../../docs/guidelines/agent-infra/api-cost-levers.md)
+        (prompt caching ~0.1x reads · Batch -50% · model tiering · effort)
 ```
 
 ## Catalog
@@ -81,6 +86,7 @@ INTENT
 | `direct-answers` | `.agent-src.uncondensed/rules/direct-answers.md` | `brevity`, `flattery`, `severity`, `tiered` | Iron-Law brevity floor (kernel) |
 | `markitdown` | upstream: github.com/microsoft/markitdown | `PDF`, `DOCX`, `HTML`, `convert` | Document → markdown converter (authoritative-link only) |
 | `/cost:report` | TBD — an internal roadmap (local-only) | `cost`, `model spend`, `budget` | Per-session cost telemetry (planned) |
+| `api-cost-levers` | `docs/guidelines/agent-infra/api-cost-levers.md` | `cache`, `caching`, `batch`, `tiering`, `effort` | Anthropic billing levers: prompt caching, Batch API, model tiering, effort/output right-sizing |
 
 ## Output format
 

package/dist/agent-src/templates/agent-settings.md

@@ -402,8 +402,31 @@ commands:
   # When `true`: show title and body in copyable code blocks and ask
   # for adjustments before creating the PR.
   # `/create-pr:description-only` always previews — that is its sole purpose.
+  #
+  # detail_level: verbosity tier of the PR Description body.
+  #   min (default) = title + 2-3 sentence what/why/impact + linked ticket;
+  #   med           = min + grouped changes + tests note;
+  #   max           = med + how-to-test + edge cases + reviewer guidance.
+  # Critical info (breaking changes, migrations, security, rollback) is
+  # ALWAYS included at every tier — the tier governs explanatory depth only.
+  #
+  # api_examples (default true): add a fenced JSON example for API-endpoint
+  #   changes ONLY when grounded in a real source (DTO/resource, OpenAPI,
+  #   fixture, probe); else a one-line pointer, never an invented example.
+  #
+  # screenshots (default false): capability-gated frontend screenshots.
+  #   true attempts capture only when the host has browser/preview tooling;
+  #   emits a note and leaves the placeholder when absent — never blocks the PR.
+  #
+  # ui_paths / api_paths: optional globs to make frontend / API detection
+  #   explicit; empty = a light heuristic that fails open.
   create_pr:
     preview_description: false
+    detail_level: min
+    api_examples: true
+    screenshots: false
+    ui_paths: []
+    api_paths: []
 
 # --- Telemetry (artefact engagement, default-off) ---
 #
@@ -582,6 +605,11 @@ the canonical narrative lives in
 | `commands.suggestion.max_options` | integer | `4` | Max number of command suggestions before the always-present "run as-is" option (total rendered = `max_options + 1`). |
 | `commands.suggestion.blocklist` | list of command names | `[]` | Commands that never appear as a suggestion. They still work when typed explicitly. |
 | `commands.create_pr.preview_description` | `true`, `false` | `false` | When `false`: `/create-pr` skips the title/body preview + adjust loop and uses the generated content directly. Saves agent tokens. When `true`: show title and body before creating and ask for adjustments. `/create-pr:description-only` always previews regardless of this setting. |
+| `commands.create_pr.detail_level` | `min`, `med`, `max` | `min` | Verbosity tier of the PR Description body. `min` = title + 2-3 sentence what/why/impact + ticket; `med` = + grouped changes + tests note; `max` = + how-to-test + edge cases + reviewer guidance. Critical info (breaking / migration / security / rollback) is included at every tier. |
+| `commands.create_pr.api_examples` | `true`, `false` | `true` | Add a grounded JSON example for API-endpoint changes; `true` includes one only from a real source (DTO/OpenAPI/fixture/probe), else a pointer, never invented; `false` = never. |
+| `commands.create_pr.screenshots` | `true`, `false` | `false` | Capability-gated frontend screenshots. `true` attempts capture when browser/preview tooling is present; notes-and-skips otherwise, never blocks the PR. Before/after is best-effort. |
