@event4u/agent-config 9.13.0 → 9.15.0

package/dist/agent-src/rules/media-governance-routing.md

@@ -26,6 +26,7 @@ validator_ignore:
   - type: "substring"
     pattern: ".agent-src.uncondensed/"
     reason: "Rule contrasts project-local placement with the .agent-src.uncondensed/rules/ alternative — mentioning the path is the argument."
+self_contained: true
 workspaces: [agent-config-maintainer, engineering, gtm]
 packs: [ai-image, ai-video]
 enforced_by:
@@ -58,12 +59,12 @@ When any trigger above matches in the user prompt or in a tool invocation, the a
 
 Each policy carries its own trigger block, so within the active context the agent narrows from this superset to the policies whose specific patterns actually fired (e.g., a prompt naming a public figure activates `public-figures.md` and `disclosure.md`; a prompt requesting `--no-disclosure` activates `disclosure.md` standalone).
 
-## Why project-local, not `.agent-src.uncondensed/rules/`
+## Why project-local, not `src/rules/`
 
-The seven media policies live under [`agents/settings/policies/media/`](../../agents/settings/policies/media/), not as `.agent-src.uncondensed/rules/domain-safety-media-*.md`, for three reasons:
+The seven media policies live under [`agents/settings/policies/media/`](../../agents/settings/policies/media/), not as `src/rules/domain-safety-media-*.md`, for three reasons:
 
 1. **They are consumed by skills and adapters**, not surfaced as standalone always-loaded prose. The cost is non-trivial (7 × ~80 lines = ~560 lines into the always-context if hoisted to rules), and most sessions never touch a video / image / voice surface.
-2. **The enforcement model is project-local** — the working precedent (`/ghostwriter:*` mandatory footer in `write-engine.md`) and the audit log (session transcripts) are project artifacts. Rules under `.agent-src.uncondensed/` are tool-portable governance; these policies are domain-specific bindings.
+2. **The enforcement model is project-local** — the working precedent (`/ghostwriter:*` mandatory footer in `write-engine.md`) and the audit log (session transcripts) are project artifacts. Rules under `src/rules/` are tool-portable governance; these policies are domain-specific bindings.
 3. **Extraction to a reusable domain pack is explicitly deferred** until a second non-video domain (audio, image, docs, exports) lands with overlapping execution surfaces. Until then, a one-domain abstraction is structurally premature — the policies stay project-local and the routing rule is the on-demand bridge.
 
 This routing rule is the bridge: it sits in the always-loaded rule set so the trigger keywords surface the project-local policies into context on demand, without paying the full always-loaded cost.

package/dist/agent-src/rules/media-sync-ground-truth.md

@@ -14,6 +14,7 @@ triggers:
   - phrase: "sing the"
   - phrase: "mit den lippen"
   - phrase: "lippen passend"
+self_contained: true
 workspaces: [agent-config-maintainer, engineering, gtm]
 packs: [ai-video]
 ---

package/dist/agent-src/rules/no-attribution-footers.md

@@ -5,6 +5,7 @@ alwaysApply: false
 description: "PR/issue/comment/commit bodies — no 'Generated with' / 'Co-authored by' / 'opened by' attribution footers"
 triggers:
   - keyword: "co-authored"
+self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 ---

package/dist/agent-src/rules/no-decorative-emojis-in-git-surfaces.md

@@ -14,6 +14,7 @@ triggers:
   - keyword: "💡"
   - keyword: "👍"
   - keyword: "❤️"
+self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 ---

package/dist/agent-src/rules/no-pr-progress-comments.md

@@ -7,6 +7,7 @@ triggers:
   - keyword: "gh pr comment"
   - keyword: "PullRequestComment"
   - phrase: "status comment"
+self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 ---

package/dist/agent-src/rules/onboarding-gate.md

@@ -6,6 +6,7 @@ triggers:
   - phrase: "first turn"
   - keyword: "onboarding"
   - path_prefix: ".agent-settings.yml"
+self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 enforced_by:

package/dist/agent-src/rules/output-discipline.md

@@ -7,6 +7,7 @@ triggers:
   - keyword: "for brevity"
   - keyword: "rest follows the same pattern"
   - phrase: "similar pattern"
+self_contained: true
 workspaces: [engineering]
 packs: [engineering-base]
 enforced_by:

