@event4u/agent-config 5.6.1 → 5.8.0

package/docs/getting-started.md

@@ -146,7 +146,7 @@ The system supports four configuration profiles:
 Set your profile in `.agent-settings.yml`:
 
 ```yaml
-cost_profile: balanced
+rule_loading_tier: balanced
 ```
 
 `balanced` is the default — kernel + tier-1 auto-rules. Rationale:
@@ -169,7 +169,7 @@ Your agent now understands slash commands:
 | `/quality-fix` | Run and fix all quality checks |
 | `/chat-history` | Inspect the persistent chat-history log (read-only `show`) |
 
-→ [Browse all 145 active commands](../.agent-src/commands/)
+→ [Browse all 150 active commands](../.agent-src/commands/)
 
 ---
 

package/docs/guidelines/agent-infra/layered-settings.md

@@ -18,8 +18,14 @@ on user request.
 | File | Git | Scope | Owner | Example values |
 |---|---|---|---|---|
 | `.agent-project-settings.yml` | **committed** | team / repo | lead maintainer | `project.stack`, `quality.php.tools`, `memory.dogfood` |
-| `~/.event4u/agent-config/agent-settings.yml` | **n/a** (outside repo) | individual developer · cross-project | individual | `name`, `ide`, `cost_profile`, `personal.bot_icon`, `personal.autonomy`, `telegraph.speak_scope` (legacy `~/.config/agent-config/agent-settings.yml` read as fallback) |
-| `.agent-settings.yml` | **gitignored** | individual developer · this project | individual | `personal.ide`, `personal.user_name`, `subagents.max_parallel`, `onboarding.onboarded` |
+| `~/.event4u/agent-config/agent-settings.yml` | **n/a** (outside repo) | individual developer · cross-project | individual | `name`, `ide`, `rule_loading_tier`, `personal.bot_icon`, `personal.autonomy`, `telegraph.speak_scope` (legacy `~/.config/agent-config/agent-settings.yml` read as fallback) |
+| `agents/settings/.agent-settings.yml` | **gitignored** | individual developer · this project | individual | `personal.ide`, `personal.user_name`, `subagents.max_parallel`, `onboarding.onboarded` |
+
+> **Canonical location (ADR-038):** the developer file lives in the settings
+> layer at `agents/settings/.agent-settings.yml` (alongside
+> `.agent-settings.local.yml`, `contexts/`, `policies/`). A repo-root
+> `.agent-settings.yml` is read as a **back-compat fallback** and is migrated
+> into the canonical location by `install` on the next run.
 
 All three are YAML. Schemas:
 
@@ -36,7 +42,7 @@ Lowest priority → highest priority:
 1. Package defaults                                   (shipped by event4u/agent-config)
 2. ~/.event4u/agent-config/agent-settings.yml         (user-global · whitelist-filtered · legacy ~/.config/agent-config/ read as fallback)
 3. .agent-project-settings.yml                        (team file, committed)
-4. .agent-settings.yml                                (developer file, gitignored)
+4. agents/settings/.agent-settings.yml                (developer file, gitignored; legacy repo-root .agent-settings.yml read as fallback — ADR-038)
 ```
 
 Keys from higher layers win unless a lower layer marks them
@@ -52,7 +58,7 @@ intentionally tiny — adding a key requires an ADR.
 ```
 name
 ide
-cost_profile
+rule_loading_tier
 personal.bot_icon
 personal.autonomy
 telegraph.speak_scope

package/docs/installation.md

@@ -303,7 +303,7 @@ explicitly by adding `agent_config_version: <semver>` to
 The orchestrator chains payload sync and bridge generation:
 
 ```bash
-bash scripts/install                  # defaults to cost_profile=balanced
+bash scripts/install                  # defaults to rule_loading_tier=balanced
 bash scripts/install --profile=minimal
 bash scripts/install --force          # overwrite existing bridges
 bash scripts/install --skip-bridges   # payload only
@@ -359,7 +359,7 @@ regardless of which AI tool they use.** No per-developer plugin installation nee
 After initial setup, commit these files:
 
 ```
-.agent-settings.yml                ← shared profile (e.g., cost_profile: balanced)
+.agent-settings.yml                ← shared profile (e.g., rule_loading_tier: balanced)
 agents/installed-tools.lock        ← AI bill of materials (ADR-008, Phase 3)
 .augment/                          ← rules, skills, commands (symlinks)
 .cursor/rules/                     ← Cursor rules (symlinks)
@@ -589,7 +589,7 @@ The system works immediately with sensible defaults. Optionally, create `.agent-
 to choose a profile:
 
 ```yaml
-cost_profile: balanced
+rule_loading_tier: balanced
 ```
 
 | Profile | What's active | For whom |

package/docs/setup/mcp-client-config.md

@@ -33,7 +33,7 @@ look for MCP server config inside `.agent-settings.yml`.
 | File | Where | Who reads it | Purpose |
 |---|---|---|---|
 | MCP client config (this page) | client-specific path per section above | the MCP client at startup | which MCP servers to talk to (name + URL / command) |
-| `.agent-settings.yml` | consumer project root (`<repo>/.agent-settings.yml`) | the agent at runtime (Claude / Cursor / …) | per-developer preferences: `name`, `ide`, `cost_profile`, `personal.autonomy`, `pipelines.skill_improvement`, `telegraph.speak_scope`, … |
+| `.agent-settings.yml` | consumer project root (`<repo>/.agent-settings.yml`) | the agent at runtime (Claude / Cursor / …) | per-developer preferences: `name`, `ide`, `rule_loading_tier`, `personal.autonomy`, `pipelines.skill_improvement`, `telegraph.speak_scope`, … |
 
