@event4u/agent-config 3.3.0 → 4.2.0

package/docs/decisions/ADR-rule-kernel-and-router.md

@@ -40,13 +40,13 @@ size budgets.
 - **Budget gates:** `task lint-rule-budget` enforces kernel ≤ 26k chars
   and per-rule ≤ 2.5k (Iron-Law overrides up to 4.0k via ADR-002).
   Daily snapshots in `agents/runtime/.rule-budget-history.jsonl`.
-- **Compression discipline:** P4.3 brought the auto-bucket from
+- **Condensation discipline:** P4.3 brought the auto-bucket from
   ~75k → 59 220 chars (under the 60k target) without behaviour drift.
 
 ### What we cut
 
 - **P4.1 / P4.2** — auto-rule → skill / guideline migrations.
-  Cancelled as scope-cut after P4.3 compression alone landed the
+  Cancelled as scope-cut after P4.3 condensation alone landed the
   auto-bucket under target. The migrations were a means, not an end.
 - **road-to-package-optimization Phase 1.2 / 1.3 / Phase 2 / Phase 3**
   — cancelled per P1.1's binary acceptance gate. The prototype
@@ -61,9 +61,9 @@ size budgets.
 ### What stayed
 
 - All Iron-Law fences. SHA-verified preserved by
-  `scripts/iron_law_sha.py` across the kernel compression pass.
+  `scripts/iron_law_sha.py` across the kernel condensation pass.
 - Behaviour parity. Golden transcripts pass under all three profiles.
-- The pre-existing `auto`-tier rules; only their compressed bodies
+- The pre-existing `auto`-tier rules; only their condensed bodies
   changed, never their obligation surface.
 
 ## Profile semantics
@@ -89,7 +89,7 @@ If the Kernel + Router model needs unwinding:
    running `compile_router.py --no-router` returns the always-loaded
    model.
 
-No data migration, no irreversible compression. Iron-Law SHA fences
+No data migration, no irreversible condensation. Iron-Law SHA fences
 mean Iron Laws can be diffed against the pre-roadmap baseline at any
 point.
 

package/docs/deploy/connector-setup.md

@@ -6,7 +6,7 @@
 > and Phase 3 (central policy) shipping first.
 >
 > Open design questions live in
-> [`agents/tmp/council-question-connector-scope.md`](../../agents/tmp/council-question-connector-scope.md).
+> [`agents/tmp/council-question-connector-scope.md`](../../agents/tmp/old/council-question-connector-scope.md).
 
 ## Audience
 
@@ -124,6 +124,6 @@ All of the above land in Phase 5, contingent on Phases 2 + 3.
 ## Cross-references
 
 - 🚧 Reserved ADR slot: `docs/decisions/ADR-025-connector-scope.md`.
-- Council question: [`agents/tmp/council-question-connector-scope.md`](../../agents/tmp/council-question-connector-scope.md).
+- Council question: [`agents/tmp/council-question-connector-scope.md`](../../agents/tmp/old/council-question-connector-scope.md).
 - Quickstart: [`quickstart.md`](quickstart.md).
 - Policy cookbook: [`policy-cookbook.md`](policy-cookbook.md).

package/docs/deploy/policy-cookbook.md

@@ -7,7 +7,7 @@
 > before code lands. Every section below is normative-once-shipped.
 >
 > Open design questions live in
-> [`agents/tmp/council-question-central-policy.md`](../../agents/tmp/council-question-central-policy.md).
+> [`agents/tmp/council-question-central-policy.md`](../../agents/tmp/old/council-question-central-policy.md).
 
 ## Audience
 
@@ -125,6 +125,6 @@ All of the above land in Phase 3. Until then, per-user
 ## Cross-references
 
 - 🚧 Reserved ADR slot: `docs/decisions/ADR-023-central-policy.md`.
-- Council question: [`agents/tmp/council-question-central-policy.md`](../../agents/tmp/council-question-central-policy.md).
+- Council question: [`agents/tmp/council-question-central-policy.md`](../../agents/tmp/old/council-question-central-policy.md).
 - Env contract: [`env-vars.md`](env-vars.md) (`POLICY_PATH`).
 - Quickstart: [`quickstart.md`](quickstart.md).

package/docs/deploy/team-deployment-posture.md

@@ -58,6 +58,26 @@ them**. The cancellations stand:
 | **Team-shared overrides server** | Shared-overrides-via-git already works for the small-team case. Server only makes sense once the org-mode threshold is reached. | `road-to-team-context.md` |
 | **OAuth connectors (Google, Slack, M365)** | Per-connector OAuth flow is a permanent footprint we can't ship without an org user agreeing to scope it. | `road-to-internal-connectors.md` |
 