package/dist/agent-src/rules/prefer-enums-over-literals.md

@@ -9,6 +9,7 @@ triggers:
   - keyword: "kind"
   - keyword: "category"
   - keyword: "migration"
+self_contained: true
 workspaces: [engineering]
 packs: [engineering-base]
 ---

package/dist/agent-src/rules/preservation-guard.md

@@ -9,6 +9,7 @@ validator_ignore:
   - type: "substring"
     pattern: ".agent-src.uncondensed/"
     reason: "Rule references the authoring tree as the operand of condensation/preservation."
+self_contained: true
 workspaces: [agent-config-maintainer]
 packs: [meta]
 enforced_by:

package/dist/agent-src/rules/question-not-instruction.md

@@ -21,6 +21,7 @@ applies_to_user_types:
   - "maintainer"
   - "operator"
   - "researcher"
+self_contained: true
 workspaces: [engineering]
 packs: [meta]
 ---

package/dist/agent-src/rules/roadmap-ci-steps-policy.md

@@ -24,6 +24,7 @@ validator_ignore:
   - type: "substring"
     pattern: ".agent-settings.yml"
     reason: "Rule reads quality.local_auto_run from .agent-settings.yml; naming the file is the contract."
+self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 roles: [planner]

package/dist/agent-src/rules/role-mode-adherence.md

@@ -6,6 +6,7 @@ alwaysApply: false
 triggers:
   - keyword: "active_role"
   - keyword: "role-mode"
+self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 ---

package/dist/agent-src/rules/runtime-safety.md

@@ -7,6 +7,7 @@ triggers:
   - keyword: "automated"
   - keyword: "assisted"
   - keyword: "handler"
+self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 ---

package/dist/agent-src/rules/security-sensitive-stop.md

@@ -14,6 +14,7 @@ validator_ignore:
   - type: "substring"
     pattern: "../../docs/"
     reason: "See-also routes to docs/threat-model.md — the canonical attack-surface doc lives there by design."
+self_contained: true
 workspaces: [engineering]
 packs: [engineering-base]
 enforced_by:

package/dist/agent-src/rules/session-canary.md

@@ -7,6 +7,7 @@ triggers:
   - keyword: "canary"
   - keyword: "canary_name"
   - phrase: "session canary"
+self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 enforced_by:
@@ -21,7 +22,12 @@ two small, always-expected reply markers whose **silent disappearance** tells
 the user the conversation is degrading and it is time for a fresh session —
 long before the agent visibly starts making mistakes.
 
-Read `personal.canary_name` from `.agent-settings.yml`. Empty or missing →
+The canary is a **personal, user-global** concern — the name resolves through
+three layers, first non-empty wins: project `.agent-settings.yml` →
+`personal.canary_name` (override only) · user-global
+`settings/.agent-settings.yml` → `personal.canary_name` · user-global
+`settings/.agent-user.yml` → `identity.name` (the name the setup wizard
+already collects — never duplicate it per project). No name on any layer →
 rule is inert.
 
 ## The Iron Law
@@ -55,7 +61,8 @@ name it and suggest a fresh session or `/agent-handoff`, per
 
 ## When NOT to fire
 
-- `personal.canary_name` empty or missing — fully inert, no greeting.
+- No name on any layer (`personal.canary_name` project + user-global, global
+  `identity.name`) — fully inert, no greeting.
 - Intermediate replies inside an ongoing task (greeting only at task start).
 - The greeting never substitutes for substance — it prefixes the answer, it is
   not the answer.

package/dist/agent-src/rules/source-confidentiality.md

@@ -14,6 +14,7 @@ validator_ignore:
   - type: "substring"
     pattern: "external_sources_denylist"
     reason: "Rule names the linter/denylist asset that necessarily holds the tokens."
+self_contained: true
 workspaces: [agent-config-maintainer]
 packs: [meta]
 enforced_by:

package/dist/agent-src/rules/source-of-truth.md

@@ -9,6 +9,7 @@ triggers:
   - path_prefix: ".augment/"
   - path_prefix: ".claude/"
   - path_prefix: ".cursor/"
+self_contained: true
 workspaces: [agent-config-maintainer]
 packs: [meta]
 enforced_by:

package/dist/agent-src/rules/spreadsheet-source-quality.md

@@ -9,6 +9,7 @@ triggers:
   - keyword: "revenue figures"
   - keyword: "market data"
   - phrase: "pull the numbers"
+self_contained: true
 workspaces:
   - finance
 packs:

package/dist/agent-src/rules/think-before-action.md

@@ -14,6 +14,7 @@ triggers:
   - keyword: "refactor"
   - keyword: "fix"
   - keyword: "optimize"
+self_contained: true
 workspaces: [engineering]
 packs: [engineering-base]
 ---

package/dist/agent-src/rules/token-budget-discipline.md

@@ -5,6 +5,7 @@ description: "rich-class skills are exempt from telegraph + thin-projector trims
 triggers:
   - keyword: "token_budget_class"
   - keyword: "rich skill"
+self_contained: true
 workspaces: [agent-config-maintainer]
 packs: [meta]
 ---

package/dist/agent-src/rules/token-efficiency.md

@@ -8,6 +8,7 @@ load_context:
 triggers:
   - keyword: "minimize tool calls"
   - phrase: "fetching logs"
+self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 ---

package/dist/agent-src/rules/token-optimizer-maintenance.md

@@ -34,10 +34,10 @@ THE CI LINK VALIDATOR IS A BACKSTOP, NOT A SUBSTITUTE FOR CARE.
 
 About to edit any of:
 
-- `.agent-src.uncondensed/rules/cli-output-handling.md`
-- `.agent-src.uncondensed/rules/token-efficiency.md`
-- `.agent-src.uncondensed/rules/direct-answers.md`
-- `.agent-src.uncondensed/skills/rtk-output-filtering/SKILL.md`
+- `src/rules/cli-output-handling.md`
+- `src/rules/token-efficiency.md`
+- `src/rules/direct-answers.md`
+- `src/skills/rtk-output-filtering/SKILL.md`
 - `src/domains/meta/agent-handoff/command.md`
 - Any other asset cited by
   [`token-optimizer`](../skills/token-optimizer/SKILL.md) (catalog
@@ -52,7 +52,7 @@ If the edit touches:
 - **The asset's path / location** (rename, move, deletion)
 
 then in the same commit, update the matching row in
-`.agent-src.uncondensed/skills/token-optimizer/SKILL.md` —
+`src/skills/token-optimizer/SKILL.md` —
 the catalog table AND the relevant tree leaf.
 
 ## Out of scope

package/dist/agent-src/rules/tool-safety.md

@@ -5,6 +5,7 @@ description: "Skill uses external tools — enforce allowlist, deny-by-default,
 triggers:
   - keyword: "allowed_tools"
   - keyword: "tool registry"
+self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 enforced_by:

package/dist/agent-src/rules/untrusted-input-defense.md

@@ -13,6 +13,8 @@ triggers:
   - phrase: "treat as instructions"
   - phrase: "from the web"
   - phrase: "scraped"
+routes_to:
+  - "guideline:agent-infra/untrusted-input-spotlighting"
 workspaces: [engineering]
 packs: [engineering-base]
 enforced_by:

package/dist/agent-src/rules/user-interaction.md

@@ -10,6 +10,7 @@ triggers:
   - keyword: "recommendation"
   - phrase: "what do you recommend"
   - phrase: "was empfiehlst du"
+self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 ---

package/dist/agent-src/rules/user-interrupt-priority.md

@@ -15,6 +15,7 @@ triggers:
   - command: "implement-ticket"
 load_context:
   - ../contexts/execution/interrupt-examples.md
+self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 ---

package/dist/agent-src/skills/adr-create/SKILL.md

@@ -170,7 +170,7 @@ the area's contract from the README in
 
 ### 6. Validate
 
-- Flat: `./scripts-run src/scripts/adr/regenerate_index --check` exits 0.
+- Flat: `./scripts-run src/scripts/adr/regenerate_index --dir docs/decisions/ --check` exits 0.
 - Per-area: `./scripts-run src/scripts/audit_adr_coverage --check` exits 0.
 - The project's CI / quality pipeline passes — locally only when
   `quality.local_auto_run: true`; under the default (`false` / missing)

package/dist/agent-src/skills/check-refs/SKILL.md

@@ -27,7 +27,7 @@ gaps:
 Use this skill when:
 