 The Worker is **stateless** and **project-agnostic** — it serves the
 same skill / rule / command catalog to every client. Personalization

package/docs/skills-catalog.md

@@ -1,6 +1,6 @@
 # Skills Catalog
 
-All **219 skills** available in this package, in alphabetical order.
+All **223 skills** available in this package, in alphabetical order.
 Click a skill name to open its SKILL.md and read the full guidance.
 
 > **Regenerate:** `python3 scripts/generate_catalog.py`
@@ -89,6 +89,8 @@ Click a skill name to open its SKILL.md and read the full guidance.
 | [`gtm-launch`](../.agent-src/skills/gtm-launch/SKILL.md) | Use when sequencing a launch — alpha / beta / GA waves, audience-by-wave logic, narrative beats per wave, engineering-readiness gates. Triggers on 'plan the launch', 'sequence GA'. |
 | [`guideline-writing`](../.agent-src/skills/guideline-writing/SKILL.md) | Use when creating or editing a guideline in docs/guidelines/ — reference material cited by skills, no auto-triggers — even when the user just says 'write up our naming conventions'. |
 | [`hiring-loop-design`](../.agent-src/skills/hiring-loop-design/SKILL.md) | Use when shaping an engineering hiring loop — stages, take-home vs live, calibration, bar-raiser, signal-vs-noise audit. Triggers on 'design our interview loop', 'audit our hiring bar'. |
+| [`image-analyser`](../.agent-src/skills/image-analyser/SKILL.md) | Use to analyse a character image down to the smallest mole and diff against a canon — per-feature spec, OCR-reads tattoo text, flags drift. Triggers 'analyse this image', 'match the canon'. |
+| [`image-creator`](../.agent-src/skills/image-creator/SKILL.md) | Use to generate a character image to spec — max-fidelity reproducible prompt from a Canon Spec, anchors-first, provider/governance-gated. Triggers 'generate this character', 'render to spec'. |
 | [`incident-commander`](../.agent-src/skills/incident-commander/SKILL.md) | Use during or right after an incident — frames severity, sets comms cadence, drafts the post-mortem skeleton — even when the user just says 'production is down' or 'wir haben einen Vorfall'. |
 | [`jira-integration`](../.agent-src/skills/jira-integration/SKILL.md) | Use when the user says "check Jira", "create ticket", "update issue", or needs JQL queries, ticket transitions, or branch-to-ticket linking. |
 | [`jobs-events`](../.agent-src/skills/jobs-events/SKILL.md) | Use when creating Laravel jobs, queued workflows, events, or listeners. Covers clear responsibilities, safe serialization, and retry/failure handling. |
@@ -152,6 +154,7 @@ Click a skill name to open its SKILL.md and read the full guidance.
 | [`playwright-testing`](../.agent-src/skills/playwright-testing/SKILL.md) | Use when writing Playwright E2E tests — browser automation, visual regression testing, Page Objects, fixtures, and reliable test patterns. |
 | [`po-discovery`](../.agent-src/skills/po-discovery/SKILL.md) | Use when shaping a fuzzy product ask into a refined backlog item — problem framing, user-story rewrite, AC tightening — even if the user just says 'help me write this ticket'. |
 | [`positioning-strategy`](../.agent-src/skills/positioning-strategy/SKILL.md) | Use when locking the market frame — category, segment, alternative, point-of-view — before messaging, launch, or pricing rides on it. Triggers on 'who are we for', 'opposable audit'. |
+| [`prediction-pool-optimizer`](../.agent-src/skills/prediction-pool-optimizer/SKILL.md) | Optimize prediction-pool tips (kicktipp etc.): rules + multi-book consensus odds → expected-points-max answer for every question, scores AND bonus. Triggers 'optimize my pool tips', 'predict'. |
 | [`privacy-review`](../.agent-src/skills/privacy-review/SKILL.md) | Use when reviewing data flows, support macros, refund templates for GDPR/CCPA/HIPAA fit — regime, consent, PII redaction (email, order-id), breach triage. Triggers 'is this GDPR-safe', 'PII redact'. |
 | [`project-analysis-core`](../.agent-src/skills/project-analysis-core/SKILL.md) | Raw discovery primitives — project discovery, version resolution, docs loading, architecture mapping, execution flow. Called by `universal-project-analysis`. Single-pass scan → `project-analyzer`. |
 | [`project-analysis-hypothesis-driven`](../.agent-src/skills/project-analysis-hypothesis-driven/SKILL.md) | Use when a bug has multiple plausible causes across layers — competing hypotheses, validation loops, evidence-based conclusions — even when the user just says 'why is this happening?'. |
@@ -199,6 +202,7 @@ Click a skill name to open its SKILL.md and read the full guidance.
 | [`skill-management`](../.agent-src/skills/skill-management/SKILL.md) | Use when condensing, decondenseing, refactoring, or improving existing skills. Covers the full skill lifecycle from verbose → sharp → maintained. |
 | [`skill-reviewer`](../.agent-src/skills/skill-reviewer/SKILL.md) | Use when reviewing, auditing, or optimizing skills — validates against the 7 Skill Killers checklist and produces fix recommendations. |
 | [`skill-writing`](../.agent-src/skills/skill-writing/SKILL.md) | Use when deciding 'should this be a skill or a rule?', creating/improving/reviewing agent skills, SKILL.md frontmatter, or procedure sections — even without saying 'skill-writing'. |
+| [`song-to-script`](../.agent-src/skills/song-to-script/SKILL.md) | Turn an audio track into a timed `## Scene N` script: song sections → per-scene durations, auto mode adds mood + lip-sync lines. Triggers 'music video', 'from the song', 'cut to the beat'. |
 | [`sql-writing`](../.agent-src/skills/sql-writing/SKILL.md) | Use when writing raw SQL — MariaDB/MySQL syntax, parameterization, raw migrations, seeders with `DB::statement` — even when the user just pastes a query and asks 'why is this slow' without naming SQL. |
 | [`stakeholder-tradeoff`](../.agent-src/skills/stakeholder-tradeoff/SKILL.md) | Use when stakeholders pull a decision in different directions — frames each lens, builds a trade-off matrix, surfaces the cost of every choice — even if the user just says 'PO and ops disagree'. |
 | [`subagent-orchestration`](../.agent-src/skills/subagent-orchestration/SKILL.md) | Use when orchestrating implementer/judge subagents — seven modes (do-and-judge ±two-stage, do-in-steps/parallel/worktrees, do-competitively, judge-with-debate) — models from .agent-settings.yml. |