+### 2026-05 feedback citation — same three asks, same Hard-Floor
+
+The 9.3/10 feedback round (delivered in chat 2026-05-25) re-affirmed
+the same three P0 items the cancellations cover: OAuth knowledge
+connectors, IAM / org mode with admin roles + quotas + audit
+retention, and organization-shared memory. The verbatim asks land on
+the same Hard-Floor wall — no funded audit, no recruited team
+customer, no scope to adopt auth-adjacent code into the package.
+
+| 9.3/10 ask | Verbatim phrasing (2026-05-25) | Maps to cancellation |
+|---|---|---|
+| OAuth knowledge connectors | "GitHub / Jira / Confluence connectors so the team's docs join the agent's knowledge index" | `road-to-internal-connectors.md` |
+| IAM / org governance | "user accounts + admin roles + quotas + audit retention" | `road-to-team-sso.md` + `road-to-central-policy.md` |
+| Organization-shared memory | "team-wide memory so what one engineer answers, the next one inherits" | `road-to-team-context.md` |
+
+Each row carries the same three release gates: **recruited customer
++ funded audit + maintainer ADR**. Until all three are met, the
+cancellation stands. Feedback rounds 11+ that re-ask the same
+questions land on this row directly.
+
 Each successor roadmap is an empty-named stub today; activation
 requires a recruited team customer plus a human-reviewed security
 audit. Until then, the answer to "team SSO when?" is: **not on this

package/docs/development.md

@@ -3,14 +3,14 @@
 ## Prerequisites
 
 - [Task](https://taskfile.dev/) (task runner)
-- Python 3.10+ (for linter, compression tools)
+- Python 3.10+ (for linter, condensation tools)
 - Bash (for install scripts, tests)
 
 ## Editing content
 
-1. **Always edit in `.agent-src.uncompressed/`** — never in `.agent-src/` or `.augment/` directly
+1. **Always edit in `.agent-src.uncondensed/`** — never in `.agent-src/` or `.augment/` directly
 2. Run `task sync` to copy non-`.md` files
-3. Use the `/compress` command to compress changed `.md` files
+3. Use the `/condense` command to condense changed `.md` files
 4. Run `task ci` to verify everything passes before pushing
 
 ---
@@ -30,15 +30,15 @@ task consistency               # Verify sync + generated tool outputs are clean
 task consistency-fix           # Regenerate all derived outputs from source
 ```
 
-### Sync & Compression
+### Sync & Condensation
 
 ```bash
-task sync                      # .agent-src.uncompressed/ → .agent-src/, then project → .augment/
-task sync-changed              # List .md files changed since last compression
+task sync                      # .agent-src.uncondensed/ → .agent-src/, then project → .augment/
+task sync-changed              # List .md files changed since last condensation
 task sync-check                # Check if .agent-src/ is in sync (for CI)
-task sync-check-hashes         # Verify compressed .md hashes match source
-task sync-mark-done <file>     # Mark a single file as compressed
-task sync-mark-all-done        # Mark ALL files as compressed
+task sync-check-hashes         # Verify condensed .md hashes match source
+task sync-mark-done <file>     # Mark a single file as condensed
+task sync-mark-all-done        # Mark ALL files as condensed
 task sync-clean-hashes         # Remove stale hashes for deleted source files
 ```
 
@@ -54,7 +54,7 @@ task clean-tools               # Remove all generated tool directories
 ```bash
 task test                      # Run all tests (bash + Python)
 task test-install              # Install script integration tests
-task test-python               # Compression and linter tests
+task test-python               # Condensation and linter tests
 task test-linter               # Skill linter unit tests
 task test-readme-linter        # README linter unit tests
 task test-runtime              # Runtime registry + dispatcher tests
@@ -85,14 +85,14 @@ task lint-skills-strict        # Lint with warnings as failures
 task lint-skills-changed       # Lint only changed files
 task lint-skills-report        # Per-file quality breakdown
 task lint-skills-regression    # Compare against main branch (detect regressions)
-task lint-skills-pairs         # Check compression quality (source vs compressed)
+task lint-skills-pairs         # Check condensation quality (source vs condensed)
 task lint-readme               # Lint README.md
 ```
 
 ### Quality Checks
 
 ```bash
-task check-compression         # Verify code blocks, headings, frontmatter preserved
+task check-condensation         # Verify code blocks, headings, frontmatter preserved
 task check-refs                # No broken cross-references
 task check-portability         # No project-specific references in shared files
 task quality-report            # Per-artifact-type quality scores
@@ -167,8 +167,8 @@ scripts/
 ├── install.py                 ← Bridge files stage (.agent-settings.yml, JSONs)
 ├── postinstall.sh             ← npm postinstall hook → scripts/install
 ├── setup.sh                   ← One-time Composer hook setup
-├── compress.py                ← Compression hash management
-├── check_compression.py       ← Compression quality checker
+├── condense.py                ← Condensation hash management
+├── check_condensation.py       ← Condensation quality checker
 ├── skill_linter.py            ← Skill/rule/command linter
 ├── lint_regression.py         ← Branch regression detection
 ├── generate_tools.sh          ← Generate tool-specific directories
@@ -190,7 +190,7 @@ tests/
 └── consistency.yml            ← Sync + hash + tool verification
 templates/consumer-settings/   ← Settings templates for consumer projects
 
