@event4u/agent-config 5.6.0 → 5.7.0

package/.agent-src/skills/prediction-pool-optimizer/reference/ev-fixtures.md

@@ -0,0 +1,80 @@
+# EV fixtures — known-good rules + odds → tip
+
+Sanity-check fixtures for `prediction-pool-optimizer` Step "Self-check". Each
+fixture states a scoring rule, the (de-vigged) market probabilities, and
+the expected-points-maximizing tip. If your method disagrees with a
+fixture, your method is wrong — find the error before shipping a tip.
+
+These are illustrative, not exhaustive. Add fixtures for any pool rule
+shape you encounter so future runs catch the same class of drift.
+
+---
+
+## Fixture 1 — standard fixed points, goal "place well"
+
+**Rule:** exact result = 4, goal-difference = 3, tendency = 2, else 0.
+No quote rule. No strategy limit. Goal: place well.
+
+**Match (football):** de-vigged market — Home 62% / Draw 24% / Away 14%.
+Most plausible exact results (Poisson on market xG ≈ 1.7 : 0.8):
+2:1 ≈ 9%, 1:0 ≈ 9%, 2:0 ≈ 8%, 1:1 ≈ 8%, 3:1 ≈ 6%.
+
+**Reasoning:** the single most likely *result* (2:1) and 1:0 both bank the
+tendency (2) on a home win plus goal-difference (3) on many neighbours.
+Expected points of "2:1" beats "tip the favourite to win 3:0" (lower hit
+rate on diff/exact) and beats any draw/away tip (tendency rarely banks).
+
+**Known-good tip:** **2:1 home.** (Risk: low.) **Not** contrarian — under
+fixed points only your own tip scores, so deviating costs EV.
+
+---
+
+## Fixture 2 — quote / rarity scoring
+
+**Rule:** points = base × rarity multiplier (rarer correct tips score
+more); tendency still banks a small base.
+
+**Match (football):** same probabilities as Fixture 1.
+
+**Reasoning:** the rarity multiplier can make a plausible-but-uncommon
+exact result (e.g. 3:1, 2:2) outscore the modal 2:1 when
+`payout(result) × P(result)` is higher. Compute EV per candidate including
+the multiplier; take the max.
+
+**Known-good tip:** the result with the highest `multiplier × probability`,
+**not** the highest probability — typically a step rarer than 2:1
+(e.g. 3:1 or 2:2 depending on the multiplier curve). (Risk: medium.)
+
+---
+
+## Fixture 3 — large pool, goal "win it"
+
+**Rule:** standard fixed points. Pool N = 400. You are outside the top 20%.
+
+**Match (football):** a near-coin-flip favourite, Home 52% / Draw 26% /
+Away 22%.
+
+**Reasoning:** with N ≥ 100 and you behind, pure EV converges with the
+field and cannot create the gap you need. Add field-relative variance on a
+*subset*: take a plausible underdog/draw where the consensus is heavy on
+the favourite, sized by a rough Kelly fraction. On safe matches, still
+tip EV-max.
+
+**Known-good tip:** EV-max on the safe matches; **calculated underdog**
+(e.g. 1:1 or away) on 2–4 high-consensus matches to manufacture upside.
+(Risk: high — intentional.)
+
+---
+
+## Fixture 4 — basketball, no draws
+
+**Rule:** correct winner = 3, correct margin bucket = +2.
+
+**Match (basketball):** market spread Home −6.5, moneyline Home 78%.
+Margin modelled Gaussian, mean ≈ 6.5, sd ≈ 11.
+
+**Reasoning:** no draw term exists; optimize winner first (Home banks 3 at
+78%), then the margin bucket from the Gaussian (most mass straddles the
+spread). Tip the winner plus the modal margin bucket.
+
+**Known-good tip:** **Home win, margin ~5–9.** (Risk: low on winner.)

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

@@ -6,7 +6,7 @@ settings.
 
 ## File format
 
-**YAML**, with a single top-level scalar (`cost_profile`) plus one level of
+**YAML**, with a single top-level scalar (`rule_loading_tier`) plus one level of
 grouped sections (`personal`, `project`, `github`, `eloquent`, `pipelines`,
 `subagents`). Comments with `#`.
 