package/docs/value.md

@@ -23,15 +23,17 @@ Liest sich von oben nach unten. Positive Δ-Werte = das Paket *kostet* Tokens (R
 | Stufe | Was sie tut | Δ Tokens | Kumulativ | Quelle |
 |---|---|---:|---:|---|
 | **Ohne Paket / Without package** | Baseline — der nackte Request ohne Paket-Regeln. | +0 | +0.00% | `n/a` · ✅ gemessen |
-| Mit Paket (Regeln laden) / With package (rule load) | Die immer-aktiven Regeln landen im Kontext jedes Requests. ⚠️ erst teurer | +8 522 | +106.53% | `dist/router.json` · ✅ gemessen |
-| | _Fußnote:_ Kernel = 10 rules (30080 chars) + charter (4010 chars); tokens ≈ chars / 4. | | | |
-| + condense (Regeln eindampfen) / + condense (rule shrink) | Build-Schritt schrumpft Regel-Dateien vor dem Ausliefern. | -186 | +104.20% | `internal/bench/reports/telegraph-v2.json` · ✅ gemessen |
+| Mit Paket (Regeln laden) / With package (rule load) | Die immer-aktiven Regeln landen im Kontext jedes Requests. ⚠️ erst teurer | +59 359 | +741.99% | `internal/bench/reports/projection-cost.json` · ✅ gemessen |
+| | _Fußnote:_ Eager-Default: alle 79 Rule-Files always-on im `.claude`-Projektionspfad (0B.6-bestätigt fürs primäre Tool). Nicht nur der Kernel — das ist die ehrliche Up-Front-Last; tokens ≈ chars / 4. | | | |
+| + thin (Regeln als Pointer) / + thin (rules as pointers) | Nicht-Kernel-Regel-Bodies werden zu router-aufgelösten Pointern. | -45 857 | +741.99% | `internal/bench/reports/projection-cost.json` · 🔁 verfügbar (Default aus) |
+| | _Fußnote:_ Verfügbar hinter `lean_projection.mode=thin` (Default `eager-all` — deshalb NICHT im Default-NETTO). Mit Thin aktiv: Rule-Layer 59359 → 13502 GPT tok (−45857, −77.3%). MUST-LOAD-Floor `task trigger-coverage` 26/26 grün; Live-A/B-Validierung ausstehend (Harness abgelehnt). Rollback = ein Flip. | | | |
+| + condense (Regeln eindampfen) / + condense (rule shrink) | Build-Schritt schrumpft Regel-Dateien vor dem Ausliefern. | -186 | +739.66% | `internal/bench/reports/telegraph-v2.json` · ✅ gemessen |
 | | _Fußnote:_ Aggregate across non-Thin-Root categories; Thin-Root files (AGENTS.md variants) net negative (~−4%) and are excluded from the rung — surfaced separately. | | | |
-| + rtk (CLI-Output filtern) / + rtk (filter CLI output) | rtk schneidet verbose CLI-Ausgabe vor dem Modell-Input weg. | -593 | +96.79% | `internal/bench/reports/rtk/latest.json` · ✅ gemessen |
-| + terse (Antworten knapper) / + terse (shorter replies) | Telegraph-Stil zielt auf knappere Modell-Antworten. | +56 | +97.49% | `internal/bench/reports/telegraph-v1.json` · ✅ gemessen |
+| + rtk (CLI-Output filtern) / + rtk (filter CLI output) | rtk schneidet verbose CLI-Ausgabe vor dem Modell-Input weg. | -585 | +732.35% | `internal/bench/reports/rtk/latest.json` · ✅ gemessen |
+| + terse (Antworten knapper) / + terse (shorter replies) | Telegraph-Stil zielt auf knappere Modell-Antworten. | +56 | +733.05% | `internal/bench/reports/telegraph-v1.json` · ✅ gemessen |
 | | _Fußnote:_ Honest: gemessener Median = -9.27% gegen 'sei knapp' — Telegraph liefert hier mehr Tokens, nicht weniger. Wir messen, wir verstecken nicht. | | | |
 