+| `commands.create_pr.ui_paths` | glob list | `[]` | Optional globs pinning frontend detection; empty = light heuristic, fail-open. |
+| `commands.create_pr.api_paths` | glob list | `[]` | Optional globs pinning API-endpoint detection; empty = light heuristic, fail-open. |
 | `verbosity.preview_artifacts` | `true`, `false` | `false` | Show generated commit messages, PR titles/bodies, branch names before acting. `false` = use generated content directly. See the token-frugality plate under `agents/roadmaps/` (Phase 2/3). |
 | `verbosity.routine_confirmations` | `true`, `false` | `false` | Confirmation prompts for routine workflow steps when there is one obvious answer ("looks good — commit?"). Iron-Law gates (`commit-policy`, `scope-control` git-ops, `non-destructive-by-default`) ALWAYS ask regardless. |
 | `verbosity.offer_council_in_delivery` | `true`, `false` | `false` | Offer "run AI Council on this?" inside delivery commands (`/feature-plan`, `/review-changes`, `/roadmap-create`). Council commands themselves are unaffected. |

package/dist/agent-src/templates/agents/agent-project-settings.example.yml

@@ -39,7 +39,7 @@ schema_version: 1
 # CI guard: a release bump of `package.json` must update this value
 # in lockstep — see scripts/check_template_pin_drift.ts (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "9.0.0"
+agent_config_version: "9.1.0"
 
 # --- Project identity ---
 project:

package/dist/agent-src/templates/scripts/work_engine/_lib/agent_settings.ts

@@ -252,7 +252,10 @@ const _AGENTS_DIR_MARKERS: readonly string[] = [
     'roadmaps',
     'settings/.ai-council.yml',
     'roadmaps-progress.md',
-    '.event4u-bridge.yml',
+    // `overrides/` is the guaranteed minimal-consumer surface (ADR-020).
+    // Replaced the retired `.event4u-bridge.yml` marker (ADR-020 amendment
+    // 2026-07-13) so a bare consumer `agents/` dir stays anchorable.
+    'overrides',
 ];
 
 /**

package/dist/discovery/deprecation-report.md

@@ -1,6 +1,6 @@
 # Discovery — Deprecation Report
 
-- Generated: `2026-07-13T16:33:05Z`
+- Generated: `2026-07-14T09:00:03Z`
 - Deprecated artefacts: **0**
 
 _None. Tree is clean._

package/dist/discovery/discovery-manifest.json

@@ -2024,7 +2024,7 @@
     },
     {
       "category": "command",
-      "checksum": "sha256:d0920f8622036de710a79580e62fe52dbac9aacb4a02ef51a883f887fe880dd4",
+      "checksum": "sha256:5345a5d1bbe083a194fbeb8d6b24b84cfbccabfea01ddbb0e706fee65a52f352",
       "install": {
         "default": true,
         "removable": false
@@ -2057,7 +2057,7 @@
     },
     {
       "category": "command",
-      "checksum": "sha256:0b65a9541ce6e3a85e498ccccedb1ae10b71b764a89d439bf30dd4bc1d532cb9",
+      "checksum": "sha256:aa8c4c8693b707d0c310dc813d520f8e07b2f7710591ed6e3e43065414f18f9a",
       "install": {
         "default": true,
         "removable": false
@@ -3295,6 +3295,32 @@
         "agent-config-maintainer"
       ]
     },
+    {
+      "category": "command",
+      "checksum": "sha256:42adcd4d33a67e05d9d2af36acff477e1c9e28de18ceac7b0b021942d154d42d",
+      "install": {
+        "default": true,
+        "removable": false
+      },
+      "lifecycle": "active",
+      "name": "explain-run",
+      "pack": "meta",
+      "packs": [
+        "meta"
+      ],
+      "path": "src/domains/meta/explain-run/command.md",
+      "slug": "explain-run",
+      "tier": 2,
+      "trust": {
+        "confidence": "high",
+        "human_review_required": false,
+        "level": "core"
+      },
+      "visibility": "internal",
+      "workspaces": [
+        "agent-config-maintainer"
+      ]
+    },
     {
       "category": "command",
       "checksum": "sha256:5ea87906367205616ee02acabd06cd14fc2b920bea1bb0986374b97ca8395ee7",
@@ -10536,6 +10562,34 @@
         "engineering"
       ]
     },
+    {
+      "category": "skill",
+      "checksum": "sha256:6abf10a4cd93bf305637d403ad317d08d0256dd441858d7243322e482e13a1bb",
+      "install": {
