@event4u/agent-config 3.3.0 → 4.2.0

package/.agent-src/commands/video/storyboard.md

@@ -43,7 +43,7 @@ diff.
 ### 1. Validate dependencies
 
 ```bash
-scripts/ai-video/lib/validate-deps.sh .agent-src.uncompressed/commands/video/storyboard.md
+scripts/ai-video/lib/validate-deps.sh .agent-src.uncondensed/commands/video/storyboard.md
 ```
 
 ### 2. Load config + resolve image provider

package/.agent-src/commands/video.md

@@ -63,7 +63,7 @@ contract under [`scripts/ai-video/lib/adapter-contract.md`](../scripts/ai-video/
 - **Run `validate-deps.sh` first.** Every subcommand calls
   `scripts/ai-video/lib/validate-deps.sh` before any adapter; fails
   fast on missing personas / skills.
-- **Edit `.agent-src.uncompressed/` only.** Generated mirrors regenerate.
+- **Edit `.agent-src.uncondensed/` only.** Generated mirrors regenerate.
 
 ## See also
 

package/.agent-src/contexts/augment-infrastructure.md

@@ -57,7 +57,7 @@ Define hard constraints: coding standards, Docker usage, language preferences, s
 |---|---|
 | `quality-workflow.md` | PHP (PHPStan → Rector → PHPStan) and JS/TS pipelines |
 | `downstream-changes.md` | After every edit, find and update ALL callers, tests, imports |
-| `augment-edit-discipline.md` | Edits inside `.augment/` / `.agent-src.uncompressed/` stay project-agnostic AND sync counts + cross-references in the same edit |
+| `augment-edit-discipline.md` | Edits inside `.augment/` / `.agent-src.uncondensed/` stay project-agnostic AND sync counts + cross-references in the same edit |
 | `context-hygiene.md` | 3-failure rule, state dumps |
 | `architecture.md` | Architecture principles, file placement |
 | `docker-commands.md` | All PHP commands run inside Docker containers |

package/.agent-src/contexts/authority/commit-mechanics.md

@@ -21,6 +21,21 @@ Outside the four below, no commit is allowed and no commit ask is allowed.
 4. **Roadmap authorization** — roadmap lists explicit commit steps and
    the user invoked roadmap execution; each commit matches a step.
 
+## Always split into logical chunks — default mandate
+
+```
+WHEN A COMMIT IS AUTHORIZED, ALWAYS SPLIT THE DIFF INTO THE
+SMALLEST LOGICAL CHUNKS THAT MAKE SENSE. NEVER ASK "EIN COMMIT
+ODER MEHRERE?", "WIE SOLL ICH SPLITTEN?", "WELCHER ZUERST?".
+THE SPLIT IS THE AGENT'S CALL, NOT THE USER'S.
+```
+
+Default shape — one chunk per concern (scope / refactor / rules / config / cleanup), in dependency order (foundation → feature → cleanup). Mixed-concern files split by hunk via `git add -p`. Generated / projected files (e.g. `.agent-src/`, `.augment/`, `.claude/`) ride with the source-of-truth chunk that produced them, not as a separate "regenerate projections" commit.
+
+The chunking decision is **never** a numbered option. Pick a sensible split, state it inline ("splitte in 3 chunks: workspace-scope · rules-hardening · gitignore-cleanup"), execute. The user retains revert / amend control after the fact — they don't need to pre-approve the chunk boundary.
+
+Carve-out — if the diff is genuinely indivisible (single hunk, single concern, single file family) → one commit, state inline. If a chunk would cross the Hard Floor below (bulk deletion / infra), surface that chunk's diff per the next section before its commit lands, not before the chunk boundary is chosen.
+
 ## Hard Floor still applies — bulk deletions and infra changes
 
 Even when one of the four `commit-policy` exceptions authorizes a

package/.agent-src/contexts/authority/kernel-rule-edits.md

@@ -2,7 +2,7 @@
 
 Loaded by [`scope-control`](../../rules/scope-control.md). Codifies the
 soak-time guarantee for edits to always-loaded (kernel) rules under
-`.agent-src.uncompressed/rules/`.
+`.agent-src.uncondensed/rules/`.
 
 **Size budget:** ≤ 1,500 chars.
 
@@ -22,7 +22,7 @@ diagnosis.
 ## Trigger
 
 A PR is a "kernel-rule edit" iff it modifies any file in
-`.agent-src.uncompressed/rules/` that is in the locked kernel set
+`.agent-src.uncondensed/rules/` that is in the locked kernel set
 (see [`docs/contracts/kernel-membership.md`](../../../docs/contracts/kernel-membership.md)).
 
