@event4u/agent-config 1.9.1

package/.agent-src/commands/memory-full.md

@@ -0,0 +1,97 @@
+---
+name: memory-full
+description: Load ALL curated entries of a given memory type into the current context — opt-in full load for deep analysis, never auto-triggered
+skills: []
+disable-model-invocation: true
+---
+
+# /memory-full
+
+Loads every entry of a single memory type into the current conversation
+as a formatted block. Use when the normal `memory_lookup` filter is too
+narrow and you need the full type for an architecture decision, audit,
+or migration.
+
+Opt-in only. Agents must never call this implicitly — the cost is linear
+in the entry count and the signal-to-noise degrades fast on large types.
+
+## Prerequisites
+
+- Consumer project has `agents/memory/<type>/` or
+  `agents/memory/<type>.yml`.
+- User explicitly asked for the full view (e.g. "show me everything we
+  know about `domain-invariants`").
+
+## Steps
+
+### 1. Pick the type
+
+```
+> Which memory type should I load in full?
+>
+> 1. domain-invariants
+> 2. architecture-decisions
+> 3. incident-learnings
+> 4. product-rules
+> 5. historical-patterns
+> 6. ownership
+```
+
+### 2. Warn about volume
+
+Before loading, count the entries:
+
+```bash
+python3 scripts/memory_lookup.py --types <type> --format json | \
+  python3 -c "import sys, json; print(len(json.load(sys.stdin)))"
+```
+
+If the count exceeds 25, warn:
+
+```
+> This will load {N} entries (~{N×200} tokens).
+>
+> 1. Continue — load everything
+> 2. Narrow by key — run /memory-full with --key pattern
+> 3. Cancel
+```
+
+### 3. Load
+
+```bash
+python3 scripts/memory_lookup.py --types <type> --format yaml
+```
+
+Render the output verbatim, grouped by status (`active` first, then
+`deprecated`, then `archived`). Each entry shows `id`, `confidence`,
+`last_validated`, and the rule body. Skip `archived` unless the user
+opts in.
+
+### 4. Confirm absorption
+
+```
+✅  Loaded {N} {type} entries into context.
+    Active: {n_active}  · Deprecated: {n_dep}  · Archived skipped: {n_arch}
+    Source: agents/memory/{type}/ (or agents/memory/{type}.yml)
+```
+
+The agent should now treat every loaded entry as an authority signal
+with its declared `confidence` — see
+[`memory-access`](../guidelines/agent-infra/memory-access.md) for
+how entries modulate edits.
+
+## When to reject
+
+- User is mid-implementation and asks for the full load as a shortcut
+  around a targeted `memory_lookup` call — redirect to the narrower
+  lookup; full load is for analysis/audit, not coding.
+- Type directory is empty — respond with "no entries yet, use
+  `/memory-add` to start".
+
+## See also
+
+- [`memory-add`](memory-add.md) — add a single entry
+- [`memory-promote`](memory-promote.md) — promote an intake signal to
+  a curated entry
+- [`memory-access`](../guidelines/agent-infra/memory-access.md) —
+  how entries flow into agent decisions