@@ -57,7 +57,7 @@ made by the user directly or by the agent on request, following the
 #            highest token cost. Pick this when working on agent-config
 #            itself or when you need every behavioural rule active.
 # custom   = ignore profile — every matrix value must be set explicitly.
-cost_profile: balanced
+rule_loading_tier: balanced
 
 # --- Personal preferences ---
 personal:
@@ -132,7 +132,7 @@ eloquent:
 # agent session can be resumed. See scripts/chat_history.py for the API.
 #
 # Defaults below are placeholders — scripts/install.py substitutes them
-# per cost_profile (see config/profiles/*.ini).
+# per rule_loading_tier (see config/profiles/*.ini).
 chat_history:
   # Log chat events to disk (true, false)
   enabled: true
@@ -199,7 +199,7 @@ pipelines:
   # Skill improvement pipeline (true, false)
   # true  = after meaningful tasks, propose learning capture and improvements (default)
   # false = silent, no post-task analysis
-  # Included by every cost_profile except `custom`.
+  # Included by every rule_loading_tier except `custom`.
   skill_improvement: true
 
 # --- Roadmap execution ---
@@ -460,7 +460,7 @@ the canonical narrative lives in
 
 | Key path | Values | Default | Description |
 |---|---|---|---|
-| `cost_profile` | `minimal`, `balanced`, `full`, `custom` | `minimal` | Selects which agent surfaces are active. See [Cost profiles](#cost-profiles). |
+| `rule_loading_tier` | `minimal`, `balanced`, `full`, `custom` | `minimal` | Selects which agent surfaces are active. See [Cost profiles](#cost-profiles). |
 | `personal.ide` | `code`, `phpstorm`, `cursor` | _(empty)_ | CLI command to open files in the IDE |
 | `personal.open_edited_files` | `true`, `false` | `false` | Auto-open edited files in the IDE after edits |
 | `personal.user_name` | first name | _(empty)_ | User's first name, used to address the user personally. Captured by `/onboard`. |
@@ -527,7 +527,7 @@ Applied automatically when `scripts/install` finds a legacy `.agent-settings`
 
 | Legacy flat key | New YAML path |
 |---|---|
-| `cost_profile` | `cost_profile` |
+| `rule_loading_tier` | `rule_loading_tier` |
 | `ide` | `personal.ide` |
 | `open_edited_files` | `personal.open_edited_files` |
 | `user_name` | `personal.user_name` |
@@ -550,7 +550,7 @@ so nothing is silently dropped; the migration log points them out.
 
 ## Cost profiles
 
-The `cost_profile` setting selects which agent surfaces are active. See
+The `rule_loading_tier` setting selects which agent surfaces are active. See
 `docs/customization.md` for the authoritative description.
 
 | Profile | Description |

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

@@ -7,7 +7,7 @@
 # Precedence (lowest → highest):
 #   1. Package defaults (shipped by event4u/agent-config)
 #   2. ~/.event4u/agent-config/agent-settings.yml — user-global DX-comfort
-#      defaults (whitelist: name, ide, cost_profile, personal.bot_icon,
+#      defaults (whitelist: name, ide, rule_loading_tier, personal.bot_icon,
 #      personal.autonomy, telegraph.speak_scope). Created on opt-in via
 #      /onboard; project-local files always win. Legacy
 #      ~/.config/agent-config/agent-settings.yml is read as a fallback.
@@ -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.py (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "4.3.0"
+agent_config_version: "5.6.1"
 
 # --- Project identity ---
 project:

package/.agent-src/templates/scripts/work_engine/_lib/agent_settings.py

@@ -100,7 +100,8 @@ def _resolve_user_global_file() -> Path:
 MERGEABLE_KEYS: tuple[str, ...] = (
     "name",
     "ide",
-    "cost_profile",
+    "rule_loading_tier",
+    "memory.cadence",
     "personal.bot_icon",
     "personal.autonomy",
     "telegraph.speak_scope",

package/.agent-src/templates/scripts/work_engine/hook_bootstrap.py

@@ -64,7 +64,7 @@ def _build_hook_registry(args: argparse.Namespace) -> HookRegistry:
         gate_hook.register(registry)
     if settings.memory_visibility:
         MemoryVisibilityHook(
-            cost_profile=settings.cost_profile,
+            memory_cadence=settings.memory_cadence,
             visibility_off=settings.memory_visibility_off,
         ).register(registry)
     if settings.chat_history_enabled:

package/.agent-src/templates/scripts/work_engine/hooks/builtin/memory_visibility.py