-**NETTO: Mehrkosten** ⚠️ — **+7 799 Tokens / Request**, kumulativ **+97.49%** vs. Baseline.
+**NETTO: Mehrkosten** ⚠️ — **+58 644 Tokens / Request**, kumulativ **+733.05%** vs. Baseline.
 
 ## Panel B — Verhalten (mit vs. ohne)
 
@@ -81,4 +83,4 @@ Diese Seite ist eine **abgeleitete** Sicht — keine eigene Messung. Sie fasst d
 - Pending rungs contribute 0 to the cumulative until measured.
 - Reference scale: 1000 requests × 8000 input / 600 output tokens per request.
 
-_Last rendered: `2026-05-31T14:37:17+00:00`_
+_Last rendered: `2026-06-01T12:10:59+00:00`_

package/docs/wizard.md

@@ -33,7 +33,7 @@ selects which surface renders.
 |---|---|---|
 | 1 | Identity | `personal.user_name`, `personal.ide` |
 | 2 | Personality | `personal.minimal_output`, `personal.play_by_play`, `personal.open_edited_files` |
-| 3 | Cost profile | `cost_profile` (minimal · balanced · full) |
+| 3 | Cost profile | `rule_loading_tier` (minimal · balanced · full) |
 | 4 | Roadmap quality | `roadmap.quality_floor`, `roadmap.run_tests_inline` |
 | 5 | Memory | `memory.enabled`, MCP server presence |
 | 6 | `.agent-user.md` | Optional long-form persona / preferences |