package/.agent-src/commands/memory-promote.md

@@ -0,0 +1,144 @@
+---
+name: memory-promote
+description: Promote an intake signal (or provisional proposal) into a curated memory entry — opens a PR and runs the admission gate.
+skills: [file-editor]
+disable-model-invocation: true
+---
+
+# /memory-promote
+
+Moves an entry from the provisional layer (intake JSONL) into the
+curated layer (`agents/memory/<type>.yml` or sharded). Promotion is
+gated by
+[`scripts/check_memory_proposal.py`](../../../scripts/check_memory_proposal.py),
+which enforces the **pattern-vs-one-off** discipline: either ≥ 2
+distinct paths share the root-cause signature, or the submitter
+supplies ≥ 3 concrete future decisions that will be steered by the
+entry.
+
+## Prerequisites
+
+- The signal already exists in `agents/memory/intake/signals-*.jsonl`
+  via [`/propose-memory`](propose-memory.md) or a producer
+  (`/bug-fix`, `/do-and-judge`, incident-role exit).
+- The user can name the intake `id` (e.g., `sig-abc123`). If not,
+  route to the read side:
+  `python3 scripts/memory_lookup.py --types <type> --key <hint>` to
+  surface candidates.
+
+## Steps
+
+### 1. Confirm the signal id
+
+```
+> Which intake signal are we promoting?
+>
+> 1. Paste `sig-xxxxxx`
+> 2. Search by path/body — I'll list candidates
+```
+
+### 2. Run the admission gate
+
+```bash
+python3 scripts/check_memory_proposal.py --intake-id <sig-id>
+```
+
+If the gate reports failures, show them to the user numbered and ask:
+
+```
+> 1. Strengthen evidence — run /propose-memory again to add sibling paths
+> 2. Fill `future_decisions:` — I'll edit the intake entry's metadata
+> 3. Abandon promotion — the finding stays as intake
+```
+
+**Do NOT bypass the gate.** If the user insists, stop and require
+explicit confirmation with `--force` intent. Never silently edit the
+gate script to lower the bar.
+
+### 3. Draft the curated entry
+
+Using the schema in
+[`engineering-memory-data-format`](../guidelines/agent-infra/engineering-memory-data-format.md),
+hydrate the full frontmatter:
+
+- `id` — kebab-case slug (not the `sig-*` id — that is an intake marker).
+- `status: active`, `confidence: medium` (unless the pattern is old
+  and well-validated — then `high`).
+- `source:` — at minimum the intake jsonl file + line number.
+- `owner:`, `last_validated: <today>`, `review_after_days:`.
+- Type-specific fields (`rule`, `symptom`, `path`, …).
+
+Show the YAML draft and ask for confirmation before writing.
+
+### 4. Write the curated entry (content-addressed)
+
+Compute the content hash and write a **one-entry file** at
+`agents/memory/<type>/<hash>.yml`:
+
+```bash
+HASH=$(python3 scripts/memory_hash.py --yaml /tmp/draft.yml)
+mkdir -p agents/memory/<type>
+mv /tmp/draft.yml agents/memory/<type>/${HASH}.yml
+```
+
+- **One entry per file** — the filename is the sha256(canonical-JSON
+  of the entry, first 12 hex chars). Two branches promoting the same
+  entry converge to the same filename and `git merge` sees an
+  unchanged file, not a conflict.
+- **Never append** to `<type>.yml` single-file mode in content-
+  addressed layouts. If the consumer still uses single-file (legacy),
+  the command MUST detect that via `agents/memory/<type>.yml`
+  existence and refuse with a migration hint:
+  `⚠️  agents/memory/<type>.yml exists — migrate to content-
+  addressed first (`/memory-migrate <type>`)`.
+- **Schema validation** — run `python3 scripts/check_memory.py
+  --path agents/memory/<type>/${HASH}.yml` before commit. On failure,
+  delete the file and stop.
+
+### 5. Record the supersede link
+
+Append a `type: supersede` line to the monthly intake JSONL:
+
+```bash
+echo '{"type":"supersede","supersedes":"<sig-id>","promoted_to":"<curated id>"}' \
+    >> agents/memory/intake/signals-$(date +%Y-%m).jsonl
+```
+
+This keeps the intake stream truthful — lookups will ignore the
+superseded signal.
+
+### 6. Open a promotion PR
+
+```bash
+git checkout -b memory/promote-<curated-id>
+git add agents/memory/ && git commit -m "memory: promote <sig-id> → <curated-id>"
+git push -u origin memory/promote-<curated-id>
+# Then route to /create-pr with the memory-promote template hint.
+```
+
+### 7. Report
+
+```
+> ✅ Promotion drafted.
+> - Signal:   <sig-id>
+> - Curated:  <curated-id> in agents/memory/<type>.yml
+> - PR:       <url or branch name>
+> - Next:     review + merge
+```
+
+## Safety
+
+- **Never** rewrite existing curated entries — conflicts go through
+  supersede-chains, not overwrites.
+- **Never** promote without the gate passing — the discipline is the
+  value of the curated layer.
+- **Never** batch-promote more than one signal per PR — each entry
+  deserves a focused review.
+
+## See also
+
+- [`/propose-memory`](propose-memory.md) — write-side entry point.
+- [`/memory-add`](memory-add.md) — direct curated write (skips intake).
+- [`engineering-memory-data-format`](../guidelines/agent-infra/engineering-memory-data-format.md)
+- [`road-to-agent-memory-integration`](../../../agents/roadmaps/road-to-agent-memory-integration.md)
+  — Phase 3.