+        "default": true,
+        "removable": true
+      },
+      "lifecycle": "active",
+      "name": "llm-provider-knowledge",
+      "packs": [
+        "meta"
+      ],
+      "path": "src/skills/llm-provider-knowledge/SKILL.md",
+      "trust": {
+        "confidence": "high",
+        "human_review_required": false,
+        "level": "experimental"
+      },
+      "workspaces": [
+        "agent-config-maintainer",
+        "engineering",
+        "product",
+        "founder",
+        "small-business",
+        "gtm",
+        "ops"
+      ]
+    },
     {
       "category": "skill",
       "checksum": "sha256:62d98b2e295e68ce7d57e09dc6dc57791435b422ede5460c1f5edb3f708494df",
@@ -13090,7 +13144,7 @@
     },
     {
       "category": "skill",
-      "checksum": "sha256:dd78527c8556401fd6ec48700087dac3068237938bc476b38464f15d53f15ce3",
+      "checksum": "sha256:0fdbc771503a17f5e27eb5d9dc3d2325863cf4e67580421176f73c5c9c10bd01",
       "install": {
         "default": true,
         "removable": false
@@ -13481,7 +13535,7 @@
       "workspaces": []
     }
   ],
-  "checksum": "sha256:a01d13b0513f9f8f628ae5d753e3c46438a1eae564edef493a8f2fbbeadd6ace",
+  "checksum": "sha256:69fcb002e72524fe832ff2fc8dc5cfc7335f71d1b6c049c8e108c83665d97eb2",
   "deprecations": [
     {
       "key": "tier",
@@ -13624,7 +13678,7 @@
       "reason": "scaffold template for ticket-bundle tickets (ADR-101); carries no runtime frontmatter — emit-tickets fills it in per ticket"
     }
   ],
-  "generated_at": "2026-07-13T16:33:05Z",
+  "generated_at": "2026-07-14T09:00:03Z",
   "packs": [
     {
       "artefact_count": 106,
@@ -14289,7 +14343,7 @@
     },
     {
       "always_on": true,
-      "artefact_count": 272,
+      "artefact_count": 274,
       "description": "Artefacts that maintain this package (agent-config itself).",
       "domain": "meta",
       "human_review_required": 0,
@@ -14305,8 +14359,8 @@
       "trust_level_default": "core",
       "trust_summary": {
         "advisory": 0,
-        "core": 271,
-        "experimental": 1,
+        "core": 272,
+        "experimental": 2,
         "professional": 0,
         "restricted": 0
       },
@@ -14396,27 +14450,27 @@
   "scanner_version": "c24312e116f8",
   "stats": {
     "by_category": {
-      "command": 183,
+      "command": 184,
       "rule": 104,
-      "skill": 274,
+      "skill": 275,
       "subagent": 1,
       "template": 1
     },
     "by_lifecycle": {
-      "active": 547,
+      "active": 549,
       "archived": 0,
       "deprecated": 0,
       "experimental": 16
     },
     "by_trust_level": {
       "advisory": 8,
-      "core": 437,
-      "experimental": 20,
+      "core": 438,
+      "experimental": 21,
       "professional": 98,
       "restricted": 0
     },
     "documented_unassigned_count": 26,
-    "total_artefacts": 563,
+    "total_artefacts": 565,
     "unassigned_count": 0
   },
   "unassigned": [],

package/dist/discovery/discovery-manifest.json.sha256

@@ -1 +1 @@
-bfce8bfcd500e36d9d77f783942e69a0aea231b590a176a283d9d95a047715f1  discovery-manifest.json
+4edf44025858feda295b87664a0aa847b8b44794c21fa92fc6fd6ce0c976608a  discovery-manifest.json

package/dist/discovery/discovery-manifest.summary.md

@@ -1,8 +1,8 @@
 # Discovery Manifest — Summary
 
-- Generated: `2026-07-13T16:33:05Z`
+- Generated: `2026-07-14T09:00:03Z`
 - Scanner: `c24312e116f8`
-- Artefacts: **563**
+- Artefacts: **565**
 - Unassigned: **0**
 
 ## `engineering` — Engineering
@@ -103,7 +103,7 @@
 
 | Pack | Artefacts |
 |---|---|
-| `meta` — Meta | 272 |
+| `meta` — Meta | 274 |
 | `memory` — Memory | 9 |
 | `analytics` — Analytics | 4 |
 | `product-reasoning` — Product Reasoning | 11 |

package/dist/discovery/orphan-report.md

@@ -1,6 +1,6 @@
 # Discovery — Orphan Report
 
-- Generated: `2026-07-13T16:33:05Z`
+- Generated: `2026-07-14T09:00:03Z`
 - Orphan artefacts: **0**
 
 > An orphan is an artefact whose declared pack has no other members.