package/llms.txt

@@ -87,6 +87,8 @@ grafana: Use when working with Grafana — dashboards, Loki LogQL queries, alert
 gtm-launch: Use when sequencing a launch — alpha / beta / GA waves, audience-by-wave logic, narrative beats per wave, engineering-readiness gates. Triggers on 'plan the launch', 'sequence GA'.
 guideline-writing: Use when creating or editing a guideline in docs/guidelines/ — reference material cited by skills, no auto-triggers — even when the user just says 'write up our naming conventions'.
 hiring-loop-design: Use when shaping an engineering hiring loop — stages, take-home vs live, calibration, bar-raiser, signal-vs-noise audit. Triggers on 'design our interview loop', 'audit our hiring bar'.
+image-analyser: Use to analyse a character image down to the smallest mole and diff against a canon — per-feature spec, OCR-reads tattoo text, flags drift. Triggers 'analyse this image', 'match the canon'.
+image-creator: Use to generate a character image to spec — max-fidelity reproducible prompt from a Canon Spec, anchors-first, provider/governance-gated. Triggers 'generate this character', 'render to spec'.
 incident-commander: Use during or right after an incident — frames severity, sets comms cadence, drafts the post-mortem skeleton — even when the user just says 'production is down' or 'wir haben einen Vorfall'.
 jira-integration: Use when the user says "check Jira", "create ticket", "update issue", or needs JQL queries, ticket transitions, or branch-to-ticket linking.
 jobs-events: Use when creating Laravel jobs, queued workflows, events, or listeners. Covers clear responsibilities, safe serialization, and retry/failure handling.
@@ -150,6 +152,7 @@ playwright-architect: Use when shaping a Playwright suite — locator strategy,
 playwright-testing: Use when writing Playwright E2E tests — browser automation, visual regression testing, Page Objects, fixtures, and reliable test patterns.
 po-discovery: Use when shaping a fuzzy product ask into a refined backlog item — problem framing, user-story rewrite, AC tightening — even if the user just says 'help me write this ticket'.
 positioning-strategy: Use when locking the market frame — category, segment, alternative, point-of-view — before messaging, launch, or pricing rides on it. Triggers on 'who are we for', 'opposable audit'.
+prediction-pool-optimizer: Optimize prediction-pool tips (kicktipp etc.): rules + multi-book consensus odds → expected-points-max answer for every question, scores AND bonus. Triggers 'optimize my pool tips', 'predict'.
 privacy-review: Use when reviewing data flows, support macros, refund templates for GDPR/CCPA/HIPAA fit — regime, consent, PII redaction (email, order-id), breach triage. Triggers 'is this GDPR-safe', 'PII redact'.
 project-analysis-core: Raw discovery primitives — project discovery, version resolution, docs loading, architecture mapping, execution flow. Called by `universal-project-analysis`. Single-pass scan → `project-analyzer`.
 project-analysis-hypothesis-driven: Use when a bug has multiple plausible causes across layers — competing hypotheses, validation loops, evidence-based conclusions — even when the user just says 'why is this happening?'.
@@ -197,6 +200,7 @@ skill-improvement-pipeline: ONLY when user explicitly requests: run the skill im
 skill-management: Use when condensing, decondenseing, refactoring, or improving existing skills. Covers the full skill lifecycle from verbose → sharp → maintained.
 skill-reviewer: Use when reviewing, auditing, or optimizing skills — validates against the 7 Skill Killers checklist and produces fix recommendations.
 skill-writing: Use when deciding 'should this be a skill or a rule?', creating/improving/reviewing agent skills, SKILL.md frontmatter, or procedure sections — even without saying 'skill-writing'.
+song-to-script: Turn an audio track into a timed `## Scene N` script: song sections → per-scene durations, auto mode adds mood + lip-sync lines. Triggers 'music video', 'from the song', 'cut to the beat'.
 sql-writing: Use when writing raw SQL — MariaDB/MySQL syntax, parameterization, raw migrations, seeders with `DB::statement` — even when the user just pastes a query and asks 'why is this slow' without naming SQL.
 stakeholder-tradeoff: Use when stakeholders pull a decision in different directions — frames each lens, builds a trade-off matrix, surfaces the cost of every choice — even if the user just says 'PO and ops disagree'.
 subagent-orchestration: Use when orchestrating implementer/judge subagents — seven modes (do-and-judge ±two-stage, do-in-steps/parallel/worktrees, do-competitively, judge-with-debate) — models from .agent-settings.yml.

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@event4u/agent-config",
-    "version": "5.6.1",
+    "version": "5.8.0",
     "description": "Universal AI Agent OS \u2014 audited skills, governance rules, commands, and templates for AI coding tools (Claude Code, Cursor, Windsurf, Copilot).",
     "license": "MIT",
     "private": false,

package/scripts/_cli/cmd_doctor.py

@@ -55,6 +55,7 @@ from scripts._lib.agent_settings import (
     ROOT_OVERRIDE_ENV,
     ProjectRootError,
     find_project_root_with_trace,
+    project_settings_path,
     resolve_project_root,
 )
 
@@ -131,7 +132,7 @@ def _settings_layer_chain(project_root: Path) -> list[str]:
     user_global = user_global_paths.resolve_with_fallback("agent-settings.yml")
     if user_global is not None and user_global.is_file():
         layers.append(str(user_global))
-    project_settings = project_root / ".agent-settings.yml"
+    project_settings = project_settings_path(project_root)
     if project_settings.is_file():
         layers.append(str(project_settings))
     return layers
@@ -778,7 +779,7 @@ def _check_tier_usage_readiness(project_root: Path) -> dict[str, Any]:
 
     Contract: ``docs/contracts/command-clusters.md`` § tier-usage signal.
     """
-    settings_file = project_root / ".agent-settings.yml"
+    settings_file = project_settings_path(project_root)
     log_path = project_root / ".agent-tier-usage.jsonl"
     enabled = False
     if settings_file.is_file():

package/scripts/_cli/cmd_explain.py

@@ -262,7 +262,7 @@ makes network calls. Output is the ExplainTrace v1 contract:
 
 why-slots answered (Markdown sections; JSON keys in parens):
 
-  inputs       — profile / preset / cost_profile with per-knob source
+  inputs       — profile / preset / rule_loading_tier with per-knob source
                  (pack | profile | preset | user | env | runtime |
                   default)
   route        — matched tier-1 rules · kernel rules · active persona

package/scripts/_cli/cmd_versions.py

@@ -18,7 +18,7 @@ import subprocess
 import sys
 from pathlib import Path
 
-from scripts._lib.agent_settings import resolve_project_root
+from scripts._lib.agent_settings import project_settings_path, resolve_project_root
 
 PACKAGE_NAME = "@event4u/agent-config"
 