 - A skill, rule, command, guideline, or context has been renamed or deleted
-- Linking a newly added artifact from elsewhere in `.agent-src.uncondensed/`
+- Linking a newly added artifact from elsewhere in `src/`
 - Preparing a PR that touches cross-references between agent artifacts
 - CI's `check-refs` job failed and the broken reference needs to be located
 

package/dist/agent-src/skills/competitive-positioning/SKILL.md

@@ -114,7 +114,7 @@ to [`upstream-contribute`](../upstream-contribute/SKILL.md).
 **WHEN NOT to use this**
 
 - The peer repo needs a generic walk-through first — route to
-  [`analyze-reference-repo`](../analyze-reference-repo/SKILL.md);
+  [`analyze-reference-repo`](../../commands/analyze/reference-repo.md);
   this skill consumes its output, never duplicates it.
 - The decision is to contribute back upstream — route to
   [`upstream-contribute`](../upstream-contribute/SKILL.md).

package/dist/agent-src/skills/condense-memory/SKILL.md

@@ -102,7 +102,7 @@ CLI exit codes:
 - **Denylist false positive** — a sensitive-looking filename outside the denylist surface (project-specific naming) will still pass `assert_safe()`. The denylist is necessary but not sufficient; the maintainer is responsible for never feeding secrets to the condenseor.
 - **Frontmatter ordering with existing keys** — if the target already has frontmatter, the condenseor preserves existing keys, drops any prior `original_sha256:` / `condensed_at:` entries, and appends the new pair. Other agents reading the file should treat the SHA + timestamp pair as the canonical condensation marker, not the file size.
 - **Negative savings on pointer-heavy files** — a `templates/AGENTS.md` that already follows Thin-Root (≥ 40 % pointers, ≥ 60-char *why*-clauses) has little prose left to drop; condensation may net near-zero or even add bytes via frontmatter. Run [`agents-md-thin-root`](../agents-md-thin-root/SKILL.md) first to maximise pointer share, then measure whether this skill still pays.
-- **Generated-tree drift** — condensing `.agent-src.uncondensed/templates/AGENTS.md` does NOT propagate to `.augment/`, `.claude/`, etc. until the package's sync + generate-tools scripts run (`scripts/condense.sh --sync` + `scripts/condense.ts --generate-tools`). Always regenerate after condensing a templated file.
+- **Generated-tree drift** — condensing `src/agent-src/templates/AGENTS.md` does NOT propagate to `.augment/`, `.claude/`, etc. until the package's sync + generate-tools scripts run (`scripts/condense.sh --sync` + `scripts/condense.ts --generate-tools`). Always regenerate after condensing a templated file.
 
 ## Measurement — when to condense
 

package/dist/agent-src/skills/context-authoring/SKILL.md

@@ -43,7 +43,7 @@ Do NOT use when:
 | `deployment-order.md` | Migration strategy, feature flags, rollback plan | `migration-safety`, `judge-bug-hunter`, release reviewers |
 | `observability.md` | Error tracking, log channels, metrics, known alerts | deploy reviewers, `bug-analyzer`, incident mode |
 
-The templates ship in `.agent-src.uncondensed/templates/contexts/` and are
+The templates ship in `src/agent-src/templates/contexts/` and are
 copied into `agents/settings/contexts/` by the installer.
 
 ## Procedure: context-authoring

package/dist/agent-src/skills/copilot-agents-optimization/SKILL.md

@@ -185,7 +185,7 @@ it as "redundant" and never trim its bullets. The patterns it covers:
   (`../docs/guidelines/foo.md`, `../contexts/bar.md`) — paths resolve
   from the file's delivered location, not from the symlink in
   `.claude/rules/` etc. (per `road-to-path-fixes.md` Strategy A).
-- `path_prefix:` triggers containing `.agent-src.uncondensed/` —
+- `path_prefix:` triggers containing `src/` —
   literal match patterns, not file refs (per Modified Option 1,
   P2.2).
 - Symlinked rule files under `.claude/rules/`, `.cursor/rules/`,

package/dist/agent-src/skills/description-assist/SKILL.md

@@ -63,7 +63,7 @@ Report which checks pass / fail in one compact line — **not** a long essay.
 