package/dist/discovery/packs.json

@@ -1,6 +1,6 @@
 {
-  "checksum": "sha256:a01d13b0513f9f8f628ae5d753e3c46438a1eae564edef493a8f2fbbeadd6ace",
-  "generated_at": "2026-07-13T16:33:05Z",
+  "checksum": "sha256:69fcb002e72524fe832ff2fc8dc5cfc7335f71d1b6c049c8e108c83665d97eb2",
+  "generated_at": "2026-07-14T09:00:03Z",
   "packs": [
     {
       "always_on": false,
@@ -1221,7 +1221,7 @@
     },
     {
       "always_on": true,
-      "artefact_count": 272,
+      "artefact_count": 274,
       "artefacts": [
         "src/agent-src/templates/agents/proposal.example.md",
         "src/domains/ai-video/image/analyse/command.md",
@@ -1309,6 +1309,7 @@
         "src/domains/meta/context/refactor/command.md",
         "src/domains/meta/cost/command.md",
         "src/domains/meta/cost/profile/command.md",
+        "src/domains/meta/explain-run/command.md",
         "src/domains/meta/mode/command.md",
         "src/domains/meta/optimize/agents-dir/command.md",
         "src/domains/meta/optimize/augmentignore/command.md",
@@ -1459,6 +1460,7 @@
         "src/skills/judge-test-coverage/SKILL.md",
         "src/skills/learning-to-rule-or-skill/SKILL.md",
         "src/skills/lint-skills/SKILL.md",
+        "src/skills/llm-provider-knowledge/SKILL.md",
         "src/skills/markitdown/SKILL.md",
         "src/skills/mcp-builder/SKILL.md",
         "src/skills/mcp/SKILL.md",
@@ -1497,15 +1499,15 @@
         "src/skills/verify-repair-loop/SKILL.md"
       ],
       "by_lifecycle": {
-        "active": 271,
+        "active": 273,
         "archived": 0,
         "deprecated": 0,
         "experimental": 1
       },
       "by_trust_level": {
         "advisory": 0,
-        "core": 271,
-        "experimental": 1,
+        "core": 272,
+        "experimental": 2,
         "professional": 0,
         "restricted": 0
       },

package/dist/discovery/trust-report.md

@@ -1,6 +1,6 @@
 # Discovery — Trust Report
 
-- Generated: `2026-07-13T16:33:05Z`
+- Generated: `2026-07-14T09:00:03Z`
 - Workspaces tracked: **10**
 - Human-review-required artefacts: **3**
 
@@ -8,16 +8,16 @@
 
 | Workspace | core | professional | experimental | advisory | restricted |
 |---|---|---|---|---|---|
-| `agent-config-maintainer` | 303 | 0 | 2 | 0 | 0 |
+| `agent-config-maintainer` | 304 | 0 | 3 | 0 | 0 |
 | `construction` | 23 | 0 | 0 | 0 | 0 |
-| `engineering` | 167 | 58 | 1 | 0 | 0 |
+| `engineering` | 167 | 58 | 2 | 0 | 0 |
 | `finance` | 26 | 4 | 0 | 1 | 0 |
-| `founder` | 30 | 0 | 0 | 1 | 0 |
-| `gtm` | 28 | 13 | 0 | 0 | 0 |
+| `founder` | 30 | 0 | 1 | 1 | 0 |
+| `gtm` | 28 | 13 | 1 | 0 | 0 |
 | `legal-review-prep` | 23 | 0 | 0 | 6 | 0 |
-| `ops` | 23 | 8 | 0 | 0 | 0 |
-| `product` | 23 | 15 | 0 | 0 | 0 |