 The CI guard (Phase 4.2 of the always-budget-relief roadmap) fails
@@ -43,6 +43,6 @@ records why the bundle is necessary in the PR body.
 ## Source
 
 - Roadmap Phase 4: always-budget-relief roadmap § Phase 4 (transient — see `agents/roadmaps/archive/`).
-- Lesson: PR #36 (2026-05-04) compressed the rollout schedule under
+- Lesson: PR #36 (2026-05-04) condensed the rollout schedule under
   autonomous mandate; the slow-rollout note was deferred until this
   ADR pass.

package/.agent-src/contexts/authority/scope-mechanics.md

@@ -91,7 +91,7 @@ User decides. Default: **3** when the current branch's name and scope match the
 
 **Failure mode — diverging stacked PRs.** Skipping the inventory and committing to the wrong base creates two PRs that should have been one stack: merge conflicts when the parent lands, rebase / force-push churn, duplicate review effort. The 30-second inventory cost up front beats hours of rebase reconciliation later.
 
-**Failure mode — opening a PR on a stale long-lived branch.** A pre-existing feature branch (e.g. `feat/X` last touched days ago) is still "the current branch" but its base — `main` — has moved on. Auto-generated artifacts (`agents/roadmaps-progress.md`, ownership matrices, compressed mirrors, hash files) are the canonical collision surface: any merged PR on `main` touched them, and the stale branch's copy is now a content conflict by construction. Opening a PR without fetching `main` first surfaces conflicts only after `gh pr create` has already published the broken PR.
+**Failure mode — opening a PR on a stale long-lived branch.** A pre-existing feature branch (e.g. `feat/X` last touched days ago) is still "the current branch" but its base — `main` — has moved on. Auto-generated artifacts (`agents/roadmaps-progress.md`, ownership matrices, condensed mirrors, hash files) are the canonical collision surface: any merged PR on `main` touched them, and the stale branch's copy is now a content conflict by construction. Opening a PR without fetching `main` first surfaces conflicts only after `gh pr create` has already published the broken PR.
 
 **Pre-PR freshness check — MANDATORY** (mirrored in [`/create-pr` Step 1b](../../commands/create-pr.md)). Before `gh pr create`:
 

package/.agent-src/contexts/communication/rules-auto/augment-source-of-truth-mechanics.md

@@ -1,6 +1,6 @@
 # Source of Truth — mechanics
 
-Workflow, compression rules, commands workflow, symlink mapping, and
+Workflow, condensation rules, commands workflow, symlink mapping, and
 quick reference for the
 [`augment-source-of-truth`](../../../rules/augment-source-of-truth.md)
 rule. The Iron Rule and the "never edit generated layers" obligation
@@ -9,45 +9,45 @@ when authoring or pre-review verification fires.
 
 ## Workflow
 
-1. **Create or edit** the file in `.agent-src.uncompressed/{path}`
-2. **Do NOT auto-compress.** Continue working.
-3. **Before commit/push:** Check if compression is needed
-   (`bash scripts/compress.sh --changed`). If files need compression,
+1. **Create or edit** the file in `.agent-src.uncondensed/{path}`
+2. **Do NOT auto-condense.** Continue working.
+3. **Before commit/push:** Check if condensation is needed
+   (`bash scripts/condense.sh --changed`). If files need condensation,
    ask the user:
    ```
-   > 📦 {N} .agent-src files need compression before commit.
+   > 📦 {N} .agent-src files need condensation before commit.
    >
-   > 1. Compress now — run /compress
-   > 2. Later — commit without compression
+   > 1. Condense now — run /condense
+   > 2. Later — commit without condensation
    ```
-4. If compressing: run `/compress` command, then
-   `bash scripts/compress.sh --mark-done {path}`
+4. If condensing: run `/condense` command, then
+   `bash scripts/condense.sh --mark-done {path}`
 
 For new non-.md files (`.php`, configs):
-`bash scripts/compress.sh --sync` copies them automatically.
+`bash scripts/condense.sh --sync` copies them automatically.
 
-**Key change:** Compression happens once before commit/push — not after every edit.
+**Key change:** Condensation happens once before commit/push — not after every edit.
 This avoids interruptions when work is still in progress.
 
-## What "compress" means
+## What "condense" means
 
 - Remove articles (a, an, the), filler, hedging, connective fluff
 - Shorten phrases: "in order to" → "to", "make sure to" → "ensure"
 - Fragments OK: "Run tests before commit" not "You should always run tests before committing"
 - Merge redundant bullets
 
-## What NEVER changes during compression
+## What NEVER changes during condensation
 
 - Code blocks, inline code, URLs, file paths, commands
 - Headings (exact text preserved)
-- Tables (structure preserved, compress cell text only)
+- Tables (structure preserved, condense cell text only)
 - YAML frontmatter
 - Technical terms, library names, API names
 - Strong language: "NEVER", "MUST", "Do NOT" — these are load-bearing
 
 ## Commands workflow
 
-Commands live in `.agent-src.uncompressed/commands/{name}.md` (single source of truth).
+Commands live in `.agent-src.uncondensed/commands/{name}.md` (single source of truth).
 Claude Code reads them via symlinks in `.claude/skills/{name}/SKILL.md`.
 