@@ -43,10 +43,12 @@ class MemoryVisibilityHook:
 
     Parameters
     ----------
-    cost_profile:
-        Cadence profile from ``.agent-settings.yml`` (``lean`` /
-        ``standard`` / ``verbose``). ``lean`` suppresses the line
-        unless ``asks ≥ 3`` per the contract's cadence table.
+    memory_cadence:
+        Cadence from ``memory.cadence`` in ``.agent-settings.yml``
+        (``auto`` / ``always`` / ``never``). ``auto`` suppresses the
+        line unless ``asks ≥ 3``; ``never`` suppresses it entirely;
+        ``always`` (default) emits whenever ``asks ≥ 1`` per the
+        contract's cadence table.
     visibility_off:
         When ``True``, the hook stays silent — used to mirror
         ``memory.visibility: off`` in the consumer settings.
@@ -59,11 +61,11 @@ class MemoryVisibilityHook:
     def __init__(
         self,
         *,
-        cost_profile: str = "standard",
+        memory_cadence: str = "always",
         visibility_off: bool = False,
         asked_types: Iterable[str] | None = None,
     ) -> None:
-        self._cost_profile = cost_profile
+        self._memory_cadence = memory_cadence
         self._visibility_off = visibility_off
         self._asked_types = (
             tuple(asked_types) if asked_types is not None else DEFAULT_ASKED_TYPES
@@ -81,7 +83,7 @@ class MemoryVisibilityHook:
         summary = summarise_visibility(memory, asked_types=self._asked_types)
         if not should_emit(
             summary,
-            cost_profile=self._cost_profile,
+            memory_cadence=self._memory_cadence,
             visibility_off=self._visibility_off,
         ):
             return

package/.agent-src/templates/scripts/work_engine/hooks/settings.py

@@ -16,7 +16,7 @@ settings.py``):
 
 Per road-to-portable-dev-preferences P3, the YAML read goes through
 :func:`work_engine._lib.agent_settings.load_agent_settings`, which
-cascades the whitelisted ``cost_profile`` (and other DX-comfort keys)
+cascades the whitelisted ``rule_loading_tier`` (and other DX-comfort keys)
 from ``~/.event4u/agent-config/agent-settings.yml`` (legacy
 ``~/.config/agent-config/agent-settings.yml`` read as fallback) when
 the project file omits them. Project values always win.
@@ -61,7 +61,7 @@ class HookSettings:
     decision_trace: bool = False
     memory_visibility: bool = False
     memory_visibility_off: bool = False
-    cost_profile: str = "standard"
+    memory_cadence: str = "always"
     chat_history_enabled: bool = False
     chat_history_script: str = DEFAULT_CHAT_HISTORY_SCRIPT
     decision_engine: DecisionEngineSettings = DecisionEngineSettings()
@@ -82,8 +82,8 @@ def load_hook_settings(
     ``~/.event4u/agent-config/agent-settings.yml`` (with a read fallback
     to the legacy ``~/.config/agent-config/agent-settings.yml``) and
     only cascades the whitelisted DX-comfort keys (currently
-    ``cost_profile``) when the project file omits them. See
-    road-to-portable-dev-preferences P3.
+    ``rule_loading_tier`` and ``memory.cadence``) when the project file
+    omits them. See road-to-portable-dev-preferences P3.
     """
     path = Path(settings_path) if settings_path else Path(DEFAULT_SETTINGS_FILE)
     raw = load_agent_settings(
@@ -133,12 +133,16 @@ def _settings_from_raw(data: dict[str, Any]) -> HookSettings:
 
     memory_section = data.get("memory")
     visibility_off = False
+    memory_cadence = "always"
     if isinstance(memory_section, dict):
         raw = memory_section.get("visibility")
         if isinstance(raw, str) and raw.strip().lower() == "off":
             visibility_off = True
         elif isinstance(raw, bool) and raw is False:
             visibility_off = True
+        cadence_raw = memory_section.get("cadence")
+        if cadence_raw is not None:
+            memory_cadence = str(cadence_raw).strip().lower() or "always"
 
     memory_hooks = hooks.get("memory_visibility")
     if isinstance(memory_hooks, dict):
@@ -148,11 +152,6 @@ def _settings_from_raw(data: dict[str, Any]) -> HookSettings:
     else:
         memory_visibility_on = True
 