-| `small-business` | 29 | 0 | 18 | 0 | 0 |
+| `ops` | 23 | 8 | 1 | 0 | 0 |
+| `product` | 23 | 15 | 1 | 0 | 0 |
+| `small-business` | 29 | 0 | 19 | 0 | 0 |
 
 ## Human-review-required artefacts
 

package/dist/discovery/workspaces.json

@@ -1,6 +1,6 @@
 {
-  "checksum": "sha256:a01d13b0513f9f8f628ae5d753e3c46438a1eae564edef493a8f2fbbeadd6ace",
-  "generated_at": "2026-07-13T16:33:05Z",
+  "checksum": "sha256:69fcb002e72524fe832ff2fc8dc5cfc7335f71d1b6c049c8e108c83665d97eb2",
+  "generated_at": "2026-07-14T09:00:03Z",
   "scanner_version": "c24312e116f8",
   "workspaces": [
     {
@@ -593,7 +593,7 @@
       ]
     },
     {
-      "artefact_count": 296,
+      "artefact_count": 298,
       "default_packs": [
         "meta",
         "memory",
@@ -606,7 +606,7 @@
       "optional_packs": [],
       "packs": [
         {
-          "artefact_count": 272,
+          "artefact_count": 274,
           "artefacts": [
             "src/agent-src/templates/agents/proposal.example.md",
             "src/domains/ai-video/image/analyse/command.md",
@@ -694,6 +694,7 @@
             "src/domains/meta/context/refactor/command.md",
             "src/domains/meta/cost/command.md",
             "src/domains/meta/cost/profile/command.md",
+            "src/domains/meta/explain-run/command.md",
             "src/domains/meta/mode/command.md",
             "src/domains/meta/optimize/agents-dir/command.md",
             "src/domains/meta/optimize/augmentignore/command.md",
@@ -844,6 +845,7 @@
             "src/skills/judge-test-coverage/SKILL.md",
             "src/skills/learning-to-rule-or-skill/SKILL.md",
             "src/skills/lint-skills/SKILL.md",
+            "src/skills/llm-provider-knowledge/SKILL.md",
             "src/skills/markitdown/SKILL.md",
             "src/skills/mcp-builder/SKILL.md",
             "src/skills/mcp/SKILL.md",

package/dist/install/install.mjs

@@ -9536,7 +9536,10 @@ var _AGENTS_DIR_MARKERS = [
   "roadmaps",
   "settings/.ai-council.yml",
   "roadmaps-progress.md",
-  ".event4u-bridge.yml"
+  // `overrides/` is the guaranteed minimal-consumer surface (ADR-020).
+  // Replaced the retired `.event4u-bridge.yml` marker (ADR-020 amendment
+  // 2026-07-13) so a bare consumer `agents/` dir stays anchorable.
+  "overrides"
 ];
 var _LEGACY_ANCHOR_ENV = "AGENT_CONFIG_LEGACY_ANCHOR";
 function _exists(p) {
@@ -14287,6 +14290,21 @@ var settingsSchema = external_exports.object({
     create_pr: external_exports.object({
       preview_description: external_exports.boolean().default(false).describe(
         "When /create-pr runs, show the generated title and body and wait for confirmation before opening the PR. Off by default (zero-friction PR creation); turn on if you want a last-look gate."