 **Required frontmatter for commands:**
@@ -60,14 +60,14 @@ disable-model-invocation: true
 
 - `name` and `disable-model-invocation: true` are required for Claude Code compatibility
 - Augment ignores unknown frontmatter fields — no conflict
-- Template: `.agent-src.uncompressed/templates/command.md`
+- Template: `.agent-src.uncondensed/templates/command.md`
 
 **Creating a new command:**
 
-1. Create `.agent-src.uncompressed/commands/{name}.md` (use template)
+1. Create `.agent-src.uncondensed/commands/{name}.md` (use template)
 2. Run `python3 scripts/skill_linter.py` — must be 0 FAIL
-3. Compress via `/compress`, which writes to `.agent-src/commands/`
-4. Run `python3 scripts/compress.py --generate-tools` — creates Claude symlink automatically
+3. Condense via `/condense`, which writes to `.agent-src/commands/`
+4. Run `python3 scripts/condense.py --generate-tools` — creates Claude symlink automatically
 
 **Never** create `.claude/skills/{name}/SKILL.md` manually for commands — always use the symlink workflow.
 
@@ -88,11 +88,11 @@ Commands have `disable-model-invocation: true` in their frontmatter.
 
 | Task | What to do |
 |---|---|
-| Edit existing file | Edit in `.agent-src.uncompressed/`, compress to `.agent-src/` |
-| Create new `.md` | Create in `.agent-src.uncompressed/`, compress to `.agent-src/` |
-| Create new non-`.md` | Create in `.agent-src.uncompressed/`, run `bash scripts/compress.sh --sync` |
-| Create new command | Create in `.agent-src.uncompressed/commands/`, sync, `python3 scripts/compress.py --generate-tools` |
-| Delete a file | Delete from `.agent-src.uncompressed/` and `.agent-src/` |
-| Check what needs compression | `bash scripts/compress.sh --changed` |
-| Mark file as compressed | `bash scripts/compress.sh --mark-done {path}` |
-| Verify everything is in sync | `bash scripts/compress.sh --check` |
+| Edit existing file | Edit in `.agent-src.uncondensed/`, condense to `.agent-src/` |
+| Create new `.md` | Create in `.agent-src.uncondensed/`, condense to `.agent-src/` |
+| Create new non-`.md` | Create in `.agent-src.uncondensed/`, run `bash scripts/condense.sh --sync` |
+| Create new command | Create in `.agent-src.uncondensed/commands/`, sync, `python3 scripts/condense.py --generate-tools` |
+| Delete a file | Delete from `.agent-src.uncondensed/` and `.agent-src/` |
+| Check what needs condensation | `bash scripts/condense.sh --changed` |
+| Mark file as condensed | `bash scripts/condense.sh --mark-done {path}` |
+| Verify everything is in sync | `bash scripts/condense.sh --check` |

package/.agent-src/contexts/communication/rules-auto/skill-quality-mechanics.md

@@ -1,7 +1,7 @@
 # Skill quality — mechanics
 
 Description-triggering recipe, merge-preservation invariants, and
-compression-preservation invariants for the
+condensation-preservation invariants for the
 [`skill-quality`](../../../rules/skill-quality.md) rule. The minimum
 sharpness table, required sections, frontmatter contract, the
 skill-independence Iron Law, and the refactor-safety NEVER list live
@@ -46,9 +46,9 @@ A merge is invalid if:
 - Anti-pattern coverage decreased
 - The merged skill became a generic umbrella doc
 
-## Compression Preservation
+## Condensation Preservation
 
-When compressing a skill, the compressed version MUST preserve:
+When condensing a skill, the condensed version MUST preserve:
 
 - Trigger quality (description + When to use)
 - All procedure steps that contain decisions
@@ -56,7 +56,7 @@ When compressing a skill, the compressed version MUST preserve:
 - All gotchas and anti-patterns
 - Strongest example (at minimum one good/bad contrast)
 
-Compression may remove:
+Condensation may remove:
 - Verbose explanations
 - Redundant examples (keep the strongest)
 - Commentary that doesn't affect execution

package/.agent-src/contexts/communication/rules-auto/think-before-action-mechanics.md

@@ -89,8 +89,8 @@ The editor may report that the user has a file open. Background
 context only — does NOT mean the user's message is about that file.
 
 - The user's message determines intent — not which file is open.
-- A user can have `README.md` open and type `/compress` — intent is
-  to compress, not to discuss the README.
+- A user can have `README.md` open and type `/condense` — intent is
+  to condense, not to discuss the README.
 - A user can have `UserController.php` open and ask "how do tests
   work?" — intent is testing, not the controller.
 - Treat the open file as relevant only when the user's message

package/.agent-src/contexts/contracts/artifact-engagement-flow.md

@@ -14,7 +14,7 @@ stability: beta
 
 This document is the stable reference for **what gets recorded, when, and
 under which constraints**. The roadmap tracks phased delivery; the rule
-([`artifact-engagement-recording`](../../.agent-src.uncompressed/rules/artifact-engagement-recording.md))
+([`artifact-engagement-recording`](../../.agent-src.uncondensed/rules/artifact-engagement-recording.md))
 tells the agent when to fire; this doc explains the contract every
 recording must honour.
 