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

@@ -0,0 +1,121 @@
+---
+name: mode
+description: Set the active role mode — prints the contract, lists default skills, and refuses work outside the contract (see role-contracts)
+disable-model-invocation: true
+---
+
+# /mode
+
+Sets `roles.active_role` in `.agent-settings.yml` and surfaces the active
+contract before any work. Six modes are defined in
+[`role-contracts`](../guidelines/agent-infra/role-contracts.md):
+
+- `developer` · `reviewer` · `tester` · `po` · `incident` · `planner`
+
+`/mode none` clears the active role. `/mode` without an argument prints
+the current state (active role, default role, contract summary).
+
+## When NOT to use
+
+- The mode should be set automatically by the router in Phase 3 — use
+  `/mode` only for explicit override or debugging.
+- Do NOT invent new modes. If the work does not fit a contract, say so
+  and fall back to no mode (per `ask-when-uncertain`).
+
+## Steps
+
+### 1. Parse argument
+
+- `/mode` → show status only (steps 3–4).
+- `/mode none` → clear `roles.active_role` (step 5).
+- `/mode <name>` → validate against the six defined modes (step 2).
+
+Anything else: refuse. List the valid values and stop.
+
+### 2. Validate the mode name
+
+Read [`role-contracts.md`](../guidelines/agent-infra/role-contracts.md).
+Extract H3 headings under `## Contract skeletons` and lowercase them.
+If `<name>` is not in that set, refuse and print the valid list.
+
+### 3. Read settings
+
+Read `.agent-settings.yml`. If missing, tell the user to run
+`/config-agent-settings` first and stop — do not create the file here.
+
+Extract `roles.default_role` and `roles.active_role`.
+
+### 4. Print the contract
+
+Echo the full contract body for the target mode from `role-contracts.md`:
+
+- Goal / Constraints / Output fields
+- Default skills the mode loads first
+- Structured mode marker the agent will emit when closing
+
+Format: rendered Markdown excerpt, not a paraphrase. The user must see
+exactly what the contract demands.
+
+### 5. Write the active role
+
+Update `roles.active_role` in `.agent-settings.yml` using the same
+section-aware merge rules as `/config-agent-settings` (preserve comments,
+preserve key order, touch only the changed field).
+
+For `/mode none`: set `active_role: ""`.
+
+Do NOT write anything for `/mode` without an argument (status only).
+
+### 6. Refuse work outside the contract
+
+Announce the switch as:
+
+```
+> entering {mode} mode — contract: {goal-field} / {constraints-field} / {output-field}
+```
+
+From this point in the session: the rule
+[`role-mode-adherence`](../rules/role-mode-adherence.md) auto-triggers on
+every closing output. If the user asks for work the contract forbids
+(e.g. "just ship this fix" while in reviewer mode), reply with a single
+numbered prompt:
+
+```
+> Current mode: {mode} — contract forbids {forbidden-action}.
+>
+> 1. Switch mode — run /mode <other>
+> 2. Stay in {mode} and scope the work to the contract
+> 3. Clear mode — run /mode none
+```
+
+## Output format
+
+```
+> entering {mode} mode — contract: …
+>
+> Default skills: {skill-a}, {skill-b}, {skill-c}
+> Closing marker: <!-- role-mode: {mode} | contract: … -->
+```
+
+For `/mode` (status only):
+
+```
+> Active role: {active_role or "(none)"}
+> Default role: {default_role or "(none)"}
+```
+
+## Gotchas
+
+- `.agent-settings.yml` is git-ignored. `/mode` never commits the file.
+- If the file is missing the `roles:` section, add it in the correct
+  place (between `subagents:` and EOF) using the template layout.
+- Mode names are case-sensitive in the file; case-insensitive on input.
+- The contract is the source of truth, not this command — if the
+  guideline changes, this command reflects the new contract on next run.
+
+## See also
+
+- [`role-contracts`](../guidelines/agent-infra/role-contracts.md) — the six modes
+- [`role-mode-adherence`](../rules/role-mode-adherence.md) — closing-output gate
+- [`config-agent-settings`](config-agent-settings.md) — baseline settings writer
+- [`ask-when-uncertain`](../rules/ask-when-uncertain.md) — never invent modes