 If the target is a skill, check for a trigger-eval report:
 
-* `.agent-src.uncondensed/skills/{name}/evals/triggers.json` — the expected-trigger corpus
+* `src/skills/{name}/evals/triggers.json` — the expected-trigger corpus
 * `evals/last-run.json` — the most recent runner output (see
   [`scripts/skill_trigger_eval.ts`](../../../scripts/skill_trigger_eval.ts))
 

package/dist/agent-src/skills/github-ci/SKILL.md

@@ -63,6 +63,7 @@ Read `.github/workflows/` to discover the actual job matrix. Common patterns:
 - Use **concurrency groups** to prevent duplicate runs: `group: ${{ github.workflow }}-${{ github.ref }}`
 - Use **`fail-fast: false`** in matrix strategies for independent job execution.
 - Extract shared logic into **reusable workflows** (`module-deploy.yaml` pattern).
+- A job with **`container:`** MUST run `git config --global --add safe.directory "$GITHUB_WORKSPACE"` immediately after `actions/checkout` — the checkout is owned by a different UID than the container user, so without it every git-backed step dies with `fatal: detected dubious ownership`.
 
 ### Composer auth
 

package/dist/agent-src/skills/guideline-writing/SKILL.md

@@ -48,7 +48,7 @@ Creating or materially rewriting a guideline **must** go through Understand
 * **Understand** — which skills or rules will cite this guideline? If the
   answer is "none", the guideline has no home — stop.
 * **Research** — **inspect** `docs/guidelines/` for overlap and grep
-  `.agent-src.uncondensed/` for pages that already cover the topic.
+  `src/` for pages that already cover the topic.
   **Analyze** 1–2 peer guidelines in the same topic folder for tone.
 * **Draft** — propose location (topic folder + filename) and outline. Only
   fill bodies once the outline is confirmed.

package/dist/agent-src/skills/lint-skills/SKILL.md

@@ -24,7 +24,7 @@ packs:
 
 Use this skill when:
 
-- Validating the shape of every skill and rule in `.agent-src.uncondensed/`
+- Validating the shape of every skill and rule in `src/`
 - Verifying execution metadata (`execution.type`, `handler`, `command`) is well-formed
 - Checking locally before opening a PR that CI's skill-lint job will pass
 - Investigating a reported linter failure on a specific skill or rule

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

@@ -206,7 +206,7 @@ Compare the README's claims to the live repository:
 | # | Severity | Section | Issue | Fix |
 |---|---|---|---|---|
 | 1 | ❌ Critical | Install | Command `X` does not exist | Replace with `Y` |
-| 2 | ❌ Critical | Profile grid | Link `.agent-src.uncondensed/profiles/` 404s | Repoint to `packages/core/.agent-src.uncondensed/profiles/` |
+| 2 | ❌ Critical | Profile grid | Link `src/agent-src/profiles/` 404s | Repoint to `packages/core/src/agent-src/profiles/` |
 | 3 | ⚠️ Major | Badges | "Skills: 218" — live count is 207 | Update badge or note drift |
 | 4 | ⚠️ Major | Usage | Example uses deprecated API | Update to current API |
 | 5 | ℹ️ Minor | Structure | Requirements buried below usage | Move above install |

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

@@ -147,6 +147,11 @@ Every roadmap follows this structure:
 - Never remove completed steps — they serve as history.
 - **Status is binary: `ready` (default, implicit) or `draft`.** New roadmaps are created **ready** unless the user explicitly says otherwise — `ready` is implicit and need not be written. A roadmap that is still being authored, awaiting upstream decisions, or capturing options without a worked plan declares `status: draft` in YAML frontmatter at the top of the file. Drafts are hidden from `agents/roadmaps-progress.md` until the flag is removed or flipped to `ready`. There are no other status values; legacy banners (`**Status: directional**`, `Status: capture-only`, `mode: feedback`) are removed.
 