-    cost_profile_raw = data.get("cost_profile") or "standard"
-    cost_profile = (
-        str(cost_profile_raw).strip().lower() or "standard"
-    )
-
     return HookSettings(
         enabled=True,
         trace=_coerce_bool(hooks.get("trace"), False),
@@ -168,7 +167,7 @@ def _settings_from_raw(data: dict[str, Any]) -> HookSettings:
         decision_trace=decision_trace_on,
         memory_visibility=memory_visibility_on,
         memory_visibility_off=visibility_off,
-        cost_profile=cost_profile,
+        memory_cadence=memory_cadence,
         chat_history_enabled=chat_block_enabled and global_chat_on,
         chat_history_script=chat_script,
         decision_engine=decision_engine_settings,

package/.agent-src/templates/scripts/work_engine/scoring/memory_visibility.py

@@ -242,17 +242,30 @@ def format_changed_decisions_block(
 def should_emit(
     summary: dict[str, Any],
     *,
-    cost_profile: str = "standard",
+    memory_cadence: str = "always",
     visibility_off: bool = False,
 ) -> bool:
-    """Apply the cadence + opt-out gates from the contract."""
+    """Apply the cadence + opt-out gates from the contract.
+
+    ``memory_cadence`` is the ``memory.cadence`` cadence key:
+
+    * ``always`` (default) — emit whenever ``asks >= 1``.
+    * ``auto`` — emit only when ``asks >= 3`` (reduces noise on
+      shallow-retrieval steps).
+    * ``never`` — suppress the line entirely.
+
+    ``visibility_off`` is the legacy ``memory.visibility: off`` master
+    switch and still wins over any ``memory_cadence`` value.
+    """
     if visibility_off:
         return False
     asks = int(summary.get("asks", 0) or 0)
     if asks <= 0:
         return False
-    profile = (cost_profile or "standard").strip().lower()
-    if profile == "lean":
+    status = (memory_cadence or "always").strip().lower()
+    if status == "never":
+        return False
+    if status == "auto":
         return asks >= 3
     return True
 

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Shared agent configuration \u2014 skills for AI coding tools (Claude Code, Augment, Cursor, Cline, Windsurf, Gemini CLI).",
-    "version": "5.6.0",
+    "version": "5.7.0",
     "keywords": [
       "agent-config",
       "skills",
@@ -292,6 +292,8 @@
         "./.claude/skills/post-as",
         "./.claude/skills/post-as-ghostwriter",
         "./.claude/skills/post-as-me",
+        "./.claude/skills/prediction-pool",
+        "./.claude/skills/prediction-pool-optimizer",
         "./.claude/skills/prepare-for-review",
         "./.claude/skills/privacy-review",
         "./.claude/skills/project-analysis-core",