+      ),
+      detail_level: external_exports.enum(["min", "med", "max"]).default("min").describe(
+        "Verbosity tier for the generated PR description body. min (default) = title + 2-3 sentence what/why/impact + linked ticket (token-frugal); med = min + grouped changes + tests note; max = med + how-to-test + edge cases + reviewer guidance. Critical info (breaking changes, migrations, security, rollback) is ALWAYS included at every tier \u2014 the tier governs explanatory depth, never whether a critical callout appears."
+      ),
+      api_examples: external_exports.boolean().default(true).describe(
+        "JSON request/response examples for API-endpoint changes. true (default) = include a fenced example ONLY when grounded in a real source (response DTO/resource, OpenAPI/schema, test fixture, or an actual probe); no grounded source \u2192 a one-line pointer, never an invented example. false = never add API examples."
+      ),
+      screenshots: external_exports.boolean().default(false).describe(
+        "Screenshots for frontend changes. false (default) = never attempt. true = attempt when the host has browser/preview tooling and the diff touches a frontend surface; capability-gated (emits a one-line note and leaves the placeholder when tooling is absent, never fails or blocks the PR). Before/after + changed-region highlighting is best-effort."
+      ),
+      ui_paths: external_exports.array(external_exports.string()).default([]).describe(
+        'Optional glob list that makes frontend detection explicit instead of heuristic (e.g. ["resources/views/**", "src/pages/**"]). Empty (default) = a light path/extension heuristic that fails open (no false enrichment when the surface is ambiguous).'
+      ),
+      api_paths: external_exports.array(external_exports.string()).default([]).describe(
+        'Optional glob list that makes API-endpoint detection explicit instead of heuristic (e.g. ["app/Http/Controllers/Api/**", "src/pages/api/**"]). Empty (default) = a light path/extension heuristic that fails open.'
       )
     })
   }),
@@ -18387,7 +18405,7 @@ function _detect_legacy_for_migration(project_root) {
     }
     return [];
   }
-  if (isFile(path11.join(project_root, CONSUMER_BRIDGE_MARKER_RELPATH))) return [];
+  if (isFile(path11.join(project_root, INSTALL_MODE_MARKER_REL))) return [];
   const found = [];
   for (const name of MIGRATE_LEGACY_YAML_FILES) {
     if (isFile(path11.join(project_root, name))) {
@@ -18446,26 +18464,17 @@ function _format_global_root_for_marker(global_root) {
   }
   return `~/${rel.split(path11.sep).join("/")}`;
 }
-function _write_consumer_bridge_marker(project_root, installer_version, env = null, now = null) {
+function _remove_legacy_consumer_bridge_marker(project_root, env = null) {
   const env_map = env ?? process3.env;
   if (env_map["AGENT_CONFIG_DEV_MODE"] === "1") return null;
   if (isDir(path11.join(project_root, ".agent-src.uncondensed"))) return null;
-  const global_root_str = _format_global_root_for_marker(
-    event4u_root(env_map)
-  );
-  const stamp = utcStamp(now ?? void 0);
-  const body = `# event4u/agent-config \u2014 consumer bridge marker (auto-written).
-# Spec: docs/contracts/consumer-bridge.md (event4u-bridge/v1).
-# Reader contract: expand ~ against the current $HOME; fail closed
-# when global_root is missing on disk; never write back through it.
-schema: event4u-bridge/v1
-global_root: ${global_root_str}
-installed_at: ${stamp}
-installer_version: ${installer_version}
-`;
   const target = path11.join(project_root, CONSUMER_BRIDGE_MARKER_RELPATH);
-  mkdirp(path11.dirname(target));
-  atomicWrite0644(target, body, ".event4u-bridge.");
+  if (!isFile(target)) return null;
+  try {
+    fs13.rmSync(target);
+  } catch {
+    return null;
+  }
   return target;
 }
 var PROJECT_ANCHOR_TOOLS = {
@@ -18487,14 +18496,13 @@ function _write_per_tool_project_anchors(project_root, tools, env = null, now =
     if (!tools.has(tool_id)) continue;
     const target = path11.join(project_root, rel_path);
     mkdirp(path11.dirname(target));
-    const bridge_abs = path11.join(project_root, CONSUMER_BRIDGE_MARKER_RELPATH);
-    const bridge_rel = path11.relative(path11.dirname(target), bridge_abs);
     const body = `# event4u/agent-config \u2014 per-tool project anchor (auto-written).