@@ -51,7 +51,7 @@ def _local_package_version() -> str:
 
 def _pinned_version() -> str:
     """Return the ``agent_config_version`` pin from ``.agent-settings.yml``."""
-    settings = _project_root() / ".agent-settings.yml"
+    settings = project_settings_path(_project_root())
     if not settings.exists():
         return ""
     try:

package/scripts/_cli/explain_last/inputs.py

@@ -16,7 +16,7 @@ from scripts._cli.explain_last.scrubber import scrub_string
 from scripts._lib.agent_settings import DEFAULT_PROJECT_FILE, load_agent_settings
 from scripts.config import presets, profiles
 
-_DEFAULT_COST_PROFILE = "balanced"
+_DEFAULT_RULE_LOADING_TIER = "balanced"
 _SILENCED_LOGGERS = ("scripts.config.profiles", "scripts.config.presets")
 
 
@@ -65,19 +65,22 @@ def build(project_root: Path) -> dict[str, Any] | None:
             )
     except (profiles.ProfileError, presets.PresetError, OSError):
         return None
-    cost_profile = settings.get("cost_profile") if isinstance(settings, dict) else None
-    cost_profile_source = "user" if cost_profile else "default"
-    if not cost_profile or cost_profile == "__COST_PROFILE__":
-        cost_profile = _DEFAULT_COST_PROFILE
-        cost_profile_source = "default"
+    rule_loading_tier = (
+        (settings.get("rule_loading_tier") or settings.get("cost_profile"))
+        if isinstance(settings, dict) else None
+    )
+    rule_loading_tier_source = "user" if rule_loading_tier else "default"
+    if not rule_loading_tier or rule_loading_tier == "__RULE_LOADING_TIER__":
+        rule_loading_tier = _DEFAULT_RULE_LOADING_TIER
+        rule_loading_tier_source = "default"
     return {
         "profile": scrub_string(resolved_profile.id),
         "preset": scrub_string(resolved_preset.id),
-        "cost_profile": scrub_string(str(cost_profile)),
+        "rule_loading_tier": scrub_string(str(rule_loading_tier)),
         "source_per_knob": {
             "profile": resolved_profile.source,
             "preset": resolved_preset.source,
-            "cost_profile": cost_profile_source,
+            "rule_loading_tier": rule_loading_tier_source,
         },
     }
 

package/scripts/_cli/explain_last/sections/inputs.py

@@ -15,7 +15,7 @@ def render(trace: dict[str, Any]) -> str:
     rows = [
         ("profile.id", inputs.get("profile"), sources.get("profile")),
         ("preset.id", inputs.get("preset"), sources.get("preset")),
-        ("cost_profile", inputs.get("cost_profile"), sources.get("cost_profile")),
+        ("rule_loading_tier", inputs.get("rule_loading_tier"), sources.get("rule_loading_tier")),
     ]
     out.append("| knob | value | source |")
     out.append("|---|---|---|")

package/scripts/_lib/agent_settings.py

@@ -76,6 +76,45 @@ def _local_settings_path(project_root: Path) -> Path:
     return project_root.joinpath(*LOCAL_PROJECT_SUBDIR, LOCAL_PROJECT_FILE)
 
 
+def _canonical_settings_path(project_root: Path) -> Path:
+    """Canonical project settings file: ``<root>/agents/settings/.agent-settings.yml``.
+
+    The project settings file lives in the project's settings layer
+    (``agents/settings/``, alongside ``contexts/`` and ``policies/`` and
+    the ``.agent-settings.local.yml`` override), NOT at the repo root.
+    The repo-root ``.agent-settings.yml`` is a legacy location read only
+    as a back-compat fallback (see :func:`project_settings_path`).
+    """
+    return project_root.joinpath(*LOCAL_PROJECT_SUBDIR, DEFAULT_PROJECT_FILE)
+
+
+def project_settings_path(project_root: Path) -> Path:
+    """Resolve the project settings file for **reading**.
+
+    Returns the canonical ``agents/settings/.agent-settings.yml`` when it
+    exists; otherwise the legacy repo-root ``.agent-settings.yml`` when
+    that exists (back-compat for installs predating the relocation);
+    otherwise the canonical path (so the caller still names the right
+    target on a fresh repo). Existence-checked, never writes.
+    """
+    canonical = _canonical_settings_path(project_root)
+    if canonical.exists():
+        return canonical
+    legacy = project_root / DEFAULT_PROJECT_FILE
+    if legacy.exists():
+        return legacy
+    return canonical
+
+
+def canonical_settings_write_path(project_root: Path) -> Path:
+    """Always the canonical **write** target: ``agents/settings/.agent-settings.yml``.
+
+    Writers (install, sync, migrate) target this unconditionally; the
+    legacy root file is migrated into it, never written afresh.
+    """
+    return _canonical_settings_path(project_root)
+
+
 DEFAULT_TEAM_FILE = ".agent-project-settings.yml"
 USER_GLOBAL_FILENAME = "agent-settings.yml"
 