@@ -55,8 +55,8 @@ refine → memory → analyze → plan → implement → test → verify → rep
 
 The setting lives at `telemetry.artifact_engagement.granularity` in
 `.agent-settings.yml`. Default `task`. Both flows
-([`/implement-ticket`](../../.agent-src.uncompressed/commands/implement-ticket.md)
-and [`/work`](../../.agent-src.uncompressed/commands/work.md)) use the
+([`/implement-ticket`](../../.agent-src.uncondensed/commands/implement-ticket.md)
+and [`/work`](../../.agent-src.uncondensed/commands/work.md)) use the
 same eight-step contract from
 [`implement-ticket-flow.md`](implement-ticket-flow.md).
 
@@ -215,7 +215,7 @@ rule listed above:
 # Validate every line against the schema + redaction floor
 python3 -c '
 import pathlib, sys
-sys.path.insert(0, ".agent-src.uncompressed/templates/scripts")
+sys.path.insert(0, ".agent-src.uncondensed/templates/scripts")
 from telemetry.engagement import EngagementSchemaError, parse_event
 log = pathlib.Path(".agent-engagement.jsonl")
 ok = bad = 0
@@ -253,7 +253,7 @@ layers reject.
 
 ## See also
 
-- [`artifact-engagement-recording`](../../.agent-src.uncompressed/rules/artifact-engagement-recording.md) — agent-side trigger
+- [`artifact-engagement-recording`](../../.agent-src.uncondensed/rules/artifact-engagement-recording.md) — agent-side trigger
 - [`implement-ticket-flow`](implement-ticket-flow.md) — the eight-step contract this rule observes
-- [`scripts/telemetry/`](../../.agent-src.uncompressed/templates/scripts/telemetry/) — schema, boundary session, settings reader
+- [`scripts/telemetry/`](../../.agent-src.uncondensed/templates/scripts/telemetry/) — schema, boundary session, settings reader
 - [`tests/telemetry/`](../../tests/telemetry/) — contract enforcement (schema, settings, aggregator, renderer, CLI, cost-floor, redaction)

package/.agent-src/contexts/contracts/command-suggestion-flow.md

@@ -5,7 +5,7 @@ stability: beta
 # Command Suggestion — Flow & Scoring Contract
 
 > Cross-cutting reference for the suggestion layer.
-> The runtime rule is [`command-suggestion`](../../.agent-src.uncompressed/rules/command-suggestion-policy.md);
+> The runtime rule is [`command-suggestion`](../../.agent-src.uncondensed/rules/command-suggestion-policy.md);
 > the architectural decision lives in [`adr-command-suggestion.md`](adr-command-suggestion.md).
 >
 > - **Created:** 2026-04-30
@@ -140,7 +140,7 @@ Cursor, Cline, Windsurf) get the engine via `scripts/`.
 
 ## See also
 
-- [`command-suggestion`](../../.agent-src.uncompressed/rules/command-suggestion-policy.md) — runtime rule
+- [`command-suggestion`](../../.agent-src.uncondensed/rules/command-suggestion-policy.md) — runtime rule
 - [`adr-command-suggestion.md`](adr-command-suggestion.md) — architectural decision
 - [`command-suggestion-eligibility.md`](command-suggestion-eligibility.md) — locked eligibility table
-- [`agent-settings`](../../.agent-src.uncompressed/templates/agent-settings.md) — `commands.suggestion.*` reference
+- [`agent-settings`](../../.agent-src.uncondensed/templates/agent-settings.md) — `commands.suggestion.*` reference

package/.agent-src/contexts/contracts/emergency-triage-block.md

@@ -2,7 +2,7 @@
 
 > Canonical content of the **Emergency Triage** block referenced by the
 > `agents-md-thin-root` skill. Both the package-root `AGENTS.md` and
-> `.agent-src.uncompressed/templates/AGENTS.md` (consumer template)
+> `.agent-src.uncondensed/templates/AGENTS.md` (consumer template)
 > embed this block verbatim. Drift is caught by the `lint-agents-md`
 > task in the package's CI pipeline.
 
@@ -19,14 +19,14 @@ Use this variant in `AGENTS.md` at the package root.
 
 1. **What is this repo?** — `event4u/agent-config`, a governed skill / rule / command suite for AI coding tools (no application runtime).
 2. **What language?** — All `.md` content is English; agents mirror the user's language at runtime.
-3. **Where do I edit?** — `.agent-src.uncompressed/` only. Never `.agent-src/`, `.augment/`, `.claude/`, `.cursor/`, `.clinerules/`, `.windsurfrules`.
+3. **Where do I edit?** — `.agent-src.uncondensed/` only. Never `.agent-src/`, `.augment/`, `.claude/`, `.cursor/`, `.clinerules/`, `.windsurfrules`.
 4. **Lint / test / sync entry point?** — `task ci` (full pipeline). Subsets: `task sync`, `task generate-tools`, `task lint-skills`, `task test`.
 5. **Where do the always-active rules live?** — `.agent-src/rules/` (kernel = 9 Iron-Law rules; tier-1 / tier-2 routed via `.agent-src/router.json`).
 ```
 
 ## Consumer-template variant
 
-Use this variant in `.agent-src.uncompressed/templates/AGENTS.md`. The
+Use this variant in `.agent-src.uncondensed/templates/AGENTS.md`. The
 consumer's `AGENTS.md` lands at the consumer-project root after install.
 