package/CHANGELOG.md

@@ -811,6 +811,63 @@ our recommendation order, not its support status.
 > that forces a new era split (`# Era: 5.5.x`, etc.) — see
 > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
+## [5.7.0](https://github.com/event4u-app/agent-config/compare/5.6.1...5.7.0) (2026-06-01)
+
+### Features
+
+* **settings:** enum-validate value-bearing settings keys in CI ([b6c56d0](https://github.com/event4u-app/agent-config/commit/b6c56d088b1b8cfa549374e864bb3dcc203972fb))
+* **value:** honest eager-vs-thin cost ladder in the value dashboard ([9a806c4](https://github.com/event4u-app/agent-config/commit/9a806c466e171f8a83e743990bc9350192745da5))
+* **fun:** add /tippspiel command + tippspiel-optimizer skill in new pack-fun ([4c8fc65](https://github.com/event4u-app/agent-config/commit/4c8fc65473556ce3635a6fdcad67096c0c15886f))
+* **skills:** add skill-composition graph + co-availability gate (roadmap 3.4) ([6db3afa](https://github.com/event4u-app/agent-config/commit/6db3afa8738331c2e85fb1f75dceb9943b2a2599))
+
+### Bug Fixes
+
+* **install:** hand off global install to the browser wizard with zero terminal prompts ([0fc46e3](https://github.com/event4u-app/agent-config/commit/0fc46e3e29220bcebfe6c97316309502ee2b7ee4))
+* **wizard:** disambiguate the rule-loading / budget / model step ([122244c](https://github.com/event4u-app/agent-config/commit/122244c859b0c9da61e60a58fa220fb6c8f699d1))
+* **cost-report:** recommend the model tier before rule loading ([2545c27](https://github.com/event4u-app/agent-config/commit/2545c277e5cc930a1e493dbf78e3ef3fe11933aa))
+* **condense:** quote frontmatter descriptions in cursor/windsurf rules ([c69c9bb](https://github.com/event4u-app/agent-config/commit/c69c9bbb56bce9c01284db90936fd7b432278ffb))
+* **install:** always overwrite our own deployed files, drop foreign-file gate ([25b593d](https://github.com/event4u-app/agent-config/commit/25b593d96da87e61f29844db088b01a346d07d81))
+* **ci:** mirror memory.cadence into the source loader + TS settings schema ([2a74eff](https://github.com/event4u-app/agent-config/commit/2a74eff244c76830745c9d1e319d6abd5fe1d80b))
+* **memory:** give the visibility-line cadence its own memory.cadence key ([e792390](https://github.com/event4u-app/agent-config/commit/e792390f59b01190769cba1f369bb574c83847bd))
+* **rules:** trim non-destructive description to the 190-char schema cap ([b2a489e](https://github.com/event4u-app/agent-config/commit/b2a489ecf9fcbadf5232417f2503fddbab657fdb))
+* **rules:** make production-branch commits a Hard-Floor opt-in (kernel) ([31f49a9](https://github.com/event4u-app/agent-config/commit/31f49a9af7fc0fb495556e8570e0adbfcb031416))
+* **discovery:** register 'fun' in discovery-manifest schema enum ([7b91f12](https://github.com/event4u-app/agent-config/commit/7b91f12fa4e1e805a121a0fd7c9adb2760f5f122))
+
+### Documentation
+
+* **install:** record ADR-036 + roadmap Phase 6 for the browser-wizard handoff ([f3cc886](https://github.com/event4u-app/agent-config/commit/f3cc886618526b1c705a2a25c1ee98eb4063a188))
+* **roadmap:** close + archive cost_profile untangle (phases 0-7; 4 items cancelled-with-follow-up) ([296b0da](https://github.com/event4u-app/agent-config/commit/296b0da47fc0ceed399438e4c5cb5801df0ea1b7))
+* record cost_profile untangle (ADR-036 + BREAKING_CHANGES + disambiguation) ([efa658a](https://github.com/event4u-app/agent-config/commit/efa658acaef31bb1d1a9ddb565b5093b03f7d62e))
+* **roadmap:** add cost_profile untangle roadmap ([708033c](https://github.com/event4u-app/agent-config/commit/708033cb5649c1d9583ea42a397795cf198b3493))
+
+### Refactoring
+
+* **settings:** rename cost_profile to rule_loading_tier across the suite ([21a31cb](https://github.com/event4u-app/agent-config/commit/21a31cb9746996324e9a49d82ad87084fb605c87))
+* **fun:** English command name + expanded triggers ([62c960e](https://github.com/event4u-app/agent-config/commit/62c960eac79cdbc2883ac4727fe05d651f9497b8))
+
+### Chores
+
+* update agent work ([7ed0cbb](https://github.com/event4u-app/agent-config/commit/7ed0cbbe45e33757f8fa59048d6f9212110da8c1))
+* sync agent-project-settings example pin to package.json (5.6.1) ([194a040](https://github.com/event4u-app/agent-config/commit/194a040628b21c2f61b1096f956f350eed131ec6))
+* regenerate index + catalog after rename ([1c6dc68](https://github.com/event4u-app/agent-config/commit/1c6dc68416570f47bf8578d60c508f0acd185993))
+* regenerate derived trees after merging main ([1f0ad58](https://github.com/event4u-app/agent-config/commit/1f0ad582d9a757acafd470d1fdd32adc362a2a49))
+* regenerate derived trees for the prediction-pool rename ([bb3225f](https://github.com/event4u-app/agent-config/commit/bb3225fa91e78bfa640d33d501175b586cbd7de7))
+* regenerate derived trees for pack-fun ([4125ba5](https://github.com/event4u-app/agent-config/commit/4125ba583cadd25ec29c23999287fc42fcc3d991))
+* update condensation hashes after requires_skills frontmatter ([baf60e5](https://github.com/event4u-app/agent-config/commit/baf60e58328051176a519628dd56f879a5c4dd86))
+* **roadmap:** re-examine lean-buildout disposition — 3.4 built, rest confirmed ([d88b633](https://github.com/event4u-app/agent-config/commit/d88b6332181013dc1757c317453519cadee3f63a))
+* **roadmap:** close + archive lean-buildout roadmap (council-resolved) ([303ca6b](https://github.com/event4u-app/agent-config/commit/303ca6b6346298601fb789d08d003e023ab26ac4))
+
+Tests: 5375 (+0 since 5.6.1)
+
+## [5.6.1](https://github.com/event4u-app/agent-config/compare/5.6.0...5.6.1) (2026-06-01)
+
+### Bug Fixes
+
+* **mcp:** send bearer auth in post-deploy smoke probe ([9d12489](https://github.com/event4u-app/agent-config/commit/9d124894b03e5e962e8014171f965ce9367de58d))
+* correct gzip kwarg in pack_mcp_content (condenselevel -> compresslevel) ([6d27677](https://github.com/event4u-app/agent-config/commit/6d2767736d6d20327a5853875fd4e9cb172babcc))
+
+Tests: 5375 (+0 since 5.6.0)
+
 ## [5.6.0](https://github.com/event4u-app/agent-config/compare/5.5.0...5.6.0) (2026-05-31)
 
