@event4u/agent-config 3.3.0 → 4.2.0

package/.agent-src/commands/feature/plan.md

@@ -147,7 +147,7 @@ I analyzed the code. Here's what I found:
 
 Check if a context document exists for the affected area:
 - `agents/settings/contexts/` for project-wide contexts
-- `app/Modules/{Module}/agents/settings/contexts/` if a module is involved
+- `{module_root}/{Module}/{agent_folder}/settings/contexts/` if a module is involved (resolved via `modules.root_paths` + `modules.agent_folder`; Laravel example: `app/Modules/{Module}/agents/settings/contexts/`)
 
 If a context exists:
 ```
@@ -162,7 +162,9 @@ If no context exists, note this for step 8 (offer to create one after planning).
 
 ### 5b. Determine scope (module vs. project-wide)
 
-Check if `app/Modules/` exists in the project. If yes, ask:
+Resolve module roots via `scripts/_lib/agent_settings.py::enumerate_modules()`
+(reads `modules.root_paths` + `modules.agent_folder` from
+`.agent-project-settings.yml`). If at least one module is discovered, ask:
 
 ```
 Does this feature belong to a specific module?
@@ -172,11 +174,11 @@ Does this feature belong to a specific module?
 ```
 
 If the user chooses a module:
-- List available modules from `app/Modules/`.
+- Render the list of modules from `enumerate_modules()`.
 - Ask which module, or accept the module name directly.
-- Target directories become:
-  - Feature: `app/Modules/{Module}/agents/features/`
-  - Roadmaps (later): `app/Modules/{Module}/agents/roadmaps/`
+- Target directories become (Laravel example shown in parentheses):
+  - Feature: `{module_root}/{Module}/{agent_folder}/features/` (`app/Modules/{Module}/agents/features/`)
+  - Roadmaps (later): `{module_root}/{Module}/{agent_folder}/roadmaps/` (`app/Modules/{Module}/agents/roadmaps/`)
   - Create directories if they don't exist (with `.gitkeep`).
 
 If project-wide:
@@ -258,7 +260,7 @@ If picked **2** → continue.
 
 - Read `.augment/templates/features.md` for the structure.
 - Create the feature file in the target directory determined in step 5a:
-  - Module: `app/Modules/{Module}/agents/features/{feature-name}.md`
+  - Module: `{module_root}/{Module}/{agent_folder}/features/{feature-name}.md` (Laravel example: `app/Modules/{Module}/agents/features/{feature-name}.md`)
   - Project-wide: `agents/features/{feature-name}.md`
 - Fill in all sections based on the conversation.
 - Set the `Module` field in the feature doc accordingly.
@@ -270,7 +272,7 @@ If picked **2** → continue.
 What should the feature be named?
 
 Suggestion: {suggested-kebab-case-name}
-{If module: "Target: app/Modules/{Module}/agents/features/{name}.md"}
+{If module: "Target: {module_root}/{Module}/{agent_folder}/features/{name}.md"}
 {If root: "Target: agents/features/{name}.md"}
 ```
 

package/.agent-src/commands/feature/refactor.md

@@ -30,7 +30,9 @@ install:
 ### 1. Find the feature
 
 - List all feature plans in `agents/features/`.
-- Also check module-level `app/Modules/*/agents/features/` directories.
+- Also check module-level feature dirs via `enumerate_modules()` — for
+  each module, look in `{module_path}/{modules.agent_folder}/features/`
+  (Laravel shape: `app/Modules/*/agents/features/`).
 
 If only one feature exists, load it directly.
 If multiple exist, show a list:

package/.agent-src/commands/feature/roadmap.md

@@ -30,7 +30,9 @@ install:
 ### 1. Find the feature
 
 - List feature plans in `agents/features/`.
-- Also check module-level `app/Modules/*/agents/features/`.
+- Also check module-level feature dirs via `enumerate_modules()` — for
+  each module, look in `{module_path}/{modules.agent_folder}/features/`
+  (Laravel shape: `app/Modules/*/agents/features/`).
 
 If the user specified a feature name, load it directly.
 Otherwise show a list and ask:
@@ -117,7 +119,7 @@ For each roadmap, work through the phases interactively:
 - Read `.augment/templates/roadmaps.md` for the format.
 - Determine the target directory from the feature's location:
   - Feature in `agents/features/` → roadmap in `agents/roadmaps/`
-  - Feature in `app/Modules/{Module}/agents/features/` → roadmap in `app/Modules/{Module}/agents/roadmaps/`
+  - Feature in `{module_root}/{Module}/{agent_folder}/features/` → roadmap in `{module_root}/{Module}/{agent_folder}/roadmaps/` (Laravel example: `app/Modules/{Module}/agents/features/` → `app/Modules/{Module}/agents/roadmaps/`)
 - Create the target directory if it doesn't exist.
 