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

@@ -0,0 +1,132 @@
+---
+name: module-create
+skills: [laravel]
+description: Create a new module from .module-template with interactive setup
+disable-model-invocation: true
+---
+
+# module-create
+
+## Instructions
+
+### 1. Check for module support
+
+- Check if `app/Modules/` exists.
+- If not:
+  ```
+  ⚠️  No module system found (no app/Modules/ directory).
+  Should I set up the module structure? (y/n)
+  ```
+  If yes → create `app/Modules/` and check if `ModuleServiceProvider` is registered.
+  If no → stop.
+
+### 2. Check for template
+
+- Check if `app/Modules/.module-template/` exists.
+- If not:
+  ```
+  ⚠️  No module template found (.module-template/).
+  I'll create the module manually based on the standard structure.
+  ```
+
+### 3. Ask for module details
+
+```
+📦 Create new module
+
+1. Module name (PascalCase, e.g. UserProfile, Reporting):
+```
+
+Wait for name. Validate:
+- Must be PascalCase
+- Must not already exist in `app/Modules/`
+- Must not contain special characters
+
+Then ask:
+
+```
+2. Route-Prefix (kebab-case, z.B. user-profile, reporting):
+   Suggestion: {auto-generated-from-name}
+
+3. Short description (one sentence):
+
+4. Which route files should be created?
+   [x] API Routes (Routes/api.php)
+   [ ] Web Routes (Routes/web.php)
+   [x] Console Routes (Routes/console.php)
+```
+
+### 4. Create the module
+
+Copy `.module-template/` to `app/Modules/{ModuleName}/`:
+
+1. Copy all files and directories.
+2. Replace placeholders in all files:
+   - `[MODULE_NAME]` → `{ModuleName}`
+   - `[module-prefix]` → `{route-prefix}`
+3. Update `README.md` with the module description.
+4. Remove unchecked route files.
+5. Create agent directories:
+   ```
+   app/Modules/{ModuleName}/agents/
+   ├── features/.gitkeep
+   ├── roadmaps/.gitkeep
+   └── contexts/.gitkeep
+   ```
+
+### 5. Verify namespace
+
+Check that PSR-4 autoloading is configured for the new module:
+
+```php
+// composer.json → autoload → psr-4
+"App\\Modules\\{ModuleName}\\": "app/Modules/{ModuleName}/"
+```
+
+If not configured, warn:
+```
+⚠️  PSR-4 autoloading not configured for App\Modules\{ModuleName}.
+Please run `composer dump-autoload` or check if a wildcard mapping exists.
+```
+
+### 6. Show result
+
+```
+═══════════════════════════════════════════════
+  ✅  MODULE CREATED: {ModuleName}
+═══════════════════════════════════════════════
+
+📁 app/Modules/{ModuleName}/
+  App/                ✅
+  Routes/             ✅  (api.php, console.php)
+  Tests/              ✅  (Component/, Integration/, Unit/)
+  agents/             ✅  (features/, roadmaps/, contexts/)
+  README.md           ✅
+
+🔗 Namespace: App\Modules\{ModuleName}\App\
+🌐 Route-Prefix: /api/v1/{route-prefix}
+
+═══════════════════════════════════════════════
+```
+
+### 7. Offer context and feature creation
+
+```
+What would you like to do next?
+
+1. 📄 Create module context → /context-create (documents structure & purpose)
+2. 📋 Plan first feature → /feature-plan (Module: {ModuleName})
+3. ✅ Done for now — continue later
+```
+
+- **Option 1:** Transition to `/context-create` with the module pre-selected.
+- **Option 2:** Transition to `/feature-plan` with the module pre-selected.
+- **Option 3:** Remind about `composer dump-autoload` if needed, then stop.
+
+### Rules
+
+- **Do NOT commit or push.**
+- **Do NOT modify existing modules.**
+- **Do NOT run `composer dump-autoload`** — only suggest it.
+- **Always use PascalCase** for module names.
+- **Always create agent directories** with `.gitkeep`.