+### Awaiting evidence — a blocker entry, never a new glyph
+
+- Waiting on **evidence that has not arrived** (soak still running, benchmark unfunded, adopter absent) is neither `[~]` nor `[-]`. Signal it with a structured `## Blockers` entry — five-field shape in [`templates/roadmaps.md` rule 20](../../agent-src/templates/roadmaps.md) — whose `Resolved when:` names the decidable signal ending the wait. The item stays `- [ ]` and points at it: `<!-- blocked-by: <id> -->`.
+- **No new glyph.** `[ ]` + `blocked-by:` = open, awaiting named evidence (stays active) · `[~]` = deferred by decision (bars archival, Iron Law 3) · `[-]` = cancelled with a reason (does not bar it). A fifth state buys nothing the entry above does not already carry.
+
 ### Phases
 
 - Group related steps into phases (e.g. "Preparation", "Migration", "Cleanup").
@@ -488,7 +493,9 @@ owner, blocked scope, and full instructions. Authoring shape:
 [`templates/roadmaps.md` rule 20](../../agent-src/templates/roadmaps.md);
 authoring guidance: [`roadmap-writing § 5b`](../roadmap-writing/SKILL.md).
 Clearing a blocker flips its `Status: resolved` and regenerates the
-dashboard in the same reply, same cadence as a checkbox flip.
+dashboard in the same reply, same cadence as a checkbox flip. The
+blocker entry is also the canonical **awaiting-evidence** signal —
+see [§ Awaiting evidence](#awaiting-evidence--a-blocker-entry-never-a-new-glyph).
 
 ## Rubric pass (optional, surfacing-only)
 

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

@@ -57,7 +57,7 @@ or supersession before opening a new one.
 ### 1. Read the canonical template first
 
 The structure, frontmatter, lifecycle, and complexity-tier rules live
-in [`.agent-src.uncondensed/templates/roadmaps.md`](../../templates/roadmaps.md).
+in [`src/agent-src/templates/roadmaps.md`](../../templates/roadmaps.md).
 Read it before authoring. Do not restate its rules in the roadmap
 body — link the template if a phase needs to override one.
 

package/dist/agent-src/skills/skill-improvement-pipeline/SKILL.md

@@ -154,7 +154,7 @@ Ask the user:
 1. Read `project.upstream_repo` and `project.improvement_pr_branch_prefix` from `.agent-settings.yml`
 2. If `project.upstream_repo` is empty → ask user for the target repo
 3. Create branch: `{prefix}{learning-slug}` from `main`
-4. Commit changes to `.agent-src.uncondensed/` AND `.augment/`
+4. Commit changes to `src/` AND `.augment/`
 5. Push branch
 6. Create PR with title: `improve(agent): {short description}`
 7. Use the agent-improvement PR template if it exists

package/dist/agent-src/skills/skill-writing/SKILL.md

@@ -68,8 +68,8 @@ Ask: **"Does the model need this to do its job correctly?"**
 
 ### Skills and commands share the `.claude/skills/` namespace
 
-Skills in `.agent-src.uncondensed/skills/{name}/SKILL.md` AND commands in
-`.agent-src.uncondensed/commands/{name}.md` both project into
+Skills in `src/skills/{name}/SKILL.md` AND commands in
+`src/domains/{domain}/{name}/command.md` both project into
 `.claude/skills/` (see `scripts/condense.ts` →
 `generate_claude_skills` + `generate_claude_commands`). Claude treats
 the whole directory as native skills.
@@ -111,7 +111,7 @@ Do NOT create a skill or rule for:
 ### 0. Inspect, then run the Drafting Protocol
 