-.agent-src.uncompressed/         ← Source of truth (human-readable, verbose)
+.agent-src.uncondensed/         ← Source of truth (human-readable, verbose)
 ├── rules/                     ← Behavior rules
 ├── skills/                    ← Skill definitions (SKILL.md per skill)
 ├── commands/                  ← Slash command definitions
@@ -198,8 +198,8 @@ templates/consumer-settings/   ← Settings templates for consumer projects
 ├── templates/                 ← Document scaffolds
 └── contexts/                  ← System knowledge documents
 
-.agent-src/                    ← Compressed output (token-efficient, shipped)
-├── (same structure)           ← Compressed .md + copied non-.md files
+.agent-src/                    ← Condensed output (token-efficient, shipped)
+├── (same structure)           ← Condensed .md + copied non-.md files
 
 .augment/                      ← Local projection for Augment Code (gitignored)
 ├── rules/                     ← Real file copies (Augment cannot load symlinked rules)

package/docs/distribution/registries.md

@@ -20,6 +20,38 @@ Use this exact text for the awesome-list entry. Adjust the link anchor per direc
 - [event4u/agent-config](https://github.com/event4u-app/agent-config#readme) — Universal AI Agent OS. Audited skills, governance rules, commands, and templates for Claude Code, Cursor, Windsurf, Copilot. Bring your own provider.
 ```
 
+## PR body update — 3.2.0 reality
+
+When the maintainer opens the PR / posts the directory entry, the
+description block carries the concrete reality the 3.2.0 review
+named. Reviewer verbatim quote: *"deutlich mehr vorzuweisen als bei
+jedem vorherigen Erwähnungszeitpunkt."* The numbers below mirror the
+3.2.0 release notes and the `task adoption:status` snapshot from
+that release; refresh them before posting if a later release has
+shipped.
+
+```
+event4u/agent-config 3.2.0 ships:
+
+- 4929 tests across Python + TypeScript matrix (Linux + macOS).
+- /knowledge cluster — local-only document ingestion via markitdown;
+  per-namespace memory_retrieve with trust scoring.
+- Three role experiences (galabau / content-creator / consultant) +
+  daily workspace browser surface in the modern Preact shell.
+- Cinematic AI-video pipeline (/video:from-script, /video:scene,
+  /video:storyboard, /video:stitch) — provider-agnostic; dry-run
+  default; the package never sees API keys.
+- 9 Iron-Law rules + tier-1/2 routed kernel; ai-council
+  second-opinion loop for high-impact decisions.
+
+Bring your own provider (Anthropic / OpenAI / Google / Cloudflare).
+No SaaS; no remote sync; npx-quickstart installs in ~3 minutes.
+```
+
+Drop this block into the PR description once and reuse it across
+the three registries; it is the "deutlich mehr vorzuweisen" frame
+condensed to a half-screen.
+
 ## Submission checklist
 
 Before opening any submission PR:

package/docs/distribution/registry-submissions.md

@@ -0,0 +1,85 @@
+---
+stability: beta
+keep-beta-until: 2026-08-26
+roadmap_ref: road-to-adoption-proof-and-ci-green.md
+---
+
+# Registry Submissions — tracking sheet
+
+> Phase C Step 2 of [`road-to-adoption-proof-and-ci-green.md`](../../agents/roadmaps/road-to-adoption-proof-and-ci-green.md).
+> Post-submission tracking sheet. The submission shape, schedule, and
+> the maintainer's automation contract live in
+> [`registries.md`](registries.md); this file is the operational
+> ledger.
+
+## Why a separate tracking sheet
+
+`registries.md` defines **what** to submit (the entry template, the
+audit cadence, the GitHub Discussions setup). This file records
+**what happened** — one row per submission, with status, link, and
+maintainer notes. Splitting them keeps `registries.md` editable as
+the submission shape evolves; this file accumulates history.
+
+## Status legend
+
+| Status | Meaning |
+|---|---|
+| `pending` | Pre-submission. Entry text staged but the maintainer has not opened the PR / submitted the form yet. |
+| `submitted` | PR opened or form submitted. Awaiting upstream review. |
+| `accepted` | Upstream merged the PR or accepted the directory entry. |
+| `rejected` | Upstream declined. Maintainer notes the reason. |
+| `stalled` | ≥ 60 days in `submitted` with no upstream response. Treated as effectively `rejected` for adoption-tracking purposes. |
+
+## Tracking rows
+
+| # | Registry | Submission shape | Status | PR / form URL | Date | Maintainer notes |
+|---|---|---|---|---|---|---|
+| 1 | `punkpeye/awesome-mcp-servers` | One-line entry under agent-tooling section; PR via `scripts/mcp_registry_submit.sh` | `pending` | — | — | Scaffold ready. Run `bash scripts/mcp_registry_submit.sh --dry-run` once before live; the live path needs the maintainer's GitHub identity. |
+| 2 | `mcp.so` | Directory form submission (web form, no programmatic API) | `pending` | — | — | Form URL: <https://mcp.so/>. Submission shape: same one-line entry, paste into the form's `description` field. |
+| 3 | `mcpservers.org` | Directory form submission (web form, verify URL at submission time) | `pending` | — | — | Form URL: <https://mcpservers.org/>. Submission shape: one-line entry; check the site is live before posting. |