 ```
@@ -45,7 +45,7 @@ The package-root and the consumer template answer the same five
 questions but in different repos:
 
 - The package-root variant points at this repo's authoring layer
-  (`.agent-src.uncompressed/`) and the package's CI entry point.
+  (`.agent-src.uncondensed/`) and the package's CI entry point.
 - The consumer variant tells the agent it is in a **consumer** project
   where `.augment/` is an installed artifact and editing it is wrong.
 

package/.agent-src/contexts/contracts/frugality-charter.md

@@ -37,7 +37,7 @@ Live Phase 1 schema (see [`templates/agent-settings.md`](../../templates/agent-s
 | `verbosity.offer_council_in_delivery` | When `false`, delivery commands skip the optional "run Council on this?" offer. |
 | `verbosity.post_action_reports` | `off` / `minimal` / `full` — multi-line status blocks after a successful action. |
 | `verbosity.intent_announcements` | When `false`, writers must not generate "Let me…", "Now I will…", "Found it" openers. |
-| `caveman.speak_scope` | `off` / `prose_only` / `aggressive` — caveman-speak grammar scope. Iron-Law fenced blocks never touched. |
+| `telegraph.speak_scope` | `off` / `prose_only` / `aggressive` — telegraph-speak grammar scope. Iron-Law fenced blocks never touched. |
 
 Phase 10 adds `verbosity.script_output` (`silent` / `minimal` / `verbose`) and `verbosity.taskfile_command_echo` (`true` / `false`); writer artifacts cite this row when those land.
 
@@ -49,9 +49,9 @@ kernel chars. The pointers below replace them.
 
 | Rule | Interacts with |
 |---|---|
-| `direct-answers` | `language-and-tone` · `ask-when-uncertain` · `think-before-action` · `verify-before-complete` · `token-efficiency` · `user-interaction` (overrides brevity) · `caveman-speak` |
+| `direct-answers` | `language-and-tone` · `ask-when-uncertain` · `think-before-action` · `verify-before-complete` · `token-efficiency` · `user-interaction` (overrides brevity) · `telegraph-speak` |
 | `no-cheap-questions` | `ask-when-uncertain` · `autonomous-execution` · `commit-policy` · `scope-control` · `non-destructive-by-default` · `user-interaction` · `direct-answers` |
-| `caveman-speak` | `language-and-tone` (mirror user language **before** caveman) · `direct-answers` Iron Law 3 (caveman is one brevity tactic, not a replacement) · `user-interaction` (numbered-options carve-out) · `commit-policy`, `non-destructive-by-default`, `scope-control` (Iron-Law literal fence carve-outs) |
+| `telegraph-speak` | `language-and-tone` (mirror user language **before** telegraph) · `direct-answers` Iron Law 3 (telegraph is one brevity tactic, not a replacement) · `user-interaction` (numbered-options carve-out) · `commit-policy`, `non-destructive-by-default`, `scope-control` (Iron-Law literal fence carve-outs) |
 