 Before writing, **inspect** the landscape: grep
-`.agent-src.uncondensed/skills/` and `rules/` for duplicates or
+`src/skills/` and `src/rules/` for duplicates or
 near-matches, and **analyze** 1–2 gold-standard peers (e.g. `pest-testing`,
 `php-coder`) to anchor shape and tone. If requirements are unclear or
 incomplete, stop and ask — do not assume.
@@ -308,7 +308,7 @@ asks for it.
 **Workspace layout** (all under `.gitignore`):
 
 ```
-.agent-src.uncondensed/skills/{name}/evals/
+src/skills/{name}/evals/
   triggers.json              # tracked — routing eval (§ 1c)
   evals.json                 # tracked — behavior eval definitions
   runs/                      # gitignored — per-iteration outputs

package/dist/agent-src/skills/token-optimizer/SKILL.md

@@ -79,11 +79,11 @@ INTENT
 
 | Asset | Path | Trigger keywords | What it does |
 |---|---|---|---|
-| `cli-output-handling` | `.agent-src.uncondensed/rules/cli-output-handling.md` | `verbose`, `tail`, `grep`, `CLI` | Wrap-tail-grep contract for any verbose command |
-| `rtk-output-filtering` | `.agent-src.uncondensed/skills/rtk-output-filtering/SKILL.md` | `rtk`, `verbose`, `filter`, `wrap` | Project-local rtk filters; wrapper command |
-| `token-efficiency` | `.agent-src.uncondensed/rules/token-efficiency.md` | `redirect`, `verbose`, `concise`, `tool` | Batch + parallelize tool calls; brevity floor |
+| `cli-output-handling` | `src/rules/cli-output-handling.md` | `verbose`, `tail`, `grep`, `CLI` | Wrap-tail-grep contract for any verbose command |
+| `rtk-output-filtering` | `src/skills/rtk-output-filtering/SKILL.md` | `rtk`, `verbose`, `filter`, `wrap` | Project-local rtk filters; wrapper command |
+| `token-efficiency` | `src/rules/token-efficiency.md` | `redirect`, `verbose`, `concise`, `tool` | Batch + parallelize tool calls; brevity floor |
 | `agent-handoff` | `src/domains/meta/agent-handoff/command.md` | `handoff`, `fresh`, `chat`, `context` | Context envelope for fresh-chat continuation |
-| `direct-answers` | `.agent-src.uncondensed/rules/direct-answers.md` | `brevity`, `flattery`, `severity`, `tiered` | Iron-Law brevity floor (kernel) |
+| `direct-answers` | `src/rules/direct-answers.md` | `brevity`, `flattery`, `severity`, `tiered` | Iron-Law brevity floor (kernel) |
 | `markitdown` | upstream: github.com/microsoft/markitdown | `PDF`, `DOCX`, `HTML`, `convert` | Document → markdown converter (authoritative-link only) |
 | `/cost:report` | TBD — an internal roadmap (local-only) § P1.2` | `cost`, `model spend`, `budget` | Per-session cost telemetry (planned) |
 | `api-cost-levers` | `docs/guidelines/agent-infra/api-cost-levers.md` | `cache`, `caching`, `batch`, `tiering`, `effort` | Anthropic billing levers: prompt caching, Batch API, model tiering, effort/output right-sizing |

package/dist/agent-src/skills/upstream-contribute/SKILL.md

@@ -79,12 +79,12 @@ Before ANY upstream work (branch, files, PR), ask the user:
 
 ### 1. Determine contribution type
 
-| Type | Uncondensed path | Condensed path |
+| Type | Source path | Condensed path |
 |---|---|---|
-| **New skill** | `.agent-src.uncondensed/skills/{name}/SKILL.md` | `.augment/skills/{name}/SKILL.md` |
-| **New rule** | `.agent-src.uncondensed/rules/{name}.md` | `.augment/rules/{name}.md` |
-| **New command** | `.agent-src.uncondensed/commands/{name}.md` | `.augment/commands/{name}.md` |
-| **New guideline** | `.agent-src.uncondensed/guidelines/{category}/{name}.md` | `.augment/guidelines/{category}/{name}.md` |
+| **New skill** | `src/skills/{name}/SKILL.md` | `.augment/skills/{name}/SKILL.md` |
+| **New rule** | `src/rules/{name}.md` | `.augment/rules/{name}.md` |
+| **New command** | `src/domains/{domain}/{name}/command.md` | `.augment/commands/{name}.md` |
+| **New guideline** | `docs/guidelines/{category}/{name}.md` | `.augment/guidelines/{category}/{name}.md` |
 | **Update to existing** | Same path as original | Same path as original |
 
 ### 2. Apply locally as override (immediate benefit)
@@ -151,7 +151,7 @@ git checkout -b feat/skills/{name}  # or fix/rules/{name}, etc.
 
 Create both files:
 
-- **Uncondensed version** → `.agent-src.uncondensed/{type}/{name}` (full, verbose, human-readable)
+- **Source version** → `src/{type}/{name}` (full, verbose, human-readable)
 - **Condensed version** → `.augment/{type}/{name}` (token-efficient, preserving all code blocks,
   headings, frontmatter, validation, gotchas)
 