+
+## How to update a row
+
+When a row transitions:
+
+1. **`pending` → `submitted`.** Set `Status: submitted`, `Date: YYYY-MM-DD`, `PR / form URL: <link>`. Add one-sentence maintainer note (e.g. "PR #142; reviewer assigned").
+2. **`submitted` → `accepted`.** Set `Status: accepted`. Append the merge timestamp to the maintainer notes. Cross-link the merge commit / form-confirmation in the notes.
+3. **`submitted` → `rejected`.** Set `Status: rejected`. Append the reviewer's stated reason verbatim (or paraphrase if the conversation is verbal).
+4. **`submitted` → `stalled`.** Set `Status: stalled` once the row has been in `submitted` for ≥ 60 days with no upstream movement. The agent's `task adoption:status` (Phase C Step 6) flags any `stalled` row.
+
+The dates are UTC.
+
+## Maintainer-side checklist
+
+Before flipping a row from `pending` to `submitted`:
+
+- [ ] The `README.md` hero block is current (no stale claims about deferred features).
+- [ ] `task ci:status --branch main` is green (per `ci-green-floor.md`).
+- [ ] The submission template in `registries.md` § Submission template matches the package's current positioning.
+- [ ] The PR body (or form description) cites concrete reality, not aspiration — `task adoption:status` outputs the recent green-check tally + npm install delta the maintainer can paste into the submission.
+
+If any row stays `pending` for more than four weeks, the maintainer
+re-validates the readiness checklist; positioning that was current
+in week 1 can age out by week 4.
+
+## Adoption-tracking signal
+
+Each row's status contributes to the adoption-dimension score
+tracked in
+[`road-to-employee-product-and-external-proof.md`](../../agents/roadmaps/road-to-employee-product-and-external-proof.md)
+Phase 0 § Adoption surface:
+
+- ≥ 1 row in `accepted` — adoption-dimension lifts from "scaffolded"
+  to "evidence" for the next review round.
+- ≥ 2 rows in `accepted` — registries are no longer the bottleneck;
+  next adoption-dimension lift requires recruit-session reports
+  (Phase B of this roadmap).
+- All rows in `pending` after four weeks — the bottleneck is the
+  human-owner action, not the scaffold; the scaffold is solid.
+
+## See also
+
+- [`registries.md`](registries.md) — submission template + audit cadence + Discussions setup.
+- [`scripts/mcp_registry_submit.sh`](../../scripts/mcp_registry_submit.sh) — automation for row 1.
+- [`mcp-submission-checklist.md`](mcp-submission-checklist.md) — MCP-specific pre-submission floor.
+- `task adoption:status` (Phase C Step 6) — one-screen adoption dashboard.

package/docs/distribution/telemetry-schema.md

@@ -10,7 +10,7 @@
 This is **install-funnel** telemetry. It is distinct from
 `telemetry.artifact_engagement` (agent-runtime skill/rule/command usage,
 stored locally per consumer project — see
-[`artifact-engagement-flow`](../../packages/core/.agent-src.uncompressed/contexts/contracts/artifact-engagement-flow.md)).
+[`artifact-engagement-flow`](../../packages/core/.agent-src.uncondensed/contexts/contracts/artifact-engagement-flow.md)).
 The two systems do not share storage, transport, or opt-in state.
 
 ## Goals

package/docs/getting-started-by-role.md

@@ -4,7 +4,7 @@
 
 `agent-config` ships ~210 skills, ~67 rules, and ~124 commands. You do not need all of them. Each role below filters to the slice that pays back in week one; the rest stays available and shows up on demand when a task references it.
 
-> **Quickstart for every role.** Run `npx -y @event4u/agent-config init` — the browser wizard auto-launches and walks you through role, pack, and identity. Headless install path lives at [`docs/wizard.md`](wizard.md#headless--ci--no-browser). The wizard writes `.agent-settings.yml`, `.augment/`, and `.claude/` atomically; nothing leaves your disk.
+> **Quickstart for every role.** Run `npx -y @event4u/agent-config init` — the browser wizard auto-launches and walks you through role, ready-made setup, and identity. Headless install path lives at [`docs/wizard.md`](wizard.md#headless--ci--no-browser). The wizard writes `.agent-settings.yml`, `.augment/`, and `.claude/` atomically; nothing leaves your disk.
 
 > **Eval-gated messaging note.** Until `task bench --corpus non-dev` reports `selection_accuracy >= 0.60` (step-12 Phase 1 exit), this page is documentation, not marketing. The skills listed below are the candidates the corpus tests against; their description quality is what the eval validates.
 
@@ -59,7 +59,7 @@ Cinematic-blueprint approach: the agent expands your script into a 12-block scen
 
 **Try the first win →** [`pack-founder-strategy/FIRST_WIN.md`](../packages/pack-founder-strategy/FIRST_WIN.md) — investor question reshaped into a defensible memo in ~10 minutes.
 
-**Install path:** **MCP for advisory work, CLI when you touch code.** Claude Desktop covers strategy / finance / narrative; CLI is needed only when you sit in the repo with the dev team.
+**Install path:** **MCP for advisor work, CLI when you touch code.** Claude Desktop covers strategy / finance / narrative; CLI is needed only when you sit in the repo with the dev team.
 
 ---
 