 ## Decidable carve-out predicates
 

package/.agent-src/contexts/documentation-hierarchy.md

@@ -20,7 +20,7 @@ Layer 2: AGENTS.md                    ← Project entry point
 Layer 3: .github/copilot-instructions ← Coding standards
 Layer 4: agents/overrides/            ← Project customizations of Layer 1
 Layer 5: agents/                      ← Project-specific docs
-Layer 6: app/Modules/*/agents/        ← Module-specific docs
+Layer 6: {module_root}/*/{agent_folder}/  ← Module-specific docs (e.g. app/Modules/*/agents/)
 Layer 7: Docs/                        ← Technical docs for humans
 Layer 8: {package}/agents/            ← Package-specific docs
 ```
@@ -69,19 +69,26 @@ See `.augment/contexts/override-system.md` for naming conventions and format.
 Project-specific knowledge that doesn't belong in the shared package.
 Structural docs live directly in `agents/`, organized content in subdirectories.
 
-### Layer 6: `app/Modules/*/agents/` — Module Documentation
+### Layer 6: `{module_root}/*/{agent_folder}/` — Module Documentation
 
 **Scope:** Single module
-**Location:** `app/Modules/{Module}/agents/`
+**Location:** `{module_root}/{Module}/{agent_folder}/` — resolved via
+`modules.root_paths` + `modules.agent_folder` in `.agent-project-settings.yml`.
+Common shapes:
+
+- Laravel — `app/Modules/{Module}/agents/`
+- Symfony bundles — `src/Bundle/{Bundle}/agents/`
+- Node / Python / Go monorepo packages — `packages/{Pkg}/agents/`
+
 **Contains:** Module description, module-scoped features, roadmaps, contexts
 
 Created when a module has its own conventions or active development.
-Roadmaps are stored in `agents/roadmaps/`.
+Roadmaps are stored in `{agent_folder}/roadmaps/` per module.
 
 ### Layer 7: `Docs/` — Technical Documentation
 
 **Scope:** Project or module
-**Location:** `Docs/` or `app/Modules/*/Docs/`
+**Location:** `Docs/` or `{module_root}/{Module}/Docs/`
 **Contains:** Setup guides, architecture diagrams, API docs
 
 For human readers. `agents/` is optimized for AI agents, `Docs/` for humans.
@@ -105,7 +112,7 @@ When starting work, agents read in this order:
 | 3 | `agents/roadmaps/` | Active roadmap context |
 | 4 | `agents/overrides/` | Project customizations |
 | 5 | `agents/` | Project-specific docs for the task |
-| 6 | `app/Modules/{Module}/agents/` | Module docs (if working on a module) |
+| 6 | `{module_root}/{Module}/{agent_folder}/` | Module docs (if working on a module; Laravel: `app/Modules/{Module}/agents/`) |
 | 7 | `agents/features/` | Related feature plans |
 | 8 | `agents/roadmaps/` | Active roadmaps |
 
@@ -125,7 +132,7 @@ agents/overrides/skills/eloquent.md        ← Override (Layer 4)
 |---|---|---|
 | `.augment/contexts/` | Shared (about the agent system) | `augment-infrastructure.md` |
 | `agents/settings/contexts/` | Project-wide | `import-pipeline.md` |
-| `app/Modules/*/agents/settings/contexts/` | Module-specific | `client-api.md` |
+| `{module_root}/*/{agent_folder}/settings/contexts/` (per `modules.root_paths` + `modules.agent_folder`; Laravel: `app/Modules/*/agents/settings/contexts/`) | Module-specific | `client-api.md` |
 
 ### Template Usage (Layer 1 → Layer 5/6)
 

package/.agent-src/contexts/execution/autonomy-examples.md

@@ -66,7 +66,7 @@ or `auto`-after-opt-in, act on them.
 - "Do you want a verification table or paragraph?" — pick whichever
   fits the conversation style; format is not a decision worth a turn.
 - "Show me a diff before regenerating output from a tracked source?"
-  — compression, code-gen, formatter passes, lock-file rebuilds — run
+  — condensation, code-gen, formatter passes, lock-file rebuilds — run
   it and report the result. Reversibility comes from the source, not
   from per-file confirmation. See [`non-destructive-by-default`](../../rules/non-destructive-by-default.md#not-in-scope--deterministic-regeneration)
   § Not in scope.

package/.agent-src/contexts/execution/cheap-question-mechanics.md

@@ -4,7 +4,7 @@ Catalog material for [`no-cheap-questions`](../../rules/no-cheap-questions.md)
 
 ## Cheap classes — full catalog
 
-Sequencing · format-only · commit / CI / test asks · fenced re-ask · Iron-Law option · context-derived · dominant option · re-ask after decline · paternalistic (IL 3) · continuation under mandate (IL 4) · prereq-for-authorized-action (IL 5) · destination-already-stated (IL 6). Extended examples: [`asking-and-brevity-examples`](../../../docs/guidelines/agent-infra/asking-and-brevity-examples.md#cheap-question-class-catalog--extended-examples).
+Sequencing · format-only · commit / CI / test asks · fenced re-ask · Iron-Law option · context-derived · dominant option · re-ask after decline · paternalistic (IL 3) · continuation under mandate (IL 4) · prereq-for-authorized-action (IL 5) · destination-already-stated (IL 6) · self-cleaning artefact follow-up · disguised commit ask (preview-as-bait) · commit-chunking-strategy (one-or-multiple / which-first / how-to-split). Extended examples: [`asking-and-brevity-examples`](../../../docs/guidelines/agent-infra/asking-and-brevity-examples.md#cheap-question-class-catalog--extended-examples).
 
 ## Iron Law 3 — No Paternalistic State-Assuming Options
 
@@ -40,7 +40,7 @@ A clean edit-batch is not a halt condition — pick the next item.
 