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

@@ -0,0 +1,157 @@
+---
+name: module-explore
+skills: [laravel]
+description: Explore a module — load its structure, docs, and context into the current conversation
+disable-model-invocation: true
+---
+
+# module-explore
+
+## Instructions
+
+### 1. Check for modules
+
+- **Laravel projects**: Check if `app/Modules/` exists.
+- **Composer projects / packages**: Check `./agents/` or `src/` for domain directories.
+- If neither exists:
+  ```
+  ⚠️  No module system found (no app/Modules/ directory).
+  ```
+  Stop.
+
+### 2. List available modules
+
+Scan `app/Modules/` and show all modules (skip `.module-template` and hidden dirs):
+
+```
+📦 Available modules:
+
+  #  Module             Directories      Agent Docs    Context
+  ─  ────────────────   ──────────────   ──────────    ───────
+  1  ApiClient          App, Routes      ❌             ❌
+  2  ClientSoftware     App, Routes      ✅ (roadmaps)  ❌
+  3  Grafana            App, Routes      ✅ (roadmaps)  ❌
+  4  Stubbing           App              ❌             ❌
+
+Which module do you want to explore? (number or name)
+```
+
+### 3. Analyze the module
+
+For the selected module, gather in parallel:
+
+**Structure:**
+- List all directories and files (2 levels deep)
+- Count PHP files per directory (Controllers, Services, Models, Jobs, Commands, etc.)
+- List route files and their contents
+
+**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 `Docs/` if it exists (human-facing documentation)
+
+**Tests:**
+- Count test files per suite (Unit, Component, Integration)
+
+**Roadmaps:**
+- Check `agents/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/contexts/` for existing context docs (project-root and module-level)
+- Check `agents/features/` for related feature plans
+
+### 4. Display module overview
+
+```
+═══════════════════════════════════════════════
+  📦 MODULE: {ModuleName}
+═══════════════════════════════════════════════
+
+{Description from README or auto-detected}
+
+───────────────────────────────────────────────
+STRUCTURE:
+───────────────────────────────────────────────
+
+  App/
+    Console/Commands/    {count} Commands
+    Enums/               {count} Enums
+    Http/Controllers/    {count} Controllers
+    Http/Requests/       {count} Requests
+    Jobs/                {count} Jobs
+    Models/              {count} Models
+    Services/            {count} Services
+
+  Routes/
+    api.php              {route count} Routes
+    console.php          {command count} Commands
+    web.php              {route count} Routes
+
+  Tests/
+    Unit/                {count} Tests
+    Component/           {count} Tests
+    Integration/         {count} Tests
+
+  Migrations/            {count} Migrations
+  Config/                {exists or not}
+
+───────────────────────────────────────────────
+NAMESPACE:
+───────────────────────────────────────────────
+
+  App\Modules\{ModuleName}\App\
+
+───────────────────────────────────────────────
+KEY CLASSES:
+───────────────────────────────────────────────
+
+  Services:
+    • {ServiceName} — {brief description}
+    • {ServiceName} — {brief description}
+
+  Controllers:
+    • {ControllerName} — {brief description}
+
+───────────────────────────────────────────────
+AGENT DOCS:
+───────────────────────────────────────────────
+
+  {List of agent docs or "No agent docs found"}
+
+───────────────────────────────────────────────
+ROADMAPS:
+───────────────────────────────────────────────
+
+  • {roadmap title} — {completed}/{total} steps (next: {next step title})
+  • "No roadmaps found" if none
+
+───────────────────────────────────────────────
+CONTEXT:
+───────────────────────────────────────────────
+
+  {Existing context doc summary or "No context found"}
+
+═══════════════════════════════════════════════
+```
+
+### 5. Offer next steps
+
+```
+What would you like to do?
+
+1. 🔍 Dive deeper — analyze a specific class/service
+2. 📄 Create context → /context-create
+3. 📋 Plan feature → /feature-plan (Module: {ModuleName})
+4. 🗺️ View roadmap (if available)
+5. ✅ Done — module context is loaded
+```
+
+### Rules
+
+- **Do NOT modify any code** — this command is read-only.
+- **Do NOT commit or push.**
+- **Load the module context** into your understanding for the rest of the conversation.
+- **Remember the module** for follow-up commands (feature-plan, context-create, etc.).