 # Spec: docs/contracts/consumer-bridge.md \xA7 Per-tool anchor strategy.
-# Tool: ${tool_id}. Bridge marker: agents/.event4u-bridge.yml.
+# Tool: ${tool_id}. Resolves the global install directly \u2014 no
+# project-local bridge marker (retired, ADR-020 amendment 2026-07-13).
+# This anchor is gitignored: each developer regenerates it on install.
 schema: event4u-bridge/v1
 tool: ${tool_id}
-bridge: ${bridge_rel}
 global_root: ${global_root_str}
 installed_at: ${stamp}
 `;
@@ -19067,10 +19075,10 @@ function install_global(tools, force, project_root = null, core_only = false) {
     const files_by_tool = _files_by_tool_from_deploy(deploy_results);
     const rc = _update_installed_tools_manifest(project_root, tools, "global", force, files_by_tool);
     if (rc !== 0) return rc;
-    const marker_path = _write_consumer_bridge_marker(project_root, installed_version);
-    if (marker_path !== null && !state.QUIET) {
-      const rel = isRelativeTo(marker_path, project_root) ? path11.relative(project_root, marker_path) : marker_path;
-      info(`Bridge marker written: ${rel}`);
+    const removed_marker = _remove_legacy_consumer_bridge_marker(project_root);
+    if (removed_marker !== null && !state.QUIET) {
+      const rel = isRelativeTo(removed_marker, project_root) ? path11.relative(project_root, removed_marker) : removed_marker;
+      info(`Removed legacy bridge marker: ${rel}`);
     }
     const anchor_paths = _write_per_tool_project_anchors(project_root, tools);
     if (anchor_paths.length > 0 && !state.QUIET) {
@@ -19423,11 +19431,10 @@ personal:
       success(`Wrote ${SETTINGS_FILE} (user_type=${user_type})`);
     }
   }
-  const installed_version = current_package_version();
-  const marker_path = _write_consumer_bridge_marker(target_root, installed_version);
-  if (marker_path !== null) {
-    const rel = isRelativeTo(marker_path, target_root) ? path11.relative(target_root, marker_path) : marker_path;
-    success(`Wrote ${rel}`);
+  const removed_marker = _remove_legacy_consumer_bridge_marker(target_root);
+  if (removed_marker !== null) {
+    const rel = isRelativeTo(removed_marker, target_root) ? path11.relative(target_root, removed_marker) : removed_marker;
+    success(`Removed legacy bridge marker: ${rel}`);
   }
   _write_install_mode_marker(target_root, "minimal");
   if (!state.QUIET) {

package/dist/mcp/registry-manifest.json

@@ -1,15 +1,15 @@
 {
   "discovery": {
-    "artefact_count": 563,
+    "artefact_count": 565,
     "scanner_version": "c24312e116f8"
   },
-  "generated_at": "2026-07-13",
+  "generated_at": "2026-07-14",
   "package": {
     "description": "Universal AI Agent OS \u2014 audited skills, governance rules, commands, and templates for AI coding tools (Claude Code, Cursor, Windsurf, Copilot).",
     "homepage": "https://event4u-app.github.io/agent-config",
     "name": "@event4u/agent-config",
     "repository": "https://github.com/event4u-app/agent-config",
-    "version": "9.0.0"
+    "version": "9.1.0"
   },
   "registries": [
     {

package/dist/scripts/_lib/agent_settings.js

@@ -213,7 +213,10 @@ const _AGENTS_DIR_MARKERS = [
     'roadmaps',
     'settings/.ai-council.yml',
     'roadmaps-progress.md',
-    '.event4u-bridge.yml',
+    // `overrides/` is the guaranteed minimal-consumer surface (ADR-020).
+    // Replaced the retired `.event4u-bridge.yml` marker (ADR-020 amendment
+    // 2026-07-13) so a bare consumer `agents/` dir stays anchorable.
+    'overrides',
 ];
 /**
  * Kill-switch (D5). When set to `"1"`, `find_project_root` /