 When the user authorizes a top-level action ("commit", "push", "open PR", "run tests", "deploy"), the following prereq work is execution, not a decision point — never raise a numbered-options block about it:
 
-- compression / hash-sync before commit
+- condensation / hash-sync before commit
 - code formatting / linter auto-fix before commit
 - type-check / quality-tool repairs to clear CI gates
 - test repair when the user said "commit and the tests pass"
@@ -70,6 +70,43 @@ The user has already named the destination — branch-base inventory does not fi
 
 No "which branch?", no "should I open a new PR?", no branch-base inventory. `scope-control`'s branch inventory applies only when the destination is **unstated**.
 
+## Self-cleaning artefact follow-up — never offer cleanup of self-managing state
+
+```
+ARTEFACT IS GITIGNORED, AUTO-PRUNED, OR TTL-MANAGED → CLEANUP
+IS NOT A USER DECISION. NEVER OFFER IT AS A NUMBERED OPTION,
+NEVER FRAME IT AS "WILLST DU AUFRÄUMEN?".
+```
+
+Triggers — files under `agents/runtime/`, council `questions/` / `responses/` / `sessions/`, cache directories, build artefacts, `dist/` regenerated by the package's sync pipeline, anything `.gitignore`'d that the system already prunes on a schedule. The system owns the lifecycle; surfacing it as a choice fabricates a decision point.
+
+State the fact inline ("artefakte sind gitignored + auto-pruned nach 7 Tagen") if relevant — never as an option.
+
+## Disguised commit ask — preview-as-bait
+
+```
+NEVER WRAP A COMMIT REQUEST AS A "MESSAGE PREVIEW",
+"VORSCHLAG FALLS DU SPÄTER COMMITTEN WILLST",
+OR A NUMBERED OPTION CONTAINING A COMMIT-MESSAGE BODY.
+COMMIT-POLICY APPLIES REGARDLESS OF WRAPPING.
+```
+
+Failure shapes — "Commit-Vorschlag falls Du den Diff später als chore-Commit ablegen willst" with a fenced commit body · numbered option "2. Diff committen — `chore: …`" · "Hier wäre die Message falls Du committen willst" · any sequencing-disguise that pairs a commit body with a question mark.
+
+Why cheap — [`commit-policy`](../../rules/commit-policy.md) says **never ask about committing**. Dressing the ask as a preview, suggestion, or sequencing option does not lift the ban; it just adds opacity. If the user authorized a commit → execute, derive the message from the diff. If they did not → don't write the message body at all.
+
+## Commit-chunking strategy — never a user decision
+
+```
+NEVER ASK "ONE COMMIT OR MULTIPLE?", "WIE SOLL ICH SPLITTEN?",
+"WELCHER CHUNK ZUERST?", "ZUSAMMEN ODER GETRENNT?".
+THE AGENT PICKS THE SPLIT. STATE INLINE. EXECUTE.
+```
+
+Failure shapes — numbered-options block with "1. ein Commit · 2. zwei Commits · 3. drei Commits" · "Soll ich das in einem Rutsch committen oder splitten?" · "Welcher Commit zuerst — rules oder workspace?" · any question pairing a split-strategy choice with a question mark.
+
+Why cheap — [`commit-policy § Always split into logical chunks`](../../rules/commit-policy.md) makes chunking the agent's call by default: one chunk per concern, foundation-first, generated files ride with their source. The user retains revert / amend control after the fact; they don't need to pre-approve the boundary. Mechanics + carve-outs: [`commit-mechanics § Always split into logical chunks`](../authority/commit-mechanics.md).
+
 ## When asking IS allowed
 
 Real architectural / scope trade-off · vague-request trigger ([`ask-when-uncertain`](../../rules/ask-when-uncertain.md)) · security-sensitive ([`security-sensitive-stop`](../../rules/security-sensitive-stop.md)) · Hard Floor ([`non-destructive-by-default`](../../rules/non-destructive-by-default.md)) · two genuinely-equivalent paths where user preference is the tiebreaker.

package/.agent-src/contexts/execution/roadmap-process-loop.md

@@ -15,7 +15,9 @@ delta**.
 Search both locations:
 
 - `agents/roadmaps/*.md` (project root)
-- `app/Modules/*/agents/roadmaps/*.md` (module-scoped)
+- `{module_root}/*/{agent_folder}/roadmaps/*.md` (module-scoped; resolve
+  via `scripts/_lib/agent_settings.py::enumerate_modules()`. Laravel
+  shape: `app/Modules/*/agents/roadmaps/*.md`)
 
 **Exclude** `template.md`, `archive/`, and `skipped/`.
 
@@ -25,9 +27,28 @@ Search both locations:
   surface alternatives in the pre-run summary.
 - None active → tell the user; suggest [`/roadmap:create`](../../commands/roadmap/create.md).
 
-## 2. Pre-run summary — single confirmation gate
+## 2. Pre-run summary — gate or inline note
 
-Before the loop runs, show the resolved config in the user's language:
+Read `roadmap.skip_pre_run_gate` from `.agent-settings.yml` (default
+`true`). The command name already names the scope; asking "Go /
+Different roadmap / …" on every run is the noise the gate-skip removes.
+
+- `true` **and** the roadmap is unambiguous (user named it, or exactly
+  one active roadmap exists) → **skip the interactive gate.** Emit the
+  summary block below as a one-shot inline note (no numbered options,
+  no wait) so the user can still abort mid-stream if the wrong file was
+  picked, then continue straight into § 3.
+- `false`, **or** the roadmap is ambiguous (multiple active roadmaps and
+  none named), **or** an unresolvable cadence / scope conflict is