@@ -75,7 +75,7 @@ Cinematic-blueprint approach: the agent expands your script into a 12-block scen
 
 ---
 
-## Consultant (advisory, freelance, fractional)
+## Consultant (advisor, freelance, fractional)
 
 > **Tailored role experience available →** [`agents/roles/consultant/`](../agents/roles/consultant/index.md) — three first tasks (client-brief refinement, investor memo, deck outline), priority-ordered skill shortlist. Status `draft` until recruit-session 03 lands.
 
@@ -89,6 +89,48 @@ Cinematic-blueprint approach: the agent expands your script into a 12-block scen
 
 ---
 
+## Sales rep (B2B individual contributor)
+
+> **Tailored role experience available →** [`agents/roles/sales/`](../agents/roles/sales/index.md) — three first tasks (answer customer · draft offer · prep discovery call), 5 named prompts, priority-ordered skill shortlist. Status `draft` until a sales-shaped recruit-session lands.
+
+**You want this if:** you sell — usually with the deal half in your head and half in scattered notes from the last three meetings. You spend your day answering customer questions, drafting offers, and prepping discovery calls under time pressure.
+
+- [`voice-and-tone-design`](../.agent-src/skills/voice-and-tone-design/SKILL.md) — lock the deal voice across buyer / procurement / exec sponsor.
+- [`customer-research`](../.agent-src/skills/customer-research/SKILL.md) — frame the buyer's likely concern from LinkedIn / website / inbound context.
+- [`competitive-positioning`](../.agent-src/skills/competitive-positioning/SKILL.md) — surface the ours-vs-theirs delta when the buyer names a competitor.
+
+**Install path:** **MCP recommended.** Claude Desktop opens, the package shows up as a tool, no terminal. See [`docs/mcp.md`](mcp.md).
+
+---
+
+## Support agent (customer success / technical support)
+
+> **Tailored role experience available →** [`agents/roles/support/`](../agents/roles/support/index.md) — three first tasks (summarise ticket · draft reply · escalation analysis), 5 named prompts, priority-ordered skill shortlist. Status `draft` until a support-shaped recruit-session lands.
+
+**You want this if:** you answer tickets — usually under SLA, often as the only person on a thread that turned into eight back-and-forth messages over two weeks. You want an assistant that summarises threads before you reply and flags escalation risks early.
+
+- [`voc-extract`](../.agent-src/skills/voc-extract/SKILL.md) — pulls verbatim customer language from threads for downstream triage.
+- [`voice-and-tone-design`](../.agent-src/skills/voice-and-tone-design/SKILL.md) — lock the support voice so every customer thread reads as one team.
+- [`churn-prevention`](../.agent-src/skills/churn-prevention/SKILL.md) — when the escalation-risk analysis flags churn-signal language.
+
+**Install path:** **MCP recommended.** Support workflows live in the ticketing tool + chat; Claude Desktop is the natural home.
+
+---
+
+## Team leader (engineering manager, function lead, fractional)
+
+> **Tailored role experience available →** [`agents/roles/leadership/`](../agents/roles/leadership/index.md) — three first tasks (weekly status · risk-analysis memo · decision record), 5 named prompts, priority-ordered skill shortlist. Status `draft` until a leadership-shaped recruit-session lands.
+
+**You want this if:** you run a team or a function. Each week you write the same three things: a status summary, a risk memo before a decision, and a decision record after. You want an assistant that turns fuzzy notes into structured documents — without inventing certainty you do not have.
+
+- [`decision-record`](../.agent-src/skills/decision-record/SKILL.md) — ADR-shaped output the team's record system already understands.
+- [`scenario-modeling`](../.agent-src/skills/scenario-modeling/SKILL.md) — best / base / downside frame when the risk memo demands a sweep.
+- [`stakeholder-tradeoff`](../.agent-src/skills/stakeholder-tradeoff/SKILL.md) — when the call has product / ops / exec sponsor pulling in different directions.
+
+**Install path:** **MCP recommended.** Leadership writing is doc-heavy; Claude Desktop is the natural home.
+
+---
+
 ## Galabau owner (Garten- und Landschaftsbau, small-business operator)
 
 > **Tailored role experience available →** [`agents/roles/galabau/`](../agents/roles/galabau/index.md) — three first tasks (offer drafting, customer-email reply, project-brief refinement), priority-ordered skill shortlist. Status `draft` until recruit-session 01 lands.

package/docs/getting-started.md

@@ -106,7 +106,7 @@ Your agent is now:
 - **Respecting your codebase** — no conflicting patterns
 - **Following standards** — consistent code quality
 
-This is enforced automatically by 75 rules. No configuration needed.
+This is enforced automatically by 77 rules. No configuration needed.
 
 ---
 
@@ -146,7 +146,7 @@ Your agent now understands slash commands:
 | `/quality-fix` | Run and fix all quality checks |
 | `/chat-history` | Inspect the persistent chat-history log (read-only `show`) |
 
-→ [Browse all 136 active commands](../.agent-src/commands/)
+→ [Browse all 135 active commands](../.agent-src/commands/)
 
