@event4u/agent-config 3.3.0 → 4.2.0

package/.agent-src/skills/module-management/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: module-management
-description: "Use when the user says "create module", "explore module", or works within app/Modules/. Understands module structure, auto-loading, route registration, and namespace conventions."
+description: "Use when working within any module under `modules.root_paths` from `.agent-project-settings.yml` — Laravel HMVC, Symfony DDD-lite, Node monorepo, Python src/, Go internal/, or a custom path."
 source: package
 domain: process
-framework: laravel
 workspaces:
   - agent-config-maintainer
 packs:
@@ -22,147 +21,220 @@ install:
 
 ## When to use
 
-Use this skill when creating, exploring, or working within a module in `app/Modules/`.
+Use this skill when creating, exploring, or working within a module under
+any directory listed in `modules.root_paths` (team setting in
+`.agent-project-settings.yml`). The skill is stack-agnostic — Laravel
+HMVC, Symfony DDD-lite, Node monorepo, Python src layout, Go internal/,
+or a custom path all flow through the same procedure with a
+stack-specific carve-out at the bottom.
+
+When `modules.enabled` is `false` (the default) the skill is a no-op —
+the project does not opt into module-aware behavior.
+
+## Understand the current layout before editing
+
+Before creating, renaming, or modifying anything inside a module:
+
+1. Read the `modules:` block from `.agent-project-settings.yml` —
+   never assume a specific module root.
+2. List the existing modules under each `modules.root_paths` entry and
+   review the target module's `README.md` (or `package.json` /
+   `pyproject.toml` description) to understand its purpose.
+3. Read any module-scoped agent docs under
+   `{module_root}/{ModuleName}/{modules.agent_folder}/contexts/`.
+4. Match the stack carve-out below by `modules.namespace_template`
+   shape and confirm the conventions before generating files.
+
+Skip this step → risk creating files in the wrong root, breaking
+stack-native auto-loading, or duplicating existing modules.
 
 ## Procedure: Work with modules
 
-1. Read `app/Modules/README.md` for the full module documentation.
-2. Check `app/Providers/ModuleServiceProvider.php` for auto-loading behavior.
-3. If module-level agent docs exist (`app/Modules/{Module}/agents/`), read them.
+1. Read `modules:` block from `.agent-project-settings.yml` via the
+   loader (`get_modules_config()` in `scripts/_lib/agent_settings.py`).
+2. For each path in `modules.root_paths`, read the module's `README.md`
+   (or `package.json` / `pyproject.toml` description) for purpose.
+3. If module-level agent docs exist under
+   `{module_root}/{modules.agent_folder}/` (default `agents/`), read them.
+4. Match the stack carve-out below by `modules.namespace_template` shape
+   or root-path heuristic — apply stack-specific conventions on top of
+   the generic procedure.
+
+## Detection (fallback when `modules:` block is empty)
 
-## Detection
+When `modules.enabled` is unset / false, the skill consults the
+auto-detection table in
+[`/module explore` Step 1](../../commands/module/explore.md) — same six
+stack shapes, fallback only. The skill never writes the `modules:`
+block automatically; that is `propose_modules_config.py` plus user
+confirmation per
+[`/agents init`](../../commands/agents/init.md) Step 7.
 
-Check if `app/Modules/` exists in the project. If it doesn't, the project doesn't use modules.
+## Generic module structure
 
-## Architecture
+```
+{module_root}/{ModuleName}/
+├── <stack-native source layout>      # see carve-out below
+├── tests/                            # module-specific tests
+├── README.md                         # module description
+└── {modules.agent_folder}/           # default: agents/
+    ├── features/                     # module-scoped feature plans
+    ├── roadmaps/                     # module-scoped roadmaps
+    └── contexts/                     # module-scoped context docs
+```
+
+The agent-folder name comes from `modules.agent_folder` (default
+`agents`). Skip directories listed in `modules.skip_dirs` (default
+`.module-template`, `.example`).
 