 ### Features

package/README.md

@@ -4,7 +4,7 @@
 
 [![Smoke](https://github.com/event4u-app/agent-config/actions/workflows/smoke.yml/badge.svg)](https://github.com/event4u-app/agent-config/actions/workflows/smoke.yml) [![Public install smoke (3 OS × 2 Node)](https://github.com/event4u-app/agent-config/actions/workflows/smoke-public-install.yml/badge.svg)](https://github.com/event4u-app/agent-config/actions/workflows/smoke-public-install.yml) [![npm](https://img.shields.io/npm/v/@event4u/agent-config?style=flat-square&label=npm&color=orange)](https://www.npmjs.com/package/@event4u/agent-config)
 
-[![Skills](https://img.shields.io/badge/Skills-222-orange?style=flat-square)](.agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-79-orange?style=flat-square)](.agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-145-orange?style=flat-square)](.agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-73-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-24-orange?style=flat-square)](.agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](.agent-src/personas/advisors/)
+[![Skills](https://img.shields.io/badge/Skills-223-orange?style=flat-square)](.agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-79-orange?style=flat-square)](.agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-146-orange?style=flat-square)](.agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-73-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-24-orange?style=flat-square)](.agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](.agent-src/personas/advisors/)
 
 > **The Universal AI Agent OS for Founders, Content Creators, Consultants, Sales, Finance, and Engineering teams. Bring your own AI provider.**
 
@@ -369,7 +369,7 @@ When a prompt matches a command's purpose ("setze ticket ABC-123 um" → `/imple
 | [**Migration**](docs/MIGRATION.md) | Per-version upgrade steps |
 | [**Showcase**](docs/showcase.md) | More examples & expected behavior |
 
-Browse content: [all 145 commands](.agent-src/commands/) · [skills catalog](docs/skills-catalog.md) · [full catalog](docs/catalog.md) · [`llms.txt`](llms.txt).
+Browse content: [all 146 commands](.agent-src/commands/) · [skills catalog](docs/skills-catalog.md) · [full catalog](docs/catalog.md) · [`llms.txt`](llms.txt).
 