 ---
 

package/docs/guidelines/agent-infra/5w2h-analysis.md

@@ -6,11 +6,11 @@ comprehensive understanding of any topic, problem, or plan. Adopted under
 the **Reference-Guideline Sunset Policy** (see frontmatter `upstream` /
 `refresh_trigger` keys) and cross-referenced from:
 
-- [`deep-reading-analyst`](../../../.agent-src.uncompressed/skills/deep-reading-analyst/SKILL.md)
+- [`deep-reading-analyst`](../../../.agent-src.uncondensed/skills/deep-reading-analyst/SKILL.md)
   — L1 Quick analysis depth.
-- [`refine-ticket`](../../../.agent-src.uncompressed/skills/refine-ticket/SKILL.md)
+- [`refine-ticket`](../../../.agent-src.uncondensed/skills/refine-ticket/SKILL.md)
   — completeness check on a Jira / Linear ticket before estimation.
-- [`bug-investigate`](../../../.agent-src.uncompressed/commands/bug-investigate.md)
+- [`bug-investigate`](../../../.agent-src.uncondensed/commands/bug-investigate.md)
   — gap analysis on an incident report before forming a hypothesis.
 
 > **Core principle:** "Quality of decisions equals quality of questions

package/docs/guidelines/agent-infra/ask-when-uncertain-demos.md

@@ -12,7 +12,7 @@ prose_delta:
 
 > Wrong / right / why demos for the `ask-when-uncertain` Iron Law
 > (one question per turn, vague-request must ask). Linked from
-> [`ask-when-uncertain`](../../.agent-src.uncompressed/rules/ask-when-uncertain.md)
+> [`ask-when-uncertain`](../../.agent-src.uncondensed/rules/ask-when-uncertain.md)
 > § Examples. Outcome baseline at
 > [`tests/golden/outcomes/ask_when_uncertain.json`](../../tests/golden/outcomes/ask_when_uncertain.json).
 

package/docs/guidelines/agent-infra/asking-and-brevity-examples.md

@@ -1,9 +1,9 @@
 # asking-and-brevity-examples
 
 Companion examples for three always-rules:
-[`ask-when-uncertain`](../../../.agent-src.uncompressed/rules/ask-when-uncertain.md),
-[`no-cheap-questions`](../../../.agent-src.uncompressed/rules/no-cheap-questions.md),
-[`direct-answers`](../../../.agent-src.uncompressed/rules/direct-answers.md).
+[`ask-when-uncertain`](../../../.agent-src.uncondensed/rules/ask-when-uncertain.md),
+[`no-cheap-questions`](../../../.agent-src.uncondensed/rules/no-cheap-questions.md),
+[`direct-answers`](../../../.agent-src.uncondensed/rules/direct-answers.md).
 
 The rules carry the Iron Laws and the obligation surface. This file
 carries the illustrative material (example questions, rationale

package/docs/guidelines/agent-infra/carve-out-predicates.md

@@ -1,14 +1,14 @@
 # Decidable Carve-Out Predicates
 
-Companion to [`frugality-charter`](../../../.agent-src.uncompressed/contexts/contracts/frugality-charter.md). Each carve-out below carries a one-sentence test. If the test cannot be answered yes/no from the artifact alone, the carve-out does not fire and default-terse rules apply.
+Companion to [`frugality-charter`](../../../.agent-src.uncondensed/contexts/contracts/frugality-charter.md). Each carve-out below carries a one-sentence test. If the test cannot be answered yes/no from the artifact alone, the carve-out does not fire and default-terse rules apply.
 
 ## Predicates
 
 - **Iron-Law literal** — the prose is an ALL-CAPS fenced block inside a rule whose title appears in [`docs/contracts/kernel-membership.md`](../../contracts/kernel-membership.md).
 
-- **Numbered-options with genuine trade-off** — the options differ in consequence (a chosen path produces a measurably different artifact or state), not in sequencing or output format. Per [`no-cheap-questions § What counts as cheap`](../../../.agent-src.uncompressed/rules/no-cheap-questions.md#what-counts-as-cheap).
+- **Numbered-options with genuine trade-off** — the options differ in consequence (a chosen path produces a measurably different artifact or state), not in sequencing or output format. Per [`no-cheap-questions § What counts as cheap`](../../../.agent-src.uncondensed/rules/no-cheap-questions.md#what-counts-as-cheap).
 
-- **Security-sensitive prompt** — the prompt requires credential input OR modifies auth / tenant / secret state, matching a trigger in [`security-sensitive-stop`](../../../.agent-src.uncompressed/rules/security-sensitive-stop.md).
+- **Security-sensitive prompt** — the prompt requires credential input OR modifies auth / tenant / secret state, matching a trigger in [`security-sensitive-stop`](../../../.agent-src.uncondensed/rules/security-sensitive-stop.md).
 
 - **Structured CLI contract** — the script's stdout is consumed by another script (a downstream parser exists under `scripts/` or `.augment/scripts/`), so the format is part of an interface contract, not narration.
 

package/docs/guidelines/agent-infra/critical-thinking.md

@@ -8,13 +8,13 @@ rebuilds from primitives) and `inversion-thinking` (which negates the
 goal). Adopted under the **Reference-Guideline Sunset Policy** and
 cross-referenced from:
 
-- [`deep-reading-analyst`](../../../.agent-src.uncompressed/skills/deep-reading-analyst/SKILL.md)
+- [`deep-reading-analyst`](../../../.agent-src.uncondensed/skills/deep-reading-analyst/SKILL.md)
   — L2 Standard / L3 Deep evaluation depth.
-- [`receiving-code-review`](../../../.agent-src.uncompressed/skills/receiving-code-review/SKILL.md)
+- [`receiving-code-review`](../../../.agent-src.uncondensed/skills/receiving-code-review/SKILL.md)
   — steelman bot / human review feedback before changing code.
-- [`improve-before-implement`](../../../.agent-src.uncompressed/rules/improve-before-implement.md)
+- [`improve-before-implement`](../../../.agent-src.uncondensed/rules/improve-before-implement.md)
   — challenge weak requirements with evidence-grade analysis.
-- [`adversarial-review`](../../../.agent-src.uncompressed/skills/adversarial-review/SKILL.md)
+- [`adversarial-review`](../../../.agent-src.uncondensed/skills/adversarial-review/SKILL.md)
   — paired stress-test on a diff after critique.
 
 > **Core principle:** "Steelman first, criticize second." — attacking

package/docs/guidelines/agent-infra/direct-answers-demos.md

@@ -13,7 +13,7 @@ prose_delta:
 > Wrong / right / why demos for the three Iron Laws of
 > `direct-answers` (no flattery, no invented facts, brevity by
 > default). Linked from
-> [`direct-answers`](../../.agent-src.uncompressed/rules/direct-answers.md)
+> [`direct-answers`](../../.agent-src.uncondensed/rules/direct-answers.md)
 > § Examples. Outcome baseline at
 > [`tests/golden/outcomes/direct_answers.json`](../../tests/golden/outcomes/direct_answers.json).
 

package/docs/guidelines/agent-infra/first-principles.md

@@ -8,11 +8,11 @@ verified primitives and reconstruct it without inherited convention.
 Adopted under the **Reference-Guideline Sunset Policy** and
 cross-referenced from:
 
-- [`deep-reading-analyst`](../../../.agent-src.uncompressed/skills/deep-reading-analyst/SKILL.md)
+- [`deep-reading-analyst`](../../../.agent-src.uncondensed/skills/deep-reading-analyst/SKILL.md)
   — L3 Deep analysis depth.
 - [`mental-models`](mental-models.md) — Munger's lattice; first
   principles is the foundational physics-style lens.
-- [`improve-before-implement`](../../../.agent-src.uncompressed/rules/improve-before-implement.md)
+- [`improve-before-implement`](../../../.agent-src.uncondensed/rules/improve-before-implement.md)
   — challenge the framing of a request before coding it.
 - [`inversion-thinking`](inversion-thinking.md) — pair: first
   principles rebuilds; inversion stress-tests the rebuild.

package/docs/guidelines/agent-infra/inversion-thinking.md

@@ -4,18 +4,18 @@ Reference guideline for Wing-1 deep-thinking work — Carl Jacobi's
 "invert, always invert" applied to **decisions and arguments**, not
 diffs. The pre-mortem on a strategy, an argument, or a written plan;
 distinct from
-[`adversarial-review`](../../../.agent-src.uncompressed/skills/adversarial-review/SKILL.md)
+[`adversarial-review`](../../../.agent-src.uncondensed/skills/adversarial-review/SKILL.md)
 which stress-tests **diffs**. Adopted under the **Reference-Guideline
 Sunset Policy** (see frontmatter `upstream` / `refresh_trigger` keys)
 and cross-referenced from:
 
-- [`refine-prompt`](../../../.agent-src.uncompressed/skills/refine-prompt/SKILL.md)
+- [`refine-prompt`](../../../.agent-src.uncondensed/skills/refine-prompt/SKILL.md)
   — pre-mortem on a free-form prompt before planning.
-- [`refine-ticket`](../../../.agent-src.uncompressed/skills/refine-ticket/SKILL.md)
+- [`refine-ticket`](../../../.agent-src.uncondensed/skills/refine-ticket/SKILL.md)
   — pre-mortem on a Jira / Linear ticket before estimation.
-- [`threat-modeling`](../../../.agent-src.uncompressed/skills/threat-modeling/SKILL.md)
+- [`threat-modeling`](../../../.agent-src.uncondensed/skills/threat-modeling/SKILL.md)
   — abuse-case generation pairs with goal inversion.
-- [`improve-before-implement`](../../../.agent-src.uncompressed/rules/improve-before-implement.md)
+- [`improve-before-implement`](../../../.agent-src.uncondensed/rules/improve-before-implement.md)
   — challenge weak requirements before writing code.
 
 > **Core principle:** "Invert, always invert." — Carl Jacobi

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

@@ -18,7 +18,7 @@ on user request.
 | File | Git | Scope | Owner | Example values |
 |---|---|---|---|---|
 | `.agent-project-settings.yml` | **committed** | team / repo | lead maintainer | `project.stack`, `quality.php.tools`, `memory.dogfood` |
-| `~/.event4u/agent-config/agent-settings.yml` | **n/a** (outside repo) | individual developer · cross-project | individual | `name`, `ide`, `cost_profile`, `personal.bot_icon`, `personal.autonomy`, `caveman.speak_scope` (legacy `~/.config/agent-config/agent-settings.yml` read as fallback) |
+| `~/.event4u/agent-config/agent-settings.yml` | **n/a** (outside repo) | individual developer · cross-project | individual | `name`, `ide`, `cost_profile`, `personal.bot_icon`, `personal.autonomy`, `telegraph.speak_scope` (legacy `~/.config/agent-config/agent-settings.yml` read as fallback) |
 | `.agent-settings.yml` | **gitignored** | individual developer · this project | individual | `personal.ide`, `personal.user_name`, `subagents.max_parallel`, `onboarding.onboarded` |
 
 All three are YAML. Schemas:
@@ -55,7 +55,7 @@ ide
 cost_profile
 personal.bot_icon
 personal.autonomy
-caveman.speak_scope
+telegraph.speak_scope
 ```
 
 Loader contract:
@@ -150,6 +150,60 @@ pattern (e.g. `*.yml` in a nested folder) would otherwise match.
   rules](#section-aware-merge-rules) — preserve existing values,
   template order, and comments. No ad-hoc YAML rewrites.
 
+## Module discovery
+
+Module-aware skills and commands (`module-management`, `/module
+explore`, `/module create`, roadmap-writing) consult the `modules:`
+block on the **team** layer
+([`agent-project-settings.example.yml`](../../templates/agents/agent-project-settings.example.yml))
+to find module roots, namespace conventions, and per-module
+`agents/` folders. Lives next to `project.stack` because it
+describes the same thing — repo layout.
+
+| Key | Default | Purpose |
+|---|---|---|
+| `modules.enabled` | `false` | Master switch; when off, every module-aware surface treats the repo as flat |
+| `modules.root_paths` | `[]` | Repo-relative directories whose direct children are modules |
+| `modules.namespace_template` | `""` | Substitution template (`{ModuleName}`) for stacks with a PHP-style namespace |
+| `modules.agent_folder` | `"agents"` | Per-module folder the agent auto-loads on `/module explore <Name>` |
+| `modules.skip_dirs` | `[".module-template", ".example"]` | Directory names skipped during enumeration |
+
+Stack-by-stack starting points (manual setup; the installer fills
+these on opt-in when it detects a known shape):
+
+```yaml
+# Laravel HMVC
+modules:
+  enabled: true
+  root_paths: [app/Modules]
+  namespace_template: "App\\Modules\\{ModuleName}\\App"
+
+# Symfony DDD-lite (or PHP with a single src tree)
+modules:
+  enabled: true
+  root_paths: [src]
+  namespace_template: "App\\{ModuleName}"
+
+# Node monorepo
+modules:
+  enabled: true
+  root_paths: [packages]
+  namespace_template: ""
+
+# Go internal layout
+modules:
+  enabled: true
+  root_paths: [internal]
+  namespace_template: ""
+```
+
+Multi-root repos list each root once; enumeration walks every
+listed root and merges results.
+
+Lock via `locked_keys: [modules.root_paths]` when the layout must
+not drift between developers — typical for compliance-critical or
+multi-team repos.
+
 ## Persona-list merge semantics
 
 Persona configuration does **not** follow the simple "higher layer