@@ -100,7 +139,8 @@ 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",
@@ -430,12 +470,14 @@ def _resolve_cascade_paths(
     """
     if cwd is None:
         legacy = Path(project_path) if project_path else Path(DEFAULT_PROJECT_FILE)
-        return [legacy, _local_settings_path(legacy.parent)]
+        return [legacy, _canonical_settings_path(legacy.parent),
+                _local_settings_path(legacy.parent)]
 
     root = find_project_root(cwd)
     if root is None:
         legacy = Path(project_path) if project_path else Path(DEFAULT_PROJECT_FILE)
-        return [legacy, _local_settings_path(legacy.parent)]
+        return [legacy, _canonical_settings_path(legacy.parent),
+                _local_settings_path(legacy.parent)]
 
     cwd_resolved = cwd.resolve()
     # Build the chain root → … → cwd (shallowest first, deepest last).
@@ -450,9 +492,15 @@ def _resolve_cascade_paths(
             break
         cursor = parent
     chain.reverse()
-    # Committed cascade root → cwd, then the single project-level local override
-    # under agents/settings/ as the deepest (winning) layer.
-    return [d / DEFAULT_PROJECT_FILE for d in chain] + [_local_settings_path(root)]
+    # Legacy per-dir cascade root → cwd (repo-root .agent-settings.yml is the
+    # shallowest, back-compat), then the canonical project settings file under
+    # agents/settings/ (wins over the legacy root location), then the
+    # per-machine local override under agents/settings/ as the deepest (winning)
+    # layer.
+    return (
+        [d / DEFAULT_PROJECT_FILE for d in chain]
+        + [_canonical_settings_path(root), _local_settings_path(root)]
+    )
 
 
 def load_agent_settings(

package/scripts/_lib/agent_src.py

@@ -30,6 +30,7 @@ from typing import Iterator
 ROOT = Path(__file__).resolve().parents[2]
 LEGACY_SRC = ROOT / ".agent-src.uncondensed"
 PACKAGES = ROOT / "packages"
+PACKAGE_CORE = PACKAGES / "core"
 
 # Repo-relative POSIX path prefixes that anchor an artefact source tree.
 # Order: legacy first (kept until the move lands), then packages/*. Each
@@ -155,3 +156,32 @@ def strip_source_prefix(rel: str) -> str | None:
 def is_artefact_path(rel: str) -> bool:
     """``True`` if a repo-relative POSIX path sits under any source root."""
     return strip_source_prefix(rel) is not None
+
+
+def resolve_package_core_path(relative_target: str) -> Path:
+    """Return the canonical ``packages/core/<relative_target>`` path.
+
+    The single resolution point for every gate that enforces something
+    against a fixed ``packages/core/`` target. A future move of the
+    ``packages/core/`` tree updates :data:`PACKAGE_CORE` here — one
+    resolver — instead of N hard-coded ``REPO_ROOT / "packages" / "core"``
+    constants scattered across gate scripts (the ``aab5755`` silent-no-op
+    class this eliminates).
+
+    Pure resolver: deterministic, **no filesystem I/O**. ``agent_src`` is
+    imported by scanners that must stay usable in the legacy-only and
+    pack-only layouts (see :func:`artefact_roots`), so this MUST NOT
+    assert existence at import or call time — a packages/core existence
+    check here would break those layouts. Callers that need existence
+    check it themselves; ``scripts/check_gate_paths.py`` is the single
+    gate that asserts the enforced targets resolve under ``packages/core/``.
+
+    Examples:
+        ``resolve_package_core_path(".agent-src.uncondensed")``
+            → ``<repo>/packages/core/.agent-src.uncondensed``
+        ``resolve_package_core_path(".agent-src.uncondensed/commands")``
+            → ``<repo>/packages/core/.agent-src.uncondensed/commands``
+        ``resolve_package_core_path("")`` → ``<repo>/packages/core``
+    """
+    rel = relative_target.replace("\\", "/").lstrip("/")
+    return PACKAGE_CORE / rel if rel else PACKAGE_CORE

package/scripts/_lib/value_ladder.py

@@ -35,6 +35,13 @@ DEFAULT_REFERENCE_SCALE = {
     "model_tier": "sonnet",
 }
 
+# Confidence levels that contribute to the cumulative / NETTO headline.
+# `pending` (not yet measured) and `available` (measured but behind a
+# default-off kill-switch, e.g. the thin projection) are shown with their
+# token_delta but excluded from the default cumulative — the headline must
+# reflect what actually ships by default.
+_COUNTING_CONFIDENCES = ("measured", "estimated", "vendor-claim")
+
 # ── Pricing ─────────────────────────────────────────────────────────────
 