package/dist/agent-src/skills/using-git-worktrees/SKILL.md

@@ -125,6 +125,27 @@ cd .worktrees/<branch-name>
 Branch names must match the project convention — see
 `commit-conventions` rule.
 
+### 4b. Seed the worktree — allow / deny list
+
+`git worktree add` checks out **tracked files only**. Everything
+gitignored — dependencies, generated projections, build output, local
+config — is absent. Seeding the wrong subset is the recurring
+worktree-trap family: a gate then fails (or falsely passes) for a
+reason the change did not cause.
+
+| Artefact | Action | Why |
+|---|---|---|
+| The dependency tree the § 5 install would produce (`vendor/`, `node_modules/`, `.venv/`, `target/`, …) | **symlink** from the primary checkout, or run the § 5 install | Absent ⇒ every gate that shells to a local binary dies on its first import. A **partial** tree (only the binary shim directory) is worse than none — it produces a scatter of spurious failures. Symlink or install fully; never half. |
+| Generated agent projections (`.augment/`, other tool trees) | **copy** from the primary checkout, or regenerate before running gates | Several gates read the projection tree. Absent ⇒ the gate reports "produced by regeneration but absent before" — red for a reason the contributor did not cause. |
+| Build output (`dist/`, compiled artefacts) | **regenerate**, never copy a stale tree | A stale copy makes a byte-identity check report generator drift that does not exist. |
+| Local settings (`.agent-settings.yml`, `.agent-settings.local.yml`) | **NEVER copy** | Gitignored, machine-local, and deliberately absent in CI. **Absent IS the CI shape** — copying it makes local gate results diverge from the gate that actually decides. A worktree that carries it is testing a configuration no pipeline runs. |
+| Secrets, `.env`, credential files | **NEVER copy** | Same reasoning, plus leak surface. |
+
+The list is encoded here, in the flow, on purpose: a separate committed
+manifest is warranted only when a **flow-external** tool needs to read
+it. Tools that seed their own throwaway worktrees already handle their
+own dependency link inline and need no manifest.
+
 ### 5. Install dependencies + verify baseline
 
 Auto-detect from manifest files:
@@ -167,6 +188,10 @@ starting a new worktree on the same branch.
   from manifest files.
 * **Skipping baseline** — failing tests pre-existed; later blamed on
   your own changes.
+* **Copying local settings in** — the worktree then passes gates the
+  pipeline fails (§ 4b deny list). Absent is correct.
+* **Partial dependency tree** — a `.bin`-only symlink yields a scatter
+  of spurious failures; bisect in a clean scratch worktree instead.
 
 ## Output format
 

package/dist/agent-src/templates/AGENTS.md

@@ -30,5 +30,5 @@
 2. **What language?** — Project-specific; agents mirror the user's language at runtime.
 3. **Where do I edit agent-config?** — Do not edit `.augment/` or `dist/agent-src/` here; they are installed artifacts. Project edits live in `agents/` and project source.
 4. **Lint / test / sync entry point?** — Project-specific (see project README); agent-config reinstalls via `composer update event4u/agent-config` or `npm update @event4u/agent-config`.
-5. **Where do the always-active rules live?** — `dist/agent-src/rules/` (kernel = 9 Iron-Law rules; tier-1 / tier-2 routed via `dist/agent-src/router.json`).
+5. **Where do the always-active rules live?** — `dist/agent-src/rules/` (kernel = 9 Iron-Law rules; tier-1 / tier-2 routed via `dist/router.json`).
 6. **Per-module agent docs?** — If `modules.enabled: true`, each module under `modules.root_paths` may carry its own `{agent_folder}/` (default `agents/`). See `module-management` skill.

package/dist/agent-src/templates/agents/agent-project-settings.example.yml

@@ -39,7 +39,7 @@ schema_version: 1
 # CI guard: a release bump of `package.json` must update this value
 # in lockstep — see scripts/check_template_pin_drift.ts (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "9.13.0"
+agent_config_version: "9.15.0"
 
 # --- Project identity ---
 project:

package/dist/agent-src/templates/command.md

@@ -49,7 +49,7 @@ suggestion:
 
 {One-line summary of what this command does.}
 
-**Source of truth:** `.agent-src.uncondensed/` — never read or edit `dist/agent-src/` or `.augment/` directly.
+**Source of truth:** `src/` — never read or edit `dist/agent-src/` or `.augment/` directly.
 
 ## Steps