 **Naming convention:**
@@ -130,8 +132,9 @@ nested subdirs:
 
 ```bash
 find agents/roadmaps -type f -iname "{feature-name}.md" 2>/dev/null
-# Module-scoped:
-find app/Modules/{Module}/agents/roadmaps -type f -iname "{feature-name}.md" 2>/dev/null
+# Module-scoped (Laravel example shown; substitute the discovered module path):
+find {module_root}/{Module}/{agent_folder}/roadmaps -type f -iname "{feature-name}.md" 2>/dev/null
+# e.g. find app/Modules/{Module}/agents/roadmaps -type f -iname "{feature-name}.md"
 ```
 
 If any planned name already exists anywhere under the namespace,

package/.agent-src/commands/fix/portability.md

@@ -88,7 +88,7 @@ Present a summary:
 
 ### 5. Apply fixes
 
-Edit files in `.agent-src.uncompressed/`, then run `bash scripts/compress.sh --sync` to regenerate `.agent-src/` and `.augment/`.
+Edit files in `.agent-src.uncondensed/`, then run `bash scripts/condense.sh --sync` to regenerate `.agent-src/` and `.augment/`.
 
 After all fixes, re-run:
 
@@ -101,12 +101,12 @@ python3 scripts/check_portability.py
 For each modified file:
 
 ```bash
-python3 scripts/compress.py --mark-done "{relative_path}"
+python3 scripts/condense.py --mark-done "{relative_path}"
 ```
 
 ## Rules
 
-- **Always fix in `.agent-src.uncompressed/`** — never edit `.augment/` directly.
+- **Always fix in `.agent-src.uncondensed/`** — never edit `.augment/` directly.
 - **Copy to `.augment/`** after fixing.
 - **Do NOT commit or push.**
 - **`agents/` directory is allowed** to have project-specific references — skip it.

package/.agent-src/commands/fix/refs.md

@@ -83,7 +83,7 @@ Present a summary before applying:
 
 ### 5. Apply fixes
 
-Edit files in `.agent-src.uncompressed/` (source of truth). Regenerate `.agent-src/` and `.augment/` via `bash scripts/compress.sh --sync`.
+Edit files in `.agent-src.uncondensed/` (source of truth). Regenerate `.agent-src/` and `.augment/` via `bash scripts/condense.sh --sync`.
 
 After all fixes:
 
@@ -98,13 +98,13 @@ Show final result.
 For each modified file:
 
 ```bash
-python3 scripts/compress.py --mark-done "{relative_path}"
+python3 scripts/condense.py --mark-done "{relative_path}"
 ```
 
 ## Rules
 
-- **Always fix in `.agent-src.uncompressed/`** — never edit `.agent-src/` or `.augment/` directly.
-- **Run `bash scripts/compress.sh --sync`** after fixing to regenerate `.agent-src/` and `.augment/`.
+- **Always fix in `.agent-src.uncondensed/`** — never edit `.agent-src/` or `.augment/` directly.
+- **Run `bash scripts/condense.sh --sync`** after fixing to regenerate `.agent-src/` and `.augment/`.
 - **Do NOT commit or push** — the user decides.
 - **Do NOT fix references in code blocks** — they are examples, not live refs.
 - **Do NOT auto-fix without showing the summary first.**

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

@@ -85,7 +85,7 @@ Cluster locked in
   [`ghostwriter-schema § exclusions`](../docs/contracts/ghostwriter-schema.md).
 - **No commit / push / PR** unless the sub-command explicitly authorises
   it (none currently do).
-- **Edit `.agent-src.uncompressed/` only.** `.agent-src/` and `.augment/`
+- **Edit `.agent-src.uncondensed/` only.** `.agent-src/` and `.augment/`
   regenerate from source.
 
 ## Storage model (recap)
@@ -94,7 +94,7 @@ Cluster locked in
 |---|---|---|
 | `agents/reference/ghostwriter/<slug>.md` (consumer) | Real-person public-figure profiles | **No** — gitignored by default. `--shared` opt-in deferred to v2. |
 | `agents/reference/ghostwriter/README.md` (consumer) | Directory anchor + how-to | Yes |
-| `.agent-src.uncompressed/ghostwriter/*.md` (package) | `fictional: true` fixtures only | Yes — CI-enforced by `scripts/lint_ghostwriter_source.py` |
+| `.agent-src.uncondensed/ghostwriter/*.md` (package) | `fictional: true` fixtures only | Yes — CI-enforced by `scripts/lint_ghostwriter_source.py` |
 
 Slug = full-name kebab-case with optional `-<discriminator>` suffix
 (`alice-walker` vs `alice-walker-novelist`). The package never

package/.agent-src/commands/memory/learn-low-impact.md

@@ -29,7 +29,7 @@ install:
 Promote `## Validated` entries from
 [`agents/decisions/low-impact-decisions.md`](../../agents/decisions/low-impact-decisions.md)
 into the upstream seed at
-`.agent-src.uncompressed/data/low-impact-decisions-seed.md` via a DRAFT
+`.agent-src.uncondensed/data/low-impact-decisions-seed.md` via a DRAFT
 PR against the agent-config package. **Validated entries only** — probation
 entries never upstream, they're unconfirmed signal.
 