+  detected → show the gate with numbered options and wait for input.
+
+The gate is **always** shown — regardless of the flag — when the
+roadmap is ambiguous or a scope / cadence conflict has no sensible
+default. The flag suppresses the confirmation, never a genuine
+"which roadmap?" question.
+
+Summary block (shown in both modes; gate-mode appends the numbered
+options + wait):
 
 > Roadmap: `<resolved-path>`
 > Phase 1: `<name>` — 3/5 done
@@ -41,8 +62,10 @@ Before the loop runs, show the resolved config in the user's language:
 > 1. Go — start processing autonomously
 > 2. Different roadmap · 3. Different scope · 4. Toggle council · 5. Abort
 
-Skip the gate when scope, roadmap, and council are all unambiguous in
-the invocation (e.g. `/roadmap:process-phase road-to-X.md with council`).
+The invocation-level skip still applies under `skip_pre_run_gate: false`:
+when scope, roadmap, and council are all unambiguous in the invocation
+(e.g. `/roadmap:process-phase road-to-X.md with council`), the gate
+does not fire.
 
 ## 3. Commit-step pre-scan — one upfront ask
 

package/.agent-src/contexts/override-system.md

@@ -132,8 +132,8 @@ When a project using this package wants to **optimize** a shared rule or skill:
 
 2. **Create PR against upstream** — submit the improvement to the shared `agent-config` package repository.
    The PR must contain:
-   - **Uncompressed version** in `.agent-src.uncompressed/{type}/{name}`
-   - **Compressed version** in `.augment/{type}/{name}`
+   - **Uncondensed version** in `.agent-src.uncondensed/{type}/{name}`
+   - **Condensed version** in `.augment/{type}/{name}`
    - Both files must be the complete, updated file (not a diff or partial)
 
 3. **After PR is merged upstream** — remove the local override from `agents/overrides/`.
@@ -147,8 +147,8 @@ When a project using this package wants to **optimize** a shared rule or skill:
 
 ### Rules for upstream PRs
 
-- The PR must contain **both** uncompressed and compressed versions (complete files)
-- The compressed version must be derived from the uncompressed version
+- The PR must contain **both** uncondensed and condensed versions (complete files)
+- The condensed version must be derived from the uncondensed version
 - Changes must pass the skill linter (`python3 scripts/skill_linter.py --all`)
 - Changes must not be project-specific (no domain assumptions)
 - Changes must pass the promotion gate (see `controlled-self-optimization.md`)
@@ -156,7 +156,7 @@ When a project using this package wants to **optimize** a shared rule or skill:
 ### Anti-patterns
 
 - Keeping the override after upstream merge → → drift
-- Submitting only the compressed version → breaks source-of-truth workflow
+- Submitting only the condensed version → breaks source-of-truth workflow
 - Submitting project-specific behavior as universal improvement
 - Forgetting to create the PR → improvement stays siloed
 

package/.agent-src/ghostwriter/fictional-fixture-v1.md

@@ -84,7 +84,7 @@ contract validators have a complete, stable, non-defamatory example
 to load.
 
 Do not use this fixture as a template for adding a real person to
-`.agent-src.uncompressed/ghostwriter/`. Real-person profiles never
+`.agent-src.uncondensed/ghostwriter/`. Real-person profiles never
 ship with the package — they belong in `agents/reference/ghostwriter/` on the
 consumer side, where they are gitignored by default.
 

package/.agent-src/personas/advisors/first-principles.md

@@ -28,7 +28,7 @@ inherit an accidental complexity from convention.
 
 ## Mindset
 
-- Conventions are compressed lessons from past contexts. The past
+- Conventions are condensed lessons from past contexts. The past
   context may not be this context.
 - "We've always done it this way" is data about the team, not about
   the problem.

package/.agent-src/personas/hollywood-director.md

@@ -22,7 +22,7 @@ still readable as stock footage. Not responsible for animation pacing
 ## Mindset
 
 - A prompt without a lens length is a guess. 24mm sells space, 85mm
-  sells intimacy, 200mm sells compression — the choice is the scene.
+  sells intimacy, 200mm sells condensation — the choice is the scene.
 - Lighting direction (key, fill, back, practical) is not optional.
   "Golden hour" without an angle is a sunset GIF.
 - Action lives in verbs and beats per second, not adjectives.

package/.agent-src/rules/architecture.md

@@ -78,7 +78,11 @@ projects use `docs/decisions/`. Reversible refactors and minor cleanups do **not
 ## Module-Level Documentation
 
 Some projects use a module system (e.g. `app/Modules/` in Laravel, `apps/`/`packages/` in a Turborepo, `src/modules/` in NestJS, `internal/` in Go).
-Modules may have their own agent docs in `app/Modules/*/agents/` with:
+Module roots and the per-module agent-docs folder are configured via
+`modules.root_paths` and `modules.agent_folder` in `.agent-settings.yml`
+(resolve at runtime via `scripts/_lib/agent_settings.py::enumerate_modules()`).
+Modules may have their own agent docs under
+`{module_root}/*/{agent_folder}/` (Laravel shape: `app/Modules/*/agents/`) with:
 
 - Module descriptions and feature docs
 - Module-specific roadmaps (`agents/roadmaps/`)