-### ModuleServiceProvider
+## Stack carve-outs
 
-`app/Providers/ModuleServiceProvider.php` auto-discovers modules by scanning `app/Modules/`:
+Apply the section that matches the project's
+`modules.namespace_template` and root-path layout.
 
-1. **Route loading** — automatically loads `Routes/api.php`, `Routes/web.php`, `Routes/console.php`
-   - API routes: prefixed with `/api`, `api` middleware
-   - Web routes: `web` middleware
-   - Console routes: loaded via `require_once`
-   - Fallback: also checks lowercase `routes/` for legacy modules
-2. **Command registration** — auto-discovers commands in `App/Console/Commands/`
-   - Fallback: also checks `Console/Commands/` for legacy modules
+### Laravel HMVC carve-out
 
-### Module structure
+**Triggers when:** `modules.namespace_template` starts with
+`App\Modules\` or root path is `app/Modules`.
 
 ```
 app/Modules/{ModuleName}/
-├── App/                         # All application code (PSR-4)
-│   ├── Console/Commands/        # Artisan commands (auto-registered)
-│   ├── Enums/
-│   ├── Http/
-│   │   ├── Controllers/
-│   │   ├── Middleware/
-│   │   └── Requests/
-│   ├── Jobs/
-│   ├── Models/
-│   ├── Rules/
-│   └── Services/
-├── Routes/                      # Auto-loaded route files
-│   ├── api.php
-│   ├── web.php
-│   └── console.php
-├── Tests/                       # Module-specific tests
-│   ├── Component/
-│   ├── Integration/
-│   └── Unit/
-├── Docs/                        # Optional technical docs
-├── agents/                      # Agent docs for this module
-│   ├── features/
-│   ├── roadmaps/
-│   └── contexts/
-└── README.md                    # Optional module description
+├── App/                              # PSR-4 source (capitalized)
+│   ├── Console/Commands/             # auto-registered
+│   ├── Http/{Controllers,Middleware,Requests}/
+│   ├── Jobs/  Models/  Services/  Rules/  Enums/
+├── Routes/                           # auto-loaded
+│   ├── api.php   web.php   console.php
+├── Tests/{Unit,Integration,Component}/
+└── agents/
 ```
 
-**Important:** Directory names use capital letters (App, Routes, Tests) for PSR-4 compliance.
+**Namespace:** `App\Modules\{ModuleName}\App\{Layer}\{Class}` — note the
+extra `App` segment.
 
-### Namespace convention
+**Auto-loading:** `app/Providers/ModuleServiceProvider.php` scans
+`app/Modules/` and registers routes (`Routes/api.php` → `/api` prefix +
+`api` middleware; `Routes/web.php` → `web` middleware) plus Artisan
+commands under `App/Console/Commands/`.
 
+**Route conventions:**
+
+```php
+// Routes/api.php — auto-prefixed /api
+Route::name('v1.')->prefix('v1/{module-prefix}')->group(function(): void {
+    Route::get('/', [Controller::class, 'index'])->name('{module-prefix}.index');
+});
 ```
-App\Modules\{ModuleName}\App\{Layer}\{Class}
+
+Module name = PascalCase. Route prefix = kebab-case. Route names = dot
+notation.
+
+### Symfony DDD-lite carve-out
+
+**Triggers when:** `modules.namespace_template` starts with `App\` (no
+`Modules` segment) or root path is `src/` with `<Domain>/` subdirs.
+
+```
+src/{Domain}/
+├── Application/                      # use cases, command handlers
+├── Domain/                           # entities, value objects
+├── Infrastructure/                   # adapters, repositories
+├── UserInterface/                    # controllers, console
+└── Tests/
 ```
 
-Examples:
-- `App\Modules\ClientSoftware\App\Services\ImportService`
-- `App\Modules\ClientSoftware\App\Http\Controllers\Import\ImportDataController`
-- `App\Modules\ClientSoftware\App\Console\Commands\ProcessImportUploadsCommand`
+**Namespace:** `App\{Domain}\{Layer}\{Class}` — no extra segment.
 
-### Route conventions
+**Auto-loading:** Symfony service container auto-wires each
+`{Domain}/` subtree per `services.yaml` resource imports.
 
-```php
-// Routes/api.php — auto-prefixed with /api by ModuleServiceProvider
-Route::name('v1.')
-    ->prefix('v1/{module-prefix}')
-    ->group(function(): void {
-        Route::get('/', [Controller::class, 'index'])->name('{module-prefix}.index');
-    });
+### Node monorepo carve-out
+
+**Triggers when:** root path is `packages/` and each child has
+`package.json`.
+
+```
+packages/{pkg-name}/
+├── package.json
+├── src/                              # entry points re-exported via "main"
+├── tests/   __tests__/
+└── README.md
 ```
 
-- Route prefix: **kebab-case** (e.g., `client-software`, `grafana`)
-- Route names: **dot notation** (e.g., `v1.imports.index`)
-- Module name: **PascalCase** (e.g., `ClientSoftware`, `Grafana`)
+**Module identity** comes from `package.json#name`, not the directory
+name. The agent folder still lives at
+`packages/{pkg-name}/{modules.agent_folder}/`.
 
-## Existing modules
+### Python src-layout carve-out
 
-| Module | Purpose |
-|---|---|
-| `ApiClient` | External API client utilities |
-| `Backoff` | Retry/backoff logic |
-| `ClientSoftware` | Client software imports, uploads, processing |
-| `Grafana` | Grafana/Loki dashboard integration |
-| `Stubbing` | Test stubs and mocks |
+**Triggers when:** root path is `src/` and each child has `__init__.py`.
 
-## Template
+```
+src/{package_name}/
+├── __init__.py
+├── <module files>
+└── tests/                            # or root-level tests/{package_name}/
+```
 
-The `.module-template` directory provides a scaffold for new modules:
-- `app/Modules/.module-template/` — copy and rename to create a new module
-- Contains placeholder route files, README, and directory structure
-- Replace `[MODULE_NAME]` and `[module-prefix]` placeholders
+**Namespace** is the import path: `{package_name}.<sub>.<class>`. Project
+metadata in `pyproject.toml`.
 
-## Agent docs in modules
+### Go internal carve-out
 
-Modules can have their own agent documentation:
+**Triggers when:** root path is `internal/` (one-level structure).
 
 ```
-app/Modules/{Module}/agents/
-├── features/       # Module-scoped feature plans
-├── roadmaps/       # Module-scoped roadmaps
-└── contexts/       # Module-scoped context documents
+internal/{pkgname}/
+├── *.go                              # package files
+└── *_test.go                         # tests colocated
 ```
 
+**Import path:** `{module-path-from-go.mod}/internal/{pkgname}`. No
+top-level grouping — each subdir of `internal/` is its own package.
+
 ## Output format
 
-1. Module directory structure following template conventions
-2. ServiceProvider, routes, and agent docs scaffolded
+1. Module directory under the matched stack carve-out.
+2. Stack-native auto-loading + routing (if applicable).
+3. Optional per-module `{modules.agent_folder}/` scaffold.
 
 ## Auto-trigger keywords
 
-- Laravel module
 - module structure
 - module creation
 - module namespace
+- create / explore module
+- per-module agent docs
 
 ### Validate
 
-- Verify namespace follows `App\Modules\{Name}\App\{Layer}` pattern.
-- Confirm `ModuleServiceProvider` auto-discovers the new module's routes and providers.
-- Run PHPStan on the module — must pass.
+- Verify namespace matches `modules.namespace_template` (when set).
+- Run stack-native auto-loading check (e.g. `php artisan route:list` for
+  Laravel HMVC, `bin/console debug:container` for Symfony,
+  `npm test --workspace=<pkg>` for Node monorepo).
 - Run module tests — must pass.
+- Run quality tools scoped to the new path.
 
 ## Gotcha
 
-- Module namespace is `App\Modules\{Name}\App\{Layer}` — don't forget the extra `App` segment.
-- Routes in modules auto-register via `ModuleServiceProvider` — don't register them manually.
-- Don't put shared code in a module — shared code belongs in `app/` not `app/Modules/`.
+- **Laravel HMVC only** — namespace has the extra `App` segment
+  (`App\Modules\X\App\…`). Other stacks do **not**.
+- Routes auto-register in Laravel HMVC and Symfony — don't register
+  manually.
+- Shared code lives outside module roots — never inside
+  `modules.root_paths`.
+- Capitalize directory names only where the stack requires it (Laravel
+  PSR-4 yes, Node `packages/` no).
 
 ## Do NOT
 
-- Do NOT manually register module routes — `ModuleServiceProvider` handles this.
-- Do NOT use lowercase directory names (`routes/`, `app/`) — use `Routes/`, `App/`.
-- Do NOT put business logic in controllers — use module services.
-- Do NOT create a module for trivial functionality — only when logical separation is needed.
+- Do NOT hardcode any stack-specific module root (Laravel
+  `<app>/<Modules>/`, Symfony `src/Domain`, Node `packages/`, …) in
+  skill bodies, commands, or context docs — read from
+  `modules.root_paths`.
+- Do NOT create a module for trivial functionality — only when logical
+  separation is needed.
+- Do NOT register module routes manually when the stack provides
+  auto-loading.
+- Do NOT add the `framework: laravel` frontmatter back to this skill —
+  the lint guard fails the build.

package/.agent-src/skills/override-management/SKILL.md

@@ -28,7 +28,7 @@ install:
 Use when creating or managing project-level overrides for shared skills, rules, commands, or guidelines — customizing `.augment/` content without modifying originals.
 
 Do NOT use when:
-- Changing shared content that should affect all projects (edit `.agent-src.uncompressed/` directly)
+- Changing shared content that should affect all projects (edit `.agent-src.uncondensed/` directly)
 - Creating new skills from scratch (use `skill-writing` skill)
 
 ## Purpose

package/.agent-src/skills/persona-writing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: persona-writing
-description: "Use when creating or editing a persona in .agent-src.uncompressed/personas/ — voice / focus / unique questions / output expectations — even when the user just says 'add a reviewer voice for X'."
+description: "Use when creating or editing a persona in .agent-src.uncondensed/personas/ — voice / focus / unique questions / output expectations — even when the user just says 'add a reviewer voice for X'."
 source: package
 domain: process
 workspaces:
@@ -24,7 +24,7 @@ install:
 ## When to use
 
 * Creating a new persona file in
-  `.agent-src.uncompressed/personas/{id}.md`
+  `.agent-src.uncondensed/personas/{id}.md`
 * Rewriting an existing persona (focus shift, output-expectation
   change — not a typo fix)
 * Deciding whether a new reviewer voice should be a persona at all
@@ -59,7 +59,7 @@ Creating or materially rewriting a persona must go through
 Understand → Research → Draft per the
 [`artifact-drafting-protocol`](../../rules/artifact-drafting-protocol.md)
 rule. Inspect existing personas under
-`.agent-src.uncompressed/personas/` for overlap before writing a new
+`.agent-src.uncondensed/personas/` for overlap before writing a new
 one.
 
 ### 1. Decide focus, not topic
@@ -107,7 +107,7 @@ persona pairs naturally with; it does not bind.
 
 ## Output format
 
-A single Markdown file at `.agent-src.uncompressed/personas/{id}.md`:
+A single Markdown file at `.agent-src.uncondensed/personas/{id}.md`:
 
 1. Frontmatter (`id`, `role`, `description`, `tier`, `mode`,
    `version`, `source`)
@@ -161,6 +161,6 @@ to every persona you author.
 
 ## Examples
 
-See `.agent-src.uncompressed/personas/ai-agent.md` (automation
+See `.agent-src.uncondensed/personas/ai-agent.md` (automation
 readiness) and `critical-challenger.md` (adversarial review) for
 canonical structure.

package/.agent-src/skills/positioning-strategy/SKILL.md

@@ -162,7 +162,7 @@ skill — that is `messaging-architecture`'s job.
   beat coined categories; category theatre is the council Q1
   out-of-scope.
 - Do NOT collapse positioning into a tagline; the four anchors are
-  the artefact, the tagline is a downstream compression.
+  the artefact, the tagline is a downstream condensation.
 - Do NOT decide pricing tiers from positioning — hand off to
   pricing / unit-economics work.
 

package/.agent-src/skills/project-docs/SKILL.md

@@ -85,10 +85,12 @@ regulations, workflows, and edge cases that the agent needs to understand the pr
 1. **List `agents/settings/contexts/`** — read any context file whose name matches the work area.
 2. **List `agents/settings/contexts/domain/`** — read domain knowledge files relevant to the business logic.
 3. **List `agents/reference/docs/`** — read detail docs for the specific topic you're working on.
-4. **Check module docs** — if working in a module, also check:
-   - `app/Modules/{Module}/agents/` — module-specific docs
-   - `app/Modules/{Module}/agents/settings/contexts/` — module-specific contexts (if exists)
-   - `app/Modules/{Module}/agents/settings/contexts/domain/` — module-specific domain knowledge (if exists)
+4. **Check module docs** — if working in a module, resolve `{module_root}` from
+   `modules.root_paths` and `{agent_folder}` from `modules.agent_folder` (see
+   `scripts/_lib/agent_settings.py::enumerate_modules()`), then check:
+   - `{module_root}/{Module}/{agent_folder}/` — module-specific docs
+   - `{module_root}/{Module}/{agent_folder}/settings/contexts/` — module-specific contexts (if exists)
+   - `{module_root}/{Module}/{agent_folder}/settings/contexts/domain/` — module-specific domain knowledge (if exists)
 
 ### Reading order
 

package/.agent-src/skills/readme-reviewer/SKILL.md

@@ -133,7 +133,7 @@ Classify each finding:
 
 - README not overloaded with deep technical detail
 - Complex content belongs in `/docs`, not README
-- Important onboarding info not missing due to over-compression
+- Important onboarding info not missing due to over-condensation
 
 Size checks:
 
@@ -214,7 +214,7 @@ Compare the README's claims to the live repository:
 | # | Severity | Section | Issue | Fix |
 |---|---|---|---|---|
 | 1 | ❌ Critical | Install | Command `X` does not exist | Replace with `Y` |
-| 2 | ❌ Critical | Profile grid | Link `.agent-src.uncompressed/profiles/` 404s | Repoint to `packages/core/.agent-src.uncompressed/profiles/` |
+| 2 | ❌ Critical | Profile grid | Link `.agent-src.uncondensed/profiles/` 404s | Repoint to `packages/core/.agent-src.uncondensed/profiles/` |
 | 3 | ⚠️ Major | Badges | "Skills: 218" — live count is 207 | Update badge or note drift |
 | 4 | ⚠️ Major | Usage | Example uses deprecated API | Update to current API |
 | 5 | ℹ️ Minor | Structure | Requirements buried below usage | Move above install |

package/.agent-src/skills/roadmap-management/SKILL.md

@@ -67,9 +67,21 @@ different agents.
 | Location | Scope |
 |---|---|
 | `agents/roadmaps/` | Project-wide roadmaps |
-| `app/Modules/{Module}/agents/roadmaps/` | Module-specific roadmaps |
+| `{module_root}/{Module}/{agent_folder}/roadmaps/` | Module-specific roadmaps (see note) |
 | `{package-root}/agents/roadmaps/` | Package-specific roadmaps |
 
+**Module path resolution.** `{module_root}` and `{agent_folder}` come from
+`modules.root_paths` and `modules.agent_folder` in
+`.agent-project-settings.yml` — see [`layered-settings`](../../../../../docs/guidelines/agent-infra/layered-settings.md).
+Common shapes:
+
+- Laravel — `app/Modules/{Module}/agents/roadmaps/`
+- Symfony bundles — `src/Bundle/{Bundle}/agents/roadmaps/`
+- Node / Python / Go monorepo packages — `packages/{Pkg}/agents/roadmaps/`
+
+Use `scripts/_lib/agent_settings.py::enumerate_modules()` to discover the
+actual paths in the current project; never assume `app/Modules/`.
+
 The file `.augment/templates/roadmaps.md` defines the canonical structure.
 **Always read it first** before creating or modifying roadmaps.
 

package/.agent-src/skills/roadmap-writing/SKILL.md

@@ -24,7 +24,9 @@ install:
 ## When to use
 
 * Authoring a new roadmap file in `agents/roadmaps/{name}.md` (or
-  module-scoped under `app/Modules/{Module}/agents/roadmaps/`)
+  module-scoped under `{module_root}/{Module}/{agent_folder}/roadmaps/` —
+  per `modules.root_paths` + `modules.agent_folder`; Laravel shape:
+  `app/Modules/{Module}/agents/roadmaps/`)
 * Rewriting an existing roadmap (phase restructure, goal pivot,
   council-pass integration — not a checkbox flip)
 * Drafting a phase block, exit criteria, or rollback section that
@@ -63,7 +65,7 @@ or supersession before opening a new one.
 ### 1. Read the canonical template first
 
 The structure, frontmatter, lifecycle, and complexity-tier rules live
-in [`.agent-src.uncompressed/templates/roadmaps.md`](../../templates/roadmaps.md).
+in [`.agent-src.uncondensed/templates/roadmaps.md`](../../templates/roadmaps.md).
 Read it before authoring. Do not restate its rules in the roadmap
 body — link the template if a phase needs to override one.
 

package/.agent-src/skills/rule-refactor/SKILL.md

@@ -88,21 +88,21 @@ For each approved verdict:
 
 * **merge** → rewrite the surviving rule to cover both domains;
   delete the absorbed one; update any `routes_to:` references.
-* **delete** → remove the file from `.agent-src.uncompressed/rules/`
+* **delete** → remove the file from `.agent-src.uncondensed/rules/`
   and the corresponding `.agent-src/rules/` projection.
 * **move-to-context** → extract the body into
-  `.agent-src.uncompressed/contexts/<area>/<name>.md`, replace the
+  `.agent-src.uncondensed/contexts/<area>/<name>.md`, replace the
   rule body with the obligation + a `load_context:` pointer.
 * **promote-to-skill** → create
-  `.agent-src.uncompressed/skills/<name>/SKILL.md`, replace the rule
+  `.agent-src.uncondensed/skills/<name>/SKILL.md`, replace the rule
   with an auto-trigger stub that routes to it (or delete the rule
   entirely if the skill's own trigger suffices).
 
 ### 6. Re-validate
 
 ```bash
-bash scripts/compress.sh --sync
-python3 scripts/compress.py --generate-tools
+bash scripts/condense.sh --sync
+python3 scripts/condense.py --generate-tools
 python3 scripts/measure_augment_budget.py --check   # must exit 0
 python3 scripts/skill_linter.py --all               # 0 FAIL
 ```

package/.agent-src/skills/rule-writing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: rule-writing
-description: "Use when creating or editing a rule in .agent-src.uncompressed/rules/ — trigger wording, always vs auto classification, size budget — even when the user just says 'add a rule for X'."
+description: "Use when creating or editing a rule in .agent-src.uncondensed/rules/ — trigger wording, always vs auto classification, size budget — even when the user just says 'add a rule for X'."
 source: package
 domain: process
 workspaces:
@@ -23,7 +23,7 @@ install:
 
 ## When to use
 
-* Creating a new rule in `.agent-src.uncompressed/rules/{name}.md`
+* Creating a new rule in `.agent-src.uncondensed/rules/{name}.md`
 * Rewriting an existing rule (not a typo fix)
 * Deciding whether something should be a rule at all
 * Converting a learning from `learning-to-rule-or-skill` into a concrete rule
@@ -55,7 +55,7 @@ Research → Draft from the
 
 * **Understand** — which agent behavior is wrong today? What should change?
   Can you point to a concrete incident or repeated pattern?
-* **Research** — **inspect** `.agent-src.uncompressed/rules/` for overlap
+* **Research** — **inspect** `.agent-src.uncondensed/rules/` for overlap
   and **analyze** `rule-type-governance`, `size-enforcement`,
   `skill-quality` before drafting.
 * **Draft** — propose frontmatter (`type`, `description`) first, wait for
@@ -105,16 +105,16 @@ fail `python3 scripts/lint_load_context.py`. Canonical reference:
 
 | Field | Form | Example |
 |---|---|---|
-| `load_context:` / `load_context_eager:` | **Logical name** rooted at the source — never `.agent-src.uncompressed/` | `contexts/execution/verification-mechanics.md` |
-| `triggers[].path_prefix:` | **Literal match pattern** the host evaluates against the file the agent is editing — not rewritten | `.agent-src.uncompressed/skills/` (source-of-truth rules) or `agents/`, `app/`, `.augment/` |
+| `load_context:` / `load_context_eager:` | **Logical name** rooted at the source — never `.agent-src.uncondensed/` | `contexts/execution/verification-mechanics.md` |
+| `triggers[].path_prefix:` | **Literal match pattern** the host evaluates against the file the agent is editing — not rewritten | `.agent-src.uncondensed/skills/` (source-of-truth rules) or `agents/`, `app/`, `.augment/` |
 | Body links to guidelines / contracts | **Verbatim relative form** — `../../docs/...` works in any markdown viewer; rewriter handles depth | `[guideline](../../docs/guidelines/<group>/<name>.md)` |
 
-The compress-time rewriter (`scripts/compress.py::_rewrite_paths`) is
+The condense-time rewriter (`scripts/condense.py::_rewrite_paths`) is
 idempotent and depth-aware — it resolves logical names and body links
-to the deployment-correct relative path at compress time, leaving
+to the deployment-correct relative path at condense time, leaving
 `path_prefix:` literally as written. The schema regex
 (`scripts/schemas/rule.schema.json`) and `scripts/lint_load_context.py`
-both reject the `.agent-src.uncompressed/` prefix in `load_context:` /
+both reject the `.agent-src.uncondensed/` prefix in `load_context:` /
 `load_context_eager:` with an error pointing at the canonical logical
 name.
 
@@ -134,10 +134,10 @@ the PR or split by responsibility.
 
 ### 5. Validate
 
-* Run `python3 scripts/skill_linter.py .agent-src.uncompressed/rules/{name}.md`
+* Run `python3 scripts/skill_linter.py .agent-src.uncondensed/rules/{name}.md`
   → must report **0 FAIL**.
-* Run `bash scripts/compress.sh --sync` to regenerate `.agent-src/rules/{name}.md`.
-* Run `python3 scripts/compress.py --generate-tools` to project into `.claude/`, `.cursor/`, `.clinerules/`, `.windsurfrules`.
+* Run `bash scripts/condense.sh --sync` to regenerate `.agent-src/rules/{name}.md`.
+* Run `python3 scripts/condense.py --generate-tools` to project into `.claude/`, `.cursor/`, `.clinerules/`, `.windsurfrules`.
 * Run the full CI pipeline locally (see `Taskfile.yml` in this repo for
   the script list) — must exit 0 except for tolerated warnings.
 
@@ -199,7 +199,7 @@ source: package           # or project for consumer-local rules
 load_context:             # logical names only — `contexts/<area>/<file>.md`
   - contexts/execution/verification-mechanics.md
 triggers:                 # path_prefix is literal, not rewritten
-  - path_prefix: ".agent-src.uncompressed/rules/"
+  - path_prefix: ".agent-src.uncondensed/rules/"
 routes_to:
   - "skill:related-skill"
 ---
@@ -211,10 +211,10 @@ and body links (relative `../../docs/...`, rewriter handles depth).
 
 ## Output format
 
-1. Complete rule file at `.agent-src.uncompressed/rules/{name}.md`
+1. Complete rule file at `.agent-src.uncondensed/rules/{name}.md`
 2. Frontmatter fully populated, no placeholders left
 3. Linter output showing 0 FAIL
-4. Confirmation that `bash scripts/compress.sh --sync` + `python3 scripts/compress.py --generate-tools` ran clean
+4. Confirmation that `bash scripts/condense.sh --sync` + `python3 scripts/condense.py --generate-tools` ran clean
 
 ## Gotchas
 
@@ -222,7 +222,7 @@ and body links (relative `../../docs/...`, rewriter handles depth).
 * Defaulting to `always` "just in case" — token cost is real, `auto` is default.
 * Description like "Rule about X" — it must describe *when*, not *what*.
 * Pasting a workflow into a rule — if it has numbered steps, split into a skill.
-* Forgetting to run `python3 scripts/compress.py --generate-tools` — downstream tools stay stale.
+* Forgetting to run `python3 scripts/condense.py --generate-tools` — downstream tools stay stale.
 * Editing `.agent-src/rules/` or `.augment/rules/` directly — those are generated.
 
 ## Frugality Standards
@@ -258,7 +258,7 @@ to every rule you author.
 ## Cloud Behavior
 
 On cloud surfaces (Claude.ai Web, Skills API) the package's
-`scripts/skill_linter.py`, `scripts/compress.py`, and `task` runner
+`scripts/skill_linter.py`, `scripts/condense.py`, and `task` runner
 are not reachable. The skill still applies — with prose-only
 validation:
 
@@ -269,9 +269,9 @@ validation:
   `type`.
 * Self-check the body: under the size budget (200 lines hard,
   120 soft), trigger sentence first, no embedded procedures.
-* Tell the user to save under `.agent-src.uncompressed/rules/{name}.md`
+* Tell the user to save under `.agent-src.uncondensed/rules/{name}.md`
   and run `task sync && task lint-skills` locally before committing.
-* Do not call the linter or compressor — they only run on the
+* Do not call the linter or condenseor — they only run on the
   user's machine.
 
 ## Examples

package/.agent-src/skills/script-writing/SKILL.md

@@ -164,7 +164,7 @@ do **not** add `silent: true` and do **not** use `{{.QUIET_FLAG}}`.
 
 ### 5. Validate
 
-* Run `python3 scripts/skill_linter.py .agent-src.uncompressed/skills/script-writing/SKILL.md` → 0 FAIL
+* Run `python3 scripts/skill_linter.py .agent-src.uncondensed/skills/script-writing/SKILL.md` → 0 FAIL
 * Run `python3 scripts/{your-script}.py --quiet` and the verbose path — exit code 0 on clean, non-zero on failure regardless of flag
 * If the script uses `_lib/script_output`, add a test under `tests/` patterned on `tests/test_script_output.py` — assert `silent` / `minimal` / `verbose` behave per § 2
 * Run the full CI pipeline locally (see `Taskfile.yml` in this repo for the script list) — must exit 0 except for tolerated warnings