@@ -65,7 +65,7 @@ the project-local corpus and the package seed:
 from scripts.ai_council.learn_low_impact_preview import build_preview
 plan = build_preview(
     corpus_path="agents/decisions/low-impact-decisions.md",
-    seed_path=".agent-src.uncompressed/data/low-impact-decisions-seed.md",
+    seed_path=".agent-src.uncondensed/data/low-impact-decisions-seed.md",
     repo_slug="<owner>/<repo>",  # from `git remote get-url origin`
     repo_root="<absolute repo root>",
     private_domains=(),   # from .agent-settings.yml policy
@@ -109,7 +109,7 @@ seed: <path>
   the refusals and stop. Otherwise invoke
   [`upstream-contribute`](../skills/upstream-contribute/SKILL.md)
   with:
-    - **target file:** `.agent-src.uncompressed/data/low-impact-decisions-seed.md`
+    - **target file:** `.agent-src.uncondensed/data/low-impact-decisions-seed.md`
     - **PR title:** `plan.render_pr_body()` first heading
     - **PR body:** `plan.render_pr_body()`
     - **patch:** `plan.render_diff()`

package/.agent-src/commands/module/explore.md

@@ -27,7 +27,19 @@ install:
 # /module explore
 ## Instructions
 
-### 1. Check for modules
+### 1. Resolve module roots
+
+Read the `modules:` block from `.agent-project-settings.yml` via the
+loader (`get_modules_config()` in `scripts/_lib/agent_settings.py`):
+
+- If `modules.enabled` is `true` and `modules.root_paths` is non-empty,
+  use those paths verbatim. Skip the fallback table.
+- If the block is missing / disabled / empty, fall back to the
+  auto-detection table below — same shape `propose_modules_config.py`
+  uses internally.
+
+**Auto-detection fallback table** (consulted only when `modules:` is
+unset):
 
 - **Laravel HMVC**: Check `app/Modules/`.
 - **Symfony / DDD-lite**: Check `src/<Domain>/` or `src/Module/<Domain>/`.
@@ -43,7 +55,11 @@ install:
 
 ### 2. List available modules
 
-Scan the detected modules directory (see step 1) and show all modules. Skip `.module-template`, `.example`, and hidden dirs:
+Enumerate modules across every resolved root via `enumerate_modules()`
+(see `scripts/_lib/agent_settings.py`). Skip directories listed in
+`modules.skip_dirs` (defaults: `.module-template`, `.example`) and
+hidden dirs. The "Agent Docs" column reflects the configured
+`modules.agent_folder` (default `agents/`):
 
 ```
 📦 Available modules:
@@ -60,7 +76,15 @@ Which module do you want to explore? (number or name)
 
 ### 3. Analyze the module
 
-For the selected module, gather in parallel:
+Resolve `{agent_folder}` from `modules.agent_folder` (default `agents`).
+Let `{module_dir}` be the selected module's `module_path` from
+`enumerate_modules()`. For the selected module, gather in parallel:
+
+**Auto-load module contexts (entry-point hook):**
+- If `{module_dir}/{agent_folder}/settings/contexts/` exists, read every
+  `*.md` it ships and surface it into the conversation context per the
+  same conventions as [`commands/context/create.md`](../context/create.md).
+- Skip silently when the folder is absent — never error.
 
 **Structure:**
 - List all directories and files (2 levels deep)
@@ -70,20 +94,21 @@ For the selected module, gather in parallel:
 **Code:**
 - Use `codebase-retrieval` to understand the module's purpose and key classes
 - Read `README.md` if it exists
-- Read agent docs (`agents/`) if they exist — including features, roadmaps, contexts
+- Read agent docs (`{module_dir}/{agent_folder}/`) if they exist — features, roadmaps, contexts
 - Read `Docs/` if it exists (human-facing documentation)
 
 **Tests:**
 - Count test files per suite (Unit, Component, Integration)
 
 **Roadmaps:**
-- Check `agents/roadmaps/*.md` for active roadmaps
+- Check `{module_dir}/{agent_folder}/roadmaps/*.md` for active roadmaps
 - For each: count completed vs total steps (e.g. "3/7 steps done")
 - Highlight the next open step
 
 **Context:**
-- Check `agents/settings/contexts/` for existing context docs (project-root and module-level)
-- Check `agents/features/` for related feature plans
+- Check `{module_dir}/{agent_folder}/settings/contexts/` for module-level context docs (already surfaced by the auto-load hook above)
+- Check `agents/settings/contexts/` for project-root contexts
+- Check `{module_dir}/{agent_folder}/features/` for related feature plans
 
 ### 4. Display module overview
 
@@ -124,7 +149,8 @@ STRUCTURE:
 NAMESPACE:
 ───────────────────────────────────────────────
 
-  App\Modules\{ModuleName}\App\
+  {modules.namespace_template substituted with {ModuleName}, or
+   "—" when the stack has no PHP-style namespace}
 
 ───────────────────────────────────────────────
 KEY CLASSES:

package/.agent-src/commands/optimize/agents-dir.md

@@ -28,7 +28,9 @@ install:
 
 One command for everything that touches the **`agents/` folder** — the
 project's prose layer (features, contexts, roadmaps, overrides) and the
-mirror dirs under `app/Modules/*/agents/`. Replaces the legacy three-leaf
+mirror dirs under each module's `{agent_folder}/` (per
+`modules.root_paths` + `modules.agent_folder`; Laravel shape:
+`app/Modules/*/agents/`). Replaces the legacy three-leaf
 surface (`/agents prepare` + `/agents audit` + `/agents cleanup`) with
 one entry-point and three explicit modes.
 
@@ -41,7 +43,7 @@ one entry-point and three explicit modes.
 | Flag | Mode | Was | What it does |
 |---|---|---|---|
 | `--scaffold` | scaffold | `/agents prepare` | Create `agents/`, `agents/features/`, `agents/settings/contexts/`, `agents/roadmaps/`, module mirrors, `.gitkeep` files |
-| `--audit` | folder-audit | `/agents audit` | Read-only inventory of `agents/`, module agents, overrides; flag duplicates, orphans, structural drift |
+| `--audit` | folder-audit | `/agents audit` | Read-only inventory of `agents/`, per-module agent docs (via `enumerate_modules()`), overrides; flag duplicates, orphans, structural drift |
 | `--fix` | fix | `/agents cleanup` | Execute actions from a prior `--audit` (or roadmap) — move, merge, delete, update; per-action confirmation |
 
 **No flag → interactive wizard.** Print the table above, ask:
@@ -62,7 +64,7 @@ surface changes.
 
 1. **Verify project root** — look for `composer.json`, `artisan`, or `package.json`.
 2. **Create directory structure** — `agents/{roadmaps,features,contexts}/.gitkeep` + `.augment/guidelines/php/.gitkeep`. Skip dirs that already exist with content.
-3. **Module support** — if `app/Modules/` exists, mirror the layout in every module: `app/Modules/{Module}/agents/{roadmaps,features,contexts}/.gitkeep`.
+3. **Module support** — resolve module roots via `scripts/_lib/agent_settings.py::enumerate_modules()`. For every discovered module, mirror the layout: `{module_root}/{Module}/{agent_folder}/{roadmaps,features,contexts}/.gitkeep` (Laravel example: `app/Modules/{Module}/agents/{roadmaps,features,contexts}/.gitkeep`). Skip when `modules.enabled: false` or no roots configured.
 4. **Verify templates** — confirm `.augment/templates/{features,roadmaps,contexts}.md` exist; warn on missing.
 5. **Clean up old templates** — offer to delete legacy `agents/features/template.md` etc. (now in `.augment/templates/`); ask before delete.
 6. **Show summary** — table with status per directory and template; flag missing as `⚠️`.
@@ -71,8 +73,8 @@ surface changes.
 
 ### `--audit` (was the folder side of `/agents audit`)
 
-1. **Inventory all agent docs** — `find agents/ -maxdepth 1`, `agents/features/`, `agents/settings/contexts/`, `agents/overrides/`, `.augment/guidelines/`, `app/Modules/*/agents/`. For each: filename, first heading, size, last `git log` date.
-2. **Module coverage** — for every `app/Modules/*/`: docs count, presence of description file, features dir, contexts dir; flag inactive modules with no docs as `🔵 Info` only.
+1. **Inventory all agent docs** — `find agents/ -maxdepth 1`, `agents/features/`, `agents/settings/contexts/`, `agents/overrides/`, `.augment/guidelines/`, and per-module `{module_path}/{agent_folder}/` (resolved via `enumerate_modules()`). For each: filename, first heading, size, last `git log` date.
+2. **Module coverage** — for every module returned by `enumerate_modules()`: docs count, presence of description file, features dir, contexts dir; flag inactive modules with no docs as `🔵 Info` only.
 3. **Scan overrides** — for every `agents/overrides/*.md`: extract `Mode:` (`extend`/`replace`) and `Original:` headers; check the original file exists; flag orphans.
 4. **Classify documents** — `Architecture / Convention / Pattern / Feature / Context / Module Doc / Override / Unclear`.
 5. **Detect issues**:
@@ -90,7 +92,7 @@ surface changes.
    Roadmap phases: critical fixes → structural cleanup → fill gaps → cleanup.
 8. **Offer next steps** — `/optimize agents-dir --fix`, `/context refactor`, or done.
 
-**Rules:** read-only — no file edits; do NOT audit `agents/roadmaps/` or `app/Modules/*/agents/roadmaps/` (separate lifecycle); do NOT audit `.augment/` (route to `/agents audit`); be specific (file, reference, what's wrong); don't flag inactive modules.
+**Rules:** read-only — no file edits; do NOT audit `agents/roadmaps/` or per-module `{module_path}/{agent_folder}/roadmaps/` (separate lifecycle); do NOT audit `.augment/` (route to `/agents audit`); be specific (file, reference, what's wrong); don't flag inactive modules.
 
 ### `--fix` (was `/agents cleanup`)
 
@@ -114,7 +116,7 @@ surface changes.
 - **No commits, no push, no PR** — finishing is a user decision per
   [`commit-policy`](../../rules/commit-policy.md).
 - **No edits to `.agent-src/` or `.augment/`** — those regenerate from
-  `.agent-src.uncompressed/`. Edit the source.
+  `.agent-src.uncondensed/`. Edit the source.
 
 ## See also
 

package/.agent-src/commands/optimize/augmentignore.md

@@ -29,7 +29,7 @@ Scans the project to find files that waste tokens in Augment's retrieval index
 and creates/updates `.augmentignore` accordingly. Also identifies irrelevant
 `.augment/skills/` and `.augment/rules/` to exclude them from the system prompt.
 
-**Source of truth for skills/rules:** `.agent-src.uncompressed/` — scan there, not `.agent-src/` or `.augment/`.
+**Source of truth for skills/rules:** `.agent-src.uncondensed/` — scan there, not `.agent-src/` or `.augment/`.
 
 ## Steps
 
@@ -308,7 +308,7 @@ echo "Rules ignored: $rules_count"
 - **When in doubt, ignore files** — false positive is easy to fix, false negative wastes tokens silently.
 - **When in doubt, keep skills** — ignoring a needed skill causes bad output, keeping an unneeded one just wastes ~3 lines.
 - **Never ignore always-active rules** — only auto-loaded rules (those with `description` frontmatter) may be ignored.
-- **Never ignore meta / agent-system skills** — these are framework-independent and used by every project regardless of stack: `agent-docs-writing`, `agents-md-thin-root`, `check-refs`, `command-routing`, `command-writing`, `compress-memory`, `context-authoring`, `copilot-agents-optimization`, `copilot-config`, `description-assist`, `file-editor`, `guideline-writing`, `learning-to-rule-or-skill`, `lint-skills`, `md-language-check`, `override-management`, `persona-writing`, `project-analyzer`, `project-docs`, `project-health`, `roadmap-writing`, `rule-writing`, `skill-improvement-pipeline`, `skill-management`, `skill-reviewer`, `skill-writing`.
+- **Never ignore meta / agent-system skills** — these are framework-independent and used by every project regardless of stack: `agent-docs-writing`, `agents-md-thin-root`, `check-refs`, `command-routing`, `command-writing`, `condense-memory`, `context-authoring`, `copilot-agents-optimization`, `copilot-config`, `description-assist`, `file-editor`, `guideline-writing`, `learning-to-rule-or-skill`, `lint-skills`, `md-language-check`, `override-management`, `persona-writing`, `project-analyzer`, `project-docs`, `project-health`, `roadmap-writing`, `rule-writing`, `skill-improvement-pipeline`, `skill-management`, `skill-reviewer`, `skill-writing`.
 - **Restore previously ignored skills** when the stack changes (e.g., Vue added to project → restore `vue` skill).
 
 ## Cloud Behavior

package/.agent-src/commands/optimize/skills.md

@@ -27,19 +27,19 @@ install:
 # /optimize skills
 Skill audit: measure, find duplicates/merge candidates, run linter, present findings. **Suggest only — never auto-apply.**
 
-**Source of truth:** `.agent-src.uncompressed/` — never read or edit `.agent-src/` or `.augment/` directly.
+**Source of truth:** `.agent-src.uncondensed/` — never read or edit `.agent-src/` or `.augment/` directly.
 
 ## Steps
 
 ### 1. Measure baseline
 
 ```bash
-total=$(ls -d .agent-src.uncompressed/skills/*/SKILL.md 2>/dev/null | wc -l | tr -d ' ')
-total_lines=$(cat .agent-src.uncompressed/skills/*/SKILL.md 2>/dev/null | wc -l | tr -d ' ')
+total=$(ls -d .agent-src.uncondensed/skills/*/SKILL.md 2>/dev/null | wc -l | tr -d ' ')
+total_lines=$(cat .agent-src.uncondensed/skills/*/SKILL.md 2>/dev/null | wc -l | tr -d ' ')
 echo "Skills: $total, Total lines: $total_lines"
 
 # Top 15 by size
-for f in .agent-src.uncompressed/skills/*/SKILL.md; do
+for f in .agent-src.uncondensed/skills/*/SKILL.md; do
   name=$(basename $(dirname "$f"))
   lines=$(wc -l < "$f" | tr -d ' ')
   echo "$lines $name"
@@ -49,7 +49,7 @@ done | sort -rn | head -15
 ### 2. Run skill linter
 
 ```bash
-python3 scripts/skill_linter.py --pairs --duplicates .agent-src.uncompressed/skills/*/SKILL.md 2>&1 | tail -20
+python3 scripts/skill_linter.py --pairs --duplicates .agent-src.uncondensed/skills/*/SKILL.md 2>&1 | tail -20
 ```
 
 Report FAIL/WARN counts. Do NOT fix linter issues here — that's the linter's or `skill-reviewer`'s job.
@@ -72,7 +72,7 @@ Present as table:
 Skills with overlapping trigger descriptions that might load simultaneously:
 
 ```bash
-for f in .agent-src.uncompressed/skills/*/SKILL.md; do
+for f in .agent-src.uncondensed/skills/*/SKILL.md; do
   name=$(basename $(dirname "$f"))
   desc=$(grep 'description:' "$f" | head -1 | sed 's/.*"\(.*\)"/\1/')
   echo "$name | $desc"
@@ -84,7 +84,7 @@ Flag pairs where descriptions target the same scenario.
 ### 5. Check sizes
 
 ```bash
-for f in .agent-src.uncompressed/skills/*/SKILL.md; do
+for f in .agent-src.uncondensed/skills/*/SKILL.md; do
   name=$(basename $(dirname "$f"))
   lines=$(wc -l < "$f" | tr -d ' ')
   [ "$lines" -gt 300 ] && echo "⚠️  $name — $lines lines"
@@ -134,6 +134,6 @@ If any check fails: do NOT suggest the change.
 
 - **No quality judgments** — the skill linter and `skill-reviewer` handle that
 - **No auto-fixes** — all changes require explicit user approval
-- **No "make it shorter"** — compression is done by Caveman Compression, not here
+- **No "make it shorter"** — condensation is done by Telegraph Condensation, not here
 - **No Killer checks** — replaced by the skill linter (`scripts/skill_linter.py`)
-- **No edits to `.agent-src/` or `.augment/`** — always edit `.agent-src.uncompressed/`, then sync
+- **No edits to `.agent-src/` or `.augment/`** — always edit `.agent-src.uncondensed/`, then sync

package/.agent-src/commands/post-as.md

@@ -60,7 +60,7 @@ Cluster locked in
 - **Do NOT omit the disclosure footer from `:ghostwriter`** — it is
   mandatory on every invocation. `:me` omits it because the user is
   the author.
-- **Edit `.agent-src.uncompressed/` only.** `.agent-src/` and
+- **Edit `.agent-src.uncondensed/` only.** `.agent-src/` and
   `.augment/` regenerate from source.
 
 ## See also

package/.agent-src/commands/project-analyze.md

@@ -37,7 +37,7 @@ Gather in parallel:
 - Check for: `artisan`, `Makefile`, `Taskfile.yml`, `docker-compose.yml`
 - Check for: `phpstan.neon`, `ecs.php`, `rector.php`, `config-dev/`
 - Check for: `.github/workflows/`, `CODEOWNERS`, `.editorconfig`
-- Check for: `app/Modules/`, multi-tenant indicators (`customer_database`)
+- Check for module roots (resolve via `scripts/_lib/agent_settings.py::enumerate_modules()`; Laravel shape: `app/Modules/`), multi-tenant indicators (`customer_database`)
 - Read: `AGENTS.md`, `.github/copilot-instructions.md` (if exist)
 
 Display:
@@ -138,7 +138,7 @@ CODE INVENTORY:
 
 ### Phase 3: Module inventory (if modules exist)
 
-If `app/Modules/` exists, analyze each module:
+If `enumerate_modules()` returns any modules (Laravel shape: `app/Modules/` exists), analyze each module:
 
 ```
 ───────────────────────────────────────────────

package/.agent-src/commands/project-health.md

@@ -35,8 +35,9 @@ Run in parallel:
 - `git branch --show-current` → current branch
 - `git log --oneline -3` → recent activity
 - Count files in `agents/` (docs, features, roadmaps, contexts)
-- Count files in `app/Modules/*/agents/` (per module)
-- Check `app/Modules/` for module list
+- Resolve modules via `scripts/_lib/agent_settings.py::enumerate_modules()`
+- For every module: count files in `{module_path}/{modules.agent_folder}/` (Laravel shape: `app/Modules/*/agents/`)
+- Module list comes from `enumerate_modules()` (Laravel shape: `app/Modules/`)
 - Count test files
 
 ### 2. Display health report

package/.agent-src/commands/research/deep.md

@@ -99,7 +99,7 @@ Read {fields_path} to get all field definitions.
 
 ## Validation (no Python, no host paths)
 Self-validate the JSON against
-`<package>/.agent-src.uncompressed/contexts/contracts/research-schema.md`
+`<package>/.agent-src.uncondensed/contexts/contracts/research-schema.md`
 in memory before writing. The well-formedness escape hatch is
 `jq -e '.[]' {output_path}` — agent runs it after write and re-tries
 once on failure. Task is complete only after both checks pass.

package/.agent-src/commands/research/report.md

@@ -88,7 +88,7 @@ script, no Python runtime.**
 | **Nested dict** | Recurse; render with `;` between sibling keys or hard-break on long values. |
 | **Long text** | Strings > 100 chars → wrap in a blockquote or insert `<br>`. |
 | **Extra fields** | JSON keys not declared in `fields.yaml` → group under `### Other info`. Filter `_source_file`, `uncertain`, and category-container keys. |
-| **`uncertain` array** | Render each entry on its own line under `### Uncertain fields`; never compress to a one-liner. |
+| **`uncertain` array** | Render each entry on its own line under `### Uncertain fields`; never condense to a one-liner. |
 | **Skip conditions** | Field value contains `[uncertain]` · field name in `uncertain` · value is `null` / empty string. |
 
 ### Step 5 — Optional `jq` template (deterministic regenerate)

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

@@ -59,7 +59,7 @@ for narrative structure, mental-models lens for object selection).
 - **Do NOT chain sub-commands.** One `/research[:<sub>]` per turn.
 - If the user invokes `/research` with no argument, **show the menu** —
   do not guess whether they meant the bare workflow or a sub-command.
-- **Edit `.agent-src.uncompressed/` only.** `.agent-src/` and `.augment/`
+- **Edit `.agent-src.uncondensed/` only.** `.agent-src/` and `.augment/`
   regenerate from source.
 
 ## Trigger

package/.agent-src/commands/roadmap/ai-council.md

@@ -33,7 +33,7 @@ Council-driven challenge + refactor scope of the
 artefact), then drives the user through applying convergence
 findings as numbered patches against the roadmap file.
 
-**Source of truth:** `.agent-src.uncompressed/` — never read or edit
+**Source of truth:** `.agent-src.uncondensed/` — never read or edit
 `.agent-src/` or `.augment/` directly.
 
 ## Instructions

package/.agent-src/commands/roadmap/create.md

@@ -32,10 +32,14 @@ install:
 Ask the user (in their language) where the roadmap should be created:
 
 > 1. Project root (`agents/roadmaps/`)
-> 2. In a module (`app/Modules/{Name}/agents/roadmaps/`)
+> 2. In a module (`{module_root}/{Name}/{agent_folder}/roadmaps/`)
 
-If the user picks a module → ask which module (list available modules if needed).
-Create the `agents/roadmaps/` directory if it doesn't exist at the chosen location.
+If the user picks a module → resolve module roots via
+`scripts/_lib/agent_settings.py::enumerate_modules()`, list available
+modules from `modules.root_paths`, and ask which one. The target
+directory is `{module_path}/{modules.agent_folder}/roadmaps/`
+(default `agent_folder` = `agents`).
+Create the `roadmaps/` directory if it doesn't exist at the chosen location.
 
 ### 2. Read the roadmap template
 
@@ -117,7 +121,8 @@ NAME="<kebab-case-name>.md"
 # Project-root roadmaps:
 find agents/roadmaps -type f -iname "$NAME" 2>/dev/null
 # Module-scoped roadmaps (only if step 1 picked a module):
-find app/Modules/<Module>/agents/roadmaps -type f -iname "$NAME" 2>/dev/null
+# resolve <ModuleRoot>/<Module>/<AgentFolder>/roadmaps/ via enumerate_modules()
+find <ModuleRoot>/<Module>/<AgentFolder>/roadmaps -type f -iname "$NAME" 2>/dev/null
 ```
 
 Use `-iname` (case-insensitive) so case-only differences still count

package/.agent-src/commands/rule-compliance-audit.md

@@ -27,7 +27,7 @@ install:
 
 ### 1. Inventory all rules
 
-Read every `.md` file in `.agent-src.uncompressed/rules/`. For each rule, extract:
+Read every `.md` file in `.agent-src.uncondensed/rules/`. For each rule, extract:
 
 - **Name** (filename without `.md`)
 - **Type** (`always` or `auto`)

package/.agent-src/commands/upstream-contribute.md

@@ -76,12 +76,12 @@ If project-specific content is found, ask:
 
 ### 3. Determine contribution type and target path
 
-| Type | Uncompressed target | Compressed target |
+| Type | Uncondensed target | Condensed target |
 |---|---|---|
-| **Skill** | `.agent-src.uncompressed/skills/{name}/SKILL.md` | `.agent-src/skills/{name}/SKILL.md` |
-| **Rule** | `.agent-src.uncompressed/rules/{name}.md` | `.agent-src/rules/{name}.md` |
-| **Command** | `.agent-src.uncompressed/commands/{name}.md` | `.agent-src/commands/{name}.md` |
-| **Guideline** | `docs/guidelines/{cat}/{name}.md` | _(not compressed; reference-only)_ |
+| **Skill** | `.agent-src.uncondensed/skills/{name}/SKILL.md` | `.agent-src/skills/{name}/SKILL.md` |
+| **Rule** | `.agent-src.uncondensed/rules/{name}.md` | `.agent-src/rules/{name}.md` |
+| **Command** | `.agent-src.uncondensed/commands/{name}.md` | `.agent-src/commands/{name}.md` |
+| **Guideline** | `docs/guidelines/{cat}/{name}.md` | _(not condensed; reference-only)_ |
 
 ### 4. Get access to the package repo
 
@@ -117,10 +117,10 @@ git checkout main && git pull
 git checkout -b {type}/{name}  # e.g. feat/skills/php-container-discovery
 ```
 
-Write the **uncompressed version** (full, verbose, human-readable).
-Write the **compressed version** (token-efficient, 40-60% shorter for skills; 1:1 for rules/commands).
+Write the **uncondensed version** (full, verbose, human-readable).
+Write the **condensed version** (token-efficient, 40-60% shorter for skills; 1:1 for rules/commands).
 
-Compressed version MUST preserve:
+Condensed version MUST preserve:
 
 - All code blocks (byte-for-byte)
 - YAML frontmatter (verbatim)
@@ -133,10 +133,10 @@ Frontmatter must have `source: package`.
 
 ```bash
 python3 scripts/skill_linter.py --all           # 0 FAIL required
-python3 scripts/check_compression.py            # No 🔴 errors for this file
-python3 scripts/compress.py --generate-tools    # Regenerate symlinks
-bash scripts/compress.sh --check                # .agent-src/ in sync with source
-bash scripts/compress.sh --check-hashes         # All hashes match
+python3 scripts/check_condensation.py            # No 🔴 errors for this file
+python3 scripts/condense.py --generate-tools    # Regenerate symlinks
+bash scripts/condense.sh --check                # .agent-src/ in sync with source
+bash scripts/condense.sh --check-hashes         # All hashes match
 ```
 
 Fix any issues before continuing.
@@ -148,8 +148,8 @@ Fix any issues before continuing.
 ```
 > ✅ Files created in {package-repo}:
 >
-> - `.agent-src.uncompressed/{type}/{name}` (uncompressed)
-> - `.agent-src/{type}/{name}` (compressed)
+> - `.agent-src.uncondensed/{type}/{name}` (uncondensed)
+> - `.agent-src/{type}/{name}` (condensed)
 >
 > Quality gates: {pass/fail summary}
 >

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

@@ -43,7 +43,7 @@ with a precise diff — no silent best-guess.
 ### 1. Validate dependencies
 
 ```bash
-scripts/ai-video/lib/validate-deps.sh .agent-src.uncompressed/commands/video/from-script.md
+scripts/ai-video/lib/validate-deps.sh .agent-src.uncondensed/commands/video/from-script.md
 ```
 
 Fails fast with the missing-id list if any declared persona / skill is

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

@@ -43,7 +43,7 @@ the run with a precise diff.
 ### 1. Validate dependencies
 
 ```bash
-scripts/ai-video/lib/validate-deps.sh .agent-src.uncompressed/commands/video/scene.md
+scripts/ai-video/lib/validate-deps.sh .agent-src.uncondensed/commands/video/scene.md
 ```
 
 ### 2. Load config + resolve providers

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

@@ -43,7 +43,7 @@ with a precise diff — the operator must say `--skip-scene <id>` or
 ### 1. Validate dependencies
 
 ```bash
-scripts/ai-video/lib/validate-deps.sh .agent-src.uncompressed/commands/video/stitch.md
+scripts/ai-video/lib/validate-deps.sh .agent-src.uncondensed/commands/video/stitch.md
 ```
 
 (Lightweight here — only the `ai-video-technical-director` persona is