 ---
 

package/config/agent-settings.template.yml

@@ -28,7 +28,7 @@ agent_config_version: ""
 # balanced = kernel + tier-1 auto-rules (default — current behaviour superset).
 # full     = kernel + tier-1 + tier-2 (everything, highest token cost).
 # custom   = ignore profile — every matrix value must be set explicitly.
-cost_profile: __COST_PROFILE__
+rule_loading_tier: __RULE_LOADING_TIER__
 
 # --- Lean projection (experimental, opt-in) ---
 #
@@ -220,7 +220,7 @@ pipelines:
   # Skill improvement pipeline (true, false)
   # true  = after meaningful tasks, propose learning capture and improvements (default)
   # false = silent, no post-task analysis
-  # Included by every cost_profile except `custom`. Flip to false here if you
+  # Included by every rule_loading_tier except `custom`. Flip to false here if you
   # want a silent agent; `custom` profile ignores this default entirely.
   skill_improvement: true
 
@@ -429,6 +429,15 @@ commands:
 # docs/contracts/agent-memory-contract.md for the on-disk shape and
 # .augment/skills/memory-consolidation/ for the four-phase loop.
 memory:
+  # Cadence for the "🧠 Memory: <hits>/<asks>" visibility line emitted
+  # after a memory-consulting step (see docs/contracts/memory-visibility-v1.md).
+  #   always = (default) emit whenever at least one memory type was asked.
+  #   auto   = emit only when ≥ 3 memory types were consulted (less noise
+  #            on shallow-retrieval steps).
+  #   never  = suppress the line entirely.
+  # The legacy `memory.visibility: off` master switch still wins over this.
+  cadence: always
+
   # Inline-review threshold for /memory load.
   # When the unreviewed intake stream contains more than this many
   # entries, /memory load surfaces a top-3 preview block before the

package/config/discovery/packs.yml

@@ -79,6 +79,7 @@
   label: Product Basic
   description: Core PO/PM artefacts (ticket refinement, AC, estimation).
   workspaces: [product]
+  requires_hint: [engineering-base]
   trust_level_default: professional
 
 - id: product-discovery
@@ -163,6 +164,16 @@
     example_workflow: scene-expander
     time_to_first_value_minutes: 12
 
+- id: fun
+  label: Fun
+  description: Non-essential social/fun workflows (prediction-pool tips, etc.).
+  workspaces: [small-business]
+  trust_level_default: experimental
+  onboarding:
+    first_win_doc: FIRST_WIN.md
+    example_workflow: prediction-pool-optimizer
+    time_to_first_value_minutes: 6
+
 - id: meta
   label: Meta
   description: Artefacts that maintain this package (agent-config itself).

package/config/discovery/workspaces.yml

@@ -55,7 +55,7 @@
   description: Self-employed / SMB-shaped owner workflows.
   example_roles: [Owner, Freelancer]
   default_packs: [small-business]
-  optional_packs: [ai-video]
+  optional_packs: [ai-video, fun]
 
 - id: construction
   label: Construction

package/config/profiles/balanced.ini

@@ -7,7 +7,7 @@
 ; a shell command can be invoked via scripts/runtime_dispatcher.py.
 ; See docs/customization.md for the full profile description.
 
-cost_profile=balanced
+rule_loading_tier=balanced
 
 ; Chat history (crash recovery) — balanced = phase-level traceability
 chat_history_frequency=per_phase

package/config/profiles/full.ini

@@ -7,7 +7,7 @@
 ; read-only and opt-in per call. See docs/customization.md for the full
 ; profile description.
 
-cost_profile=full
+rule_loading_tier=full
 
 ; Chat history (crash recovery) — full = tool-level traceability + summarize on overflow
 chat_history_frequency=per_tool

package/config/profiles/minimal.ini

@@ -7,7 +7,7 @@
 ; profile description. scripts/install.py merges this file with
 ; config/agent-settings.template.ini to produce the user's .agent-settings.
 
-cost_profile=minimal
+rule_loading_tier=minimal
 
 ; Chat history (crash recovery) — minimal = lightest footprint
 chat_history_frequency=per_turn

package/dist/discovery/deprecation-report.md

@@ -1,6 +1,6 @@
 # Discovery — Deprecation Report
 
-- Generated: `2026-05-31T21:27:24Z`
+- Generated: `2026-06-01T14:03:17Z`
 - Deprecated artefacts: **0**
 
 _None. Tree is clean._