 
@@ -228,6 +235,96 @@ def load_rung_from_frugality(
     }
 
 
+def load_rung_from_projection(
+    projection: Optional[Dict[str, Any]],
+    reference_scale: Dict[str, Any],
+    pricing_row: Dict[str, Any],
+    tool: str = ".claude",
+) -> Optional[Dict[str, Any]]:
+    """Build the load rung from the REAL eager always-on footprint.
+
+    Phase 3.1 honesty fix: the older `load_rung_from_router` counts only the
+    kernel + charter (~8.5k tok), modelling non-kernel rules as on-demand.
+    But 0B.6 confirmed the primary tool **eager-loads every rule body**
+    (~59k tok always-on). This rung reads that measured footprint from
+    `internal/bench/reports/projection-cost.json::rule_footprint[<tool>]`
+    so Panel A reflects what actually lands in context per request.
+
+    Returns None when the projection report lacks the footprint, so the
+    caller can fall back to the router/frugality rung.
+    """
+    rf = (projection or {}).get("rule_footprint", {})
+    entry = rf.get(tool) or next(iter(rf.values()), None)
+    if not entry or "tokens_gpt" not in entry:
+        return None
+    token_delta = int(entry["tokens_gpt"])
+    files = int(entry.get("files", 0))
+    return {
+        "id": "load",
+        "label": "Mit Paket (Regeln laden) / With package (rule load)",
+        "what_it_does": "Die immer-aktiven Regeln landen im Kontext jedes Requests.",
+        "token_delta": token_delta,
+        "eur_delta": price_input_delta_eur(token_delta, reference_scale, pricing_row),
+        "cumulative_pct": 0.0,
+        "confidence": "measured",
+        "source_report": "internal/bench/reports/projection-cost.json",
+        "footnote": (
+            f"Eager-Default: alle {files} Rule-Files always-on im "
+            f"`{tool}`-Projektionspfad (0B.6-bestätigt fürs primäre Tool). "
+            "Nicht nur der Kernel — das ist die ehrliche Up-Front-Last; "
+            "tokens ≈ chars / 4."
+        ),
+    }
+
+
+def thin_rung_from_projection(
+    projection: Optional[Dict[str, Any]],
+    reference_scale: Dict[str, Any],
+    pricing_row: Dict[str, Any],
+) -> Dict[str, Any]:
+    """Build the thin-projection rung (Phase 3.1 lever).
+
+    The thin projection keeps the kernel full-bodied and demotes every
+    non-kernel rule body to a router-resolved pointer, measured at
+    −`saved_gpt` tokens. It ships **behind a kill-switch**
+    (`lean_projection.mode`, default `eager-all`), so this rung is
+    `confidence: available` — its measured delta is shown but does NOT
+    enter the default cumulative (the default reality is eager). The
+    footnote states the would-be always-on total and the validation state.
+    """
+    tp = (projection or {}).get("thin_projection", {})
+    if not tp or "saved_gpt" not in tp:
+        return pending_rung(
+            "thin",
+            "+ thin (Regeln als Pointer) / + thin (rules as pointers)",
+            "Nicht-Kernel-Regel-Bodies werden zu router-aufgelösten Pointern.",
+            "internal/bench/reports/projection-cost.json",
+            footnote="Run scripts/project_thin_rules.py --measure to populate.",
+        )
+    saved = int(tp["saved_gpt"])
+    thin_total = int(tp.get("thin_gpt", 0))
+    eager_total = int(tp.get("eager_gpt", 0))
+    pct = tp.get("saved_pct", 0)
+    return {
+        "id": "thin",
+        "label": "+ thin (Regeln als Pointer) / + thin (rules as pointers)",
+        "what_it_does": "Nicht-Kernel-Regel-Bodies werden zu router-aufgelösten Pointern.",
+        "token_delta": -saved,
+        "eur_delta": price_input_delta_eur(-saved, reference_scale, pricing_row),
+        "cumulative_pct": 0.0,
+        "confidence": "available",
+        "source_report": "internal/bench/reports/projection-cost.json",
+        "footnote": (
+            f"Verfügbar hinter `lean_projection.mode=thin` (Default `eager-all` "
+            f"— deshalb NICHT im Default-NETTO). Mit Thin aktiv: Rule-Layer "
+            f"{eager_total} → {thin_total} GPT tok (−{saved}, −{pct}%). "
+            "MUST-LOAD-Floor `task trigger-coverage` 26/26 grün; "
+            "Live-A/B-Validierung ausstehend (Harness abgelehnt). "
+            "Rollback = ein Flip."
+        ),
+    }
+
+
 def condense_rung_from_telegraph_v2(
     telegraph_v2: Optional[Dict[str, Any]],
     baseline_input_tokens: int,
@@ -551,7 +648,7 @@ def assemble_ladder(
         rung_copy = dict(rung)
         delta = (
             int(rung_copy.get("token_delta", 0))
-            if rung_copy.get("confidence") != "pending"
+            if rung_copy.get("confidence") in _COUNTING_CONFIDENCES
             else 0
         )
         running += delta
@@ -575,7 +672,7 @@ def compute_totals(
     cumulative_token_delta = sum(
         int(r.get("token_delta", 0))
         for r in rungs
-        if r.get("confidence") != "pending"
+        if r.get("confidence") in _COUNTING_CONFIDENCES
     )
     cumulative_pct = 0.0
     if baseline_input_tokens > 0: