@event4u/agent-config 5.10.1 → 6.0.0

package/.agent-src/rules/non-destructive-by-default.md

@@ -1,58 +0,0 @@
----
-type: "always"
-tier: "safety-floor"
-description: "Hard Floor: agent asks before prod-trunk commits/merges, deploys, pushes, prod data/infra, bulk deletions/infra commits; verify branch before each commit; no autonomy or roadmap bypass"
-alwaysApply: true
-load_context:
-  - ../contexts/authority/destructive-mechanics.md
-workspaces:
-  - engineering
-packs:
-  - engineering-base
----
-
-# Non-Destructive by Default
-
-Universal safety floor. Applies in every mode, every conversation, every turn. Autonomy, "just keep going", roadmap authorizations, and standing permissions narrow other rules — **none lift this one**.
-
-## The Iron Law
-
-```
-HARD FLOOR OVERRIDES EVERYTHING.
-NO AUTONOMY SETTING, NO ROADMAP STEP, NO STANDING INSTRUCTION,
-NO "JUST KEEP GOING" CAN BYPASS IT.
-```
-
-Triggers below require explicit user confirmation **on this turn** — not from a previous turn, not from a roadmap, not from a standing autonomy directive (anchor list: [`autonomous-execution § opt-in detection`](autonomous-execution.md#opt-in-detection--match-by-intent-not-exact-string)):
-
-| Trigger | Examples |
-|---|---|
-| **Production-branch merge** | `main`, `master`, `prod`, `production`, `release/*`, or any branch the project marks as deployment trunk |
-| **Commit on a production branch** | any `git commit` while `HEAD` is on a prod trunk (set above). **Verify branch before every commit** — `main` is opt-in only, never inferred from a prior turn or a merged PR that left the repo on `main` |
-| **Deploy / release** | `terraform apply` on prod, `kubectl apply` on prod, deploy scripts, release commands, tag pushes that trigger CI deployment |
-| **Push to remote** | any `git push` (also covered by [`scope-control`](scope-control.md), restated so the floor never weakens) |
-| **Production data / infra** | prod DB writes / migrations, prod config, secrets rotation, IAM / role / policy, DNS, anything in a `prod`-scoped path or pipeline |
-| **Whimsical / unscoped bulk deletion** | `rm -rf <dir>`, `git rm -r`, glob deletions, `DROP TABLE`, `TRUNCATE`, `git reset --hard` past unpushed work — when **not required** by the current task. Task-aligned WIP deletions are allowed (below) |
-| **Commit containing bulk deletions or infra changes** | commit whose diff removes a directory, deletes ≥5 unrelated files, or touches Terraform / Pulumi / k8s manifests / Ansible / cloud-config — surface diff and confirm even when [`commit-policy`](commit-policy.md) otherwise authorizes |
-
-Standing "just keep going" + next step crosses the floor → STOP, surface what's about to happen (one numbered-options block per [`user-interaction`](user-interaction.md)), wait. Other rules still apply to every other step.
-
-## Not in scope — deterministic regeneration
-
-Output regenerated from a tracked source (condensation, code-gen, formatter passes, lock-file rebuilds) is reversible from source — **not destructive**. Lives in [`autonomous-execution § Trivial`](autonomous-execution.md#trivial--just-act-do-not-ask). Per-file diff approval is theater.
-
-## Bulk deletions during WIP — allowed if task-connected
-
-Deletions inside an **active, user-stated task** are allowed in the working tree, even multiple files / folders — the Hard Floor moves to the **commit** (row 6), not the in-progress edit. Whimsical / drive-by / unnamed-scope deletions still trip the floor on the edit. Allowed / forbidden lists: [`destructive-mechanics § Bulk deletions during WIP`](../contexts/authority/destructive-mechanics.md).
-
-## Failure modes
-
-Full catalog (autonomy-as-cover, roadmap-as-authorization, refusing-named-deletions, commit-without-diff-surface, roadmap-step ≠ commit-authorization): [`destructive-mechanics § Failure modes`](../contexts/authority/destructive-mechanics.md).
-
-## Cloud Behavior
-
-Floor applies on every surface — Claude.ai Web, Skills API, any cloud agent. No "cloud override".
-
-## See also
-
-[`autonomous-execution`](autonomous-execution.md) · [`commit-policy`](commit-policy.md) · [`scope-control`](scope-control.md) · [`user-interaction`](user-interaction.md).

package/.agent-src/rules/persona-governance.md

@@ -1,93 +0,0 @@
----
-type: "auto"
-tier: "2a"
-description: "Creating/editing/proposing personas — enforce per-domain cap (≤ 2 specialists), ≥ 1 skill citation, deprecation path"
-triggers:
-  - path_prefix: ".agent-src.uncondensed/personas/"
-  - path_prefix: ".agent-src/personas/"
-  - keyword: "persona"
-  - keyword: "personas"
-  - phrase: "new persona"
-  - phrase: "add a persona"
-  - phrase: "specialist persona"
-  - phrase: "review lens"
-routes_to:
-  - "contract:persona-schema"
-applies_to_user_types:
-  - "maintainer"
-  - "developer"
-validator_ignore:
-  - type: "substring"
-    pattern: "../../docs/"
-    reason: "Rule routes to docs/contracts/persona-schema.md and docs/personas.md — the canonical persona catalog and schema live there by design."
-  - type: "substring"
-    pattern: ".agent-src.uncondensed/"
-    reason: "Rule documents the persona authoring tree (.agent-src.uncondensed/personas/) as the deprecation-path operand."
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
----
-
-# Persona Governance
-
-## Iron Law
-
-```
-ONE PERSONA, ONE OWNER, ONE SKILL CITATION, ONE DOMAIN SLOT.
-NO NEW SPECIALIST WITHOUT A DEPRECATION CANDIDATE WHEN THE DOMAIN IS FULL.
-```
-
-Personas are review lenses, not free real estate. Every specialist persona has a maintenance cost: it must stay aligned with the schema, the cited skills must still want it, and the per-domain reasoning surface must not bloat to the point that no single persona is load-bearing. This rule routes the agent to [`docs/contracts/persona-schema.md`](../docs/contracts/persona-schema.md) and [`docs/personas.md`](../../docs/personas.md) and enforces the four discipline checks below.
-
-## The four checks
-
-### 1. Per-domain cap — ≤ 2 specialised personas per content domain
-
-A **content domain** is a self-contained creative or technical surface that one or two specialist personas can fully cover. Current domains:
-
-| Domain | Specialists allowed | Examples |
-|---|---|---|
-| ai-video / ai-image / ai-audio | ≤ 2 | one director-shaped lens + one technical-tuning lens |
-| backend engineering | ≤ 2 | architect + ORM-tamer |
-| frontend engineering | ≤ 2 | component / lifecycle + design / a11y |
-| security | ≤ 2 | abuse-case + secrets-and-trust |
-| gtm / growth | ≤ 2 | CMO + RevOps |
-| money / strategy | ≤ 2 | finance-partner + strategist |
-| people / org | ≤ 2 | engineering-manager + people-strategist |
-| customer / discovery | ≤ 2 | discovery-lead + customer-success-lead |
-
-**Core personas** (`developer`, `senior-engineer`, `product-owner`, `stakeholder`, `critical-challenger`, `ai-agent`) are exempt — they are always-loaded cross-cutting lenses, not domain specialists.
-
-A new specialist into a full domain MUST come with a deprecation candidate from the same domain. The agent surfaces both, then runs an ai-council debate (per [`ai-council`](../../.agent-src/skills/ai-council/SKILL.md)) before any rename / merge / delete.
-
-### 2. Skill citation floor — ≥ 1 cite before merge
-
-A specialist persona without a `personas: [<id>]` citation in at least one skill's frontmatter is dead weight. The PR adding the persona MUST also add the citation, OR the PR is rejected. Citation map lives in [`docs/personas.md § Skill citations`](../../docs/personas.md#skill-citations).
-
-### 3. Deprecation path — delete immediately, record in commit
-
-A persona being removed is **deleted in the same commit** that lands its replacement. The commit message names the successor (or "merged into X") and cites the council decision (or maintainer rationale) that authorised it. No soak window — internal personas have no external consumers; a persona file kept around as a tombstone is dead weight the linter still loads. No silent deletes either: the audit trail is the commit, not a docs table.
-
-### 4. Schema conformance — the skill linter is the gate
-
-Every persona file is linted against [`docs/contracts/persona-schema.md`](../docs/contracts/persona-schema.md) by the skill linter: frontmatter shape, tier enum, wing enum, required sections per tier, line budget per tier (with wing override), `Unique Questions` ≥ 3, filename / id match, description ≤ 160 chars. The agent runs `python3 scripts/skill_linter.py` before any persona PR is marked ready.
-
-## Failure modes — what counts as a violation
-
-- Adding a third specialist to a full domain without naming the deprecation candidate.
-- Landing a specialist with no `personas: [<id>]` cite in any skill.
-- Renaming or deleting a persona file without naming the successor (or sunset reason) in the commit message.
-- Editing core-tier personas in-place with breaking changes (rename, section removal) without bumping to a new id.
-- Skipping the skill linter (`python3 scripts/skill_linter.py`) on a persona PR.
-
-## Day-one state
-
-Resolved 2026-05-17 via two-round ai-council debate (members: anthropic/claude-sonnet-4-5, openai/gpt-4o — converged delete-and-fold): `pixar-storyboard-artist` deleted; acting / beat-decomposition lens folded into [`pixar-storyteller`](../skills/pixar-storyteller/SKILL.md) skill body. Active per-domain count for `ai-video` now 2 (`ai-video-technical-director`, `hollywood-director`), within cap. Total active personas in root cluster: 24 (plus 5 advisors in `personas/advisors/`). Full inventory + ownership in [`docs/personas.md`](../../docs/personas.md).
-
-## See also
-
-- [`docs/contracts/persona-schema.md`](../docs/contracts/persona-schema.md) — schema lock, tiers, sections, size budgets, linter enforcement surface.
-- [`docs/personas.md`](../../docs/personas.md) — active persona catalog, citation map, ownership column.
-- [`ai-council`](../../.agent-src/skills/ai-council/SKILL.md) — neutral second-opinion mechanism used for merge / deprecation decisions.
-- [`skill-quality`](skill-quality.md) — sibling discipline rule for skill files.

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

@@ -1,97 +0,0 @@
----
-type: "auto"
-tier: "2b"
-alwaysApply: false
-description: "Merging/refactoring/condensing skills, rules, commands, or guidelines — prevent quality loss"
-triggers:
-  - intent: "merge skill"
-  - intent: "condense rule"
-  - intent: "refactor artifact"
-  - keyword: "Iron Law"
-validator_ignore:
-  - type: "substring"
-    pattern: ".agent-src.uncondensed/"
-    reason: "Rule references the authoring tree as the operand of condensation/preservation."
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
----
-
-# Preservation Guard
-
-When transforming any agent artifact (merge, refactor, condense, split, restructure),
-the result must be **at least as strong** as the original.
-
-## Iron Laws — every passage stays, telegraph is fine
-
-Sections marked **Iron Law** (any heading matching `# Iron Law`, `# Iron Laws`,
-`# The Iron Law`, at any heading level, including numbered variants like
-`Iron Law 1`, `Iron Law 2`) are **non-negotiable** and require the strictest
-preservation:
-
-- [ ] **Heading preserved verbatim** — exact text and exact heading level. Drop the
-  heading → the law is gone, even if the code block underneath survives.
-- [ ] **Fenced code blocks preserved byte-for-byte** — the law itself.
-- [ ] **Negation clauses preserved** — `NO X`, `NEVER Y`, `NOT Z` stay in. These
-  are the load-bearing exception denials, not filler.
-- [ ] **Every passage stays** — every paragraph, every list item, and every
-  fenced code block from the source survives in the condensed output, in
-  order. One paragraph → one paragraph; one bullet → one bullet. Dropping
-  whole sentences, merging two paragraphs into one, or skipping a list item
-  is forbidden, even if the surviving prose still "makes the point".
-- [ ] **No Iron Law downgrades** — `## Iron Law` MUST NOT become `### Iron Law`,
-  `**Iron Law:**`, or inline prose. Heading level is part of the prominence.
-
-**Telegraph style is encouraged for Iron Law bodies** — drop articles ("the",
-"a"), shorten phrasing, primitive grammar, terse cave-speak. Word count is
-not a budget; the structural unit count is. As long as every paragraph,
-bullet, and code block from the source is present, condense as hard as you
-want. What's forbidden is **deletion**: the rationale paragraph stays, the
-canonical-failure example stays, every "NEVER X" bullet stays.
-
-`scripts/check_condensation.py` enforces these mechanically — any violation is
-an `error`, not a warning.
-
-## Mandatory preservation checklist
-
-Before completing any transformation, verify:
-
-- [ ] **Iron Law sections** preserved per the rules above — heading, body, fenced blocks, rationale
-- [ ] **Strongest validation step** preserved — concrete verify/confirm actions survive
-- [ ] **Strongest example** preserved — the most illustrative code block or scenario stays
-- [ ] **Strongest anti-pattern** preserved — the most important "Do NOT" or failure mode stays
-- [ ] **Essential decision hints** preserved — if/when/unless logic that prevents mistakes
-- [ ] **Required sections** preserved — When to use, Procedure, Output, Gotchas, Do NOT
-- [ ] **Single clear responsibility** preserved — no scope creep from merging unrelated concerns
-- [ ] **Strong language** preserved — "MUST", "NEVER", "Do NOT" not weakened to "should", "avoid"
-
-## Reject criteria
-
-**REJECT** the transformation if it:
-
-- Removes or downgrades an Iron Law heading
-- Drops a paragraph, list item, or fenced code block from an Iron Law section
-- Strips negation clauses or canonical-failure prose from an Iron Law
-- Removes a concrete validation step without equivalent replacement
-- Removes the strongest example without equivalent replacement
-- Removes the strongest anti-pattern without equivalent replacement
-- Weakens routing or decision logic
-- Broadens scope by merging unrelated workflows
-- Weakens strong enforcement language
-
-## Applies to
-
-- Skill merges (combining two skills into one)
-- Skill splits (extracting part of a skill)
-- Refactoring (restructuring without behavior change)
-- Condensation (`.agent-src.uncondensed/` → `.agent-src/`)
-- Rule consolidation
-- Guideline restructuring
-
-## References
-
-- Skill: `skill-management` — condensation/refactoring modes
-- Skill: `skill-reviewer` — condensation safety checks
-- Command: `/condense` — condensation quality checklist
-- Linter: `scripts/skill_linter.py` — `check_condensation_quality()`

package/.agent-src/rules/provider-lifecycle-discipline.md

@@ -1,78 +0,0 @@
----
-type: "auto"
-tier: "2a"
-description: "Editing an AI video/image/audio adapter — declare lifecycle tier (experimental | stable | deprecated | community); never default to non-stable"
-triggers:
-  - keyword: "/video:"
-  - keyword: "/image:"
-  - keyword: "/audio:"
-  - keyword: "ai-video"
-  - keyword: "ai-image"
-  - keyword: "ai-audio"
-  - keyword: "adapter"
-  - keyword: "provider"
-  - path_prefix: "scripts/ai-video/adapters/"
-  - path_prefix: "agents/.ai-video.xml"
-  - phrase: "lifecycle"
-  - phrase: "default provider"
-routes_to:
-  - "contract:provider-lifecycle"
-applies_to_user_types:
-  - "creator"
-  - "developer"
-  - "maintainer"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
----
-
-# Provider Lifecycle Discipline
-
-## Iron Law
-
-```
-NEVER DEFAULT TO A NON-STABLE PROVIDER SILENTLY.
-SURFACE THE LIFECYCLE TIER. ASK BEFORE RUNNING.
-```
-
-This rule routes the agent to [`docs/contracts/provider-lifecycle.md`](../docs/contracts/provider-lifecycle.md) whenever a `/video:* / /image:* / /audio:*` surface fires, an adapter under `scripts/ai-video/adapters/` is read or edited, or `agents/templates/.ai-video.xml.example` (or the operator's `agents/.ai-video.xml`) is in play. The contract defines four tiers — `experimental | stable | deprecated | community` — and the agent's obligations per tier.
-
-## What this rule enforces
-
-1. **Read the tier before picking.** When the agent resolves a provider (from `--provider <id>`, from `<default-video-provider>` / `<default-image-provider>`, or from a skill's default), it MUST read both:
-   - the `<lifecycle>` element under `<provider id="…">` in `agents/templates/.ai-video.xml.example` (or the operator's `.ai-video.xml`), and
-   - the `Lifecycle:` header comment in `scripts/ai-video/adapters/<id>.sh`.
-   Mismatch between the two is a contract violation and MUST be surfaced before running.
-
-2. **Refuse-and-surface on non-stable.** If the resolved default is `experimental`, `deprecated`, or `community`, the agent surfaces the tier and the path to the contract, then emits **one** clarifying question (per [`ask-when-uncertain`](ask-when-uncertain.md)): either confirm the non-stable run, or pick a `stable` provider. No silent default. No "I'll just try it".
-
-3. **Refuse `deprecated` without naming the successor.** A `deprecated` adapter's header comment records the successor; the agent surfaces "X is deprecated; successor: Y" before any run, even with confirmation.
-
-4. **Record the tier in the run summary.** The summary line emitted after every `/video:* / /image:* / /audio:*` run names the chosen provider AND its tier. This is the audit-log entry the agent-in-the-loop enforcement model rests on.
-
-5. **Promotion is the maintainer's call.** The agent never auto-promotes `experimental → stable`. It MAY draft a promotion checklist (see [`docs/contracts/provider-lifecycle.md § 2`](../docs/contracts/provider-lifecycle.md#-2--promotion-path)) for maintainer review, but the tier-flip commit is human-authored.
-
-## Failure modes — what counts as a violation
-
-- Running `/video:scene` against the `<default-video-provider>` without reading the lifecycle tag first → violation.
-- Picking a `community` provider because it was named in the prompt, without surfacing the tier → violation.
-- Editing an adapter and leaving its header `Lifecycle:` comment out of sync with `agents/templates/.ai-video.xml.example` → violation (CI does not catch this; the agent must).
-- Auto-promoting an adapter from `experimental` to `stable` because "dry-run worked" → violation. Promotion requires a maintainer-captured real-API smoke trace under `agents/reference/ai-video/smoke-traces/`.
-
-## Day-one state
-
-All five shipped adapters (`openai-images`, `gemini-veo`, `kling`, `higgsfield`, `sora`) ship as `experimental`. This means **every** default `/video:* / /image:*` run today triggers the refuse-and-surface path. That is intentional — it is the conservative-by-construction posture the contract argues for. As maintainers capture smoke traces and flip individual adapters to `stable`, the friction reduces per-adapter.
-
-## Why agent-in-the-loop, not Python gate
-
-A Python pre-run gate enumerating tier-by-command rules would either be too coarse (`experimental → block`, breaking day-to-day dev iteration) or too detailed (per-command tier matrix, drifting from reality on every new provider). The agent reading the tag at run time, surfacing the tier, and asking is the correct enforcement surface: the model that picked the provider is the model that surfaces the obligation, and the human is the policy decision point.
-
-The CI guarantee is structural reachability — the linter would fail if a provider was declared in `agents/templates/.ai-video.xml.example` without a lifecycle tag (extension planned). It does not enforce the runtime obligation; the agent does.
-
-## See also
-
-- [`docs/contracts/provider-lifecycle.md`](../docs/contracts/provider-lifecycle.md) — the full tier definitions, promotion / demotion criteria, and day-one assignment matrix.
-- [`scripts/ai-video/lib/adapter-contract.md`](../../scripts/ai-video/lib/adapter-contract.md) — the four-method shell surface every adapter implements; the tier tag is read alongside this contract.
-- [`media-governance-routing`](media-governance-routing.md) — sibling tier-2a rule that surfaces the prompt-side policy layer; this rule covers the provider-side discipline.
-- [`ask-when-uncertain`](ask-when-uncertain.md) — the one-question-per-turn discipline the refuse-and-surface path uses.

package/.agent-src/rules/roadmap-progress-sync.md

@@ -1,99 +0,0 @@
----
-type: "auto"
-tier: "1"
-description: "Any roadmap touch (file move, checkbox flip, phase change) regens dashboard same response; archive at 0 open"
-triggers:
-  - path_prefix: "agents/roadmaps/"
-  - command: "/roadmap:process-step"
-  - command: "/roadmap:process-phase"
-  - command: "/roadmap:process-full"
-routes_to:
-  - "guideline:agent-infra/roadmap-progress-mechanics"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
----
-
-# Roadmap Progress Sync
-
-## Iron Law 1 — dashboard sync, same response
-
-```
-ANY ROADMAP TOUCH → REGENERATE THE DASHBOARD, SAME RESPONSE.
-NO EXCEPTIONS. NO "I'LL DO IT AT THE END". NO BATCHING ACROSS TURNS.
-```
-
-Roadmap touch = create / rename / delete / move file, add/rename/remove a phase, OR flip any checkbox (`[ ]` ↔ `[x]` ↔ `[~]` ↔ `[-]`). Regen command: `./agent-config roadmap:progress`. Archive (`git mv` → `archive/`) the moment `count_open == 0` — same response.
-
-## Iron Law 2 — real-time checkbox cadence (autonomous execution)
-
-```
-EVERY DONE STEP FLIPS [ ] → [x] IN THE SAME REPLY THAT LANDS THE WORK.
-NO "I UPDATE THE ROADMAP AT THE END OF THE PHASE."
-A REPLY THAT LANDS A VERIFIED STEP WITHOUT FLIPPING ITS CHECKBOX
-IS A RULE VIOLATION, NOT AN OVERSIGHT.
-```
-
-`/roadmap:process-step`, `/roadmap:process-phase`, `/roadmap:process-full`, and any other multi-step autonomous run flip the box for step N **before** moving on to step N+1. The checkbox itself is the real-time monitor — the markdown file is the source of truth, the dashboard is a derived view.
-
-`command:` triggers in this rule's frontmatter load it the moment any `/roadmap:process-*` command fires and keep it loaded for the whole run — independent of whether the agent is editing files under `agents/roadmaps/`. The loop carries its own deterministic flip-guard at [`roadmap-process-loop § 5b`](../contexts/execution/roadmap-process-loop.md#5b-flip-guard--deterministic) — defense-in-depth, not a substitute for the inline flip.
-
-**Step counts as done** when code/doc saved AND verification cited in step passed (fresh output, this reply or earlier).
-
-**Glyph semantics** — single source of truth, aligned with `scripts/update_roadmap_progress.py` and [`roadmap-management`](../skills/roadmap-management/SKILL.md):
-
-| Glyph | Meaning | Counter |
-|---|---|---|
-| `[ ]` | open — planned, not done | `count_open` |
-| `[x]` | done — landed + verified | `count_done` |
-| `[~]` | deferred — planned, not happening **this** run; blocks archive (Iron Law 3) | `count_deferred` |
-| `[-]` | cancelled — scope dropped | `count_cancelled` |
-
-`[~]` is **not** "in-progress". Mid-reply work-in-flight has no checkbox change until step lands — normal `[ ] → [x]`.
-
-**Dashboard regen cadence — opt-in batching.** Checkbox flip is non-batchable. **Subprocess regen** (`./agent-config roadmap:progress`) is batchable per `roadmap.dashboard_regen_cadence` (`per_step` default · `every_5_steps` · `phase_boundary`). Run end, phase boundary, any file-shape touch (rename / phase add / archive — Iron Law 1) always force immediate regen regardless of cadence.
-
-## Iron Law 3 — no silent archive with unresolved deferred items
-
-```
-A ROADMAP WITH `[~]` DEFERRED ITEMS NEVER AUTO-ARCHIVES SILENTLY.
-SURFACE EVERY DEFERRED STEP. ASK USER WHAT HAPPENS TO THE PLAN.
-A SILENT ARCHIVE THAT BURIES PLANNED-FOR-LATER WORK
-IS A RULE VIOLATION, NOT A CONVENIENCE.
-```
-
-When closure check fires (`count_open == 0` and `count_deferred > 0`), agent MUST:
-
-1. Enumerate every `[~]` step (phase + step text + any inline `<!-- deferred: ... -->` annotation).
-2. Present numbered options (per [`user-interaction`](user-interaction.md)) — at minimum:
-   1. **Follow-up roadmap (draft)** — spawn `agents/roadmaps/road-to-<slug>.md` with `status: draft`, `parent_roadmap: <this-slug>`, deferred steps lifted verbatim into phases. Draft hidden from dashboard until flipped to `ready`.
-   2. **Follow-up roadmap (ready, blocked)** — spawn with `status: ready` (default), `parent_roadmap: <this-slug>`, plus body note `> Blocked until <condition>`. Dashboard surfaces it; execution waits.
-   3. **Keep in this archive** — confirm deferred items stay searchable in archived file; no follow-up. Records explicit decision-to-drop in same reply.
-   4. **Restore selected items to `[ ]`** — finish them in this roadmap before archive.
-   5. **Convert selected items to `[-]` cancelled** — drop with rationale recorded inline.
-3. Only after user resolves deferrals does `git mv` to `archive/` run. Dashboard regen happens after resolution.
-
-Migration mechanics (file naming, frontmatter, body shape, parent back-link) live in [`roadmap-management § Spawn follow-up from deferred items`](../skills/roadmap-management/SKILL.md). Rule owns obligation; skill owns procedure.
-
-## Pre-send self-check — MANDATORY
-
-Before sending any reply that landed roadmap work:
-
-1. Did this reply land a step (code/doc saved + verification passed)?
-2. Is its checkbox flipped to `[x]` / `[~]` / `[-]` in `agents/roadmaps/<file>.md`? If no → flip, then continue.
-3. Is regen due now per `roadmap.dashboard_regen_cadence`?
-   - `per_step` → yes, always.
-   - `every_5_steps` → yes when this is the 5th, 10th, … closed step in the run, or the last step of the reply.
-   - `phase_boundary` → only when this reply closes the phase or run.
-   - Any file-shape touch (rename / phase add / archive) → yes, regardless of cadence.
-   If yes and not run yet → run `./agent-config roadmap:progress`, then continue.
-4. Did `count_open` reach 0?
-   - **No** → continue normally.
-   - **Yes + `count_deferred == 0`** → `git mv` to `archive/` and regen again — same reply.
-   - **Yes + `count_deferred > 0`** → STOP. Run Iron Law 3 deferred-resolution flow (surface items + numbered options + wait). Archive only after resolution.
-
-Any "no" at step 2 → reply is incomplete. Do not send. Skipped step 3 regen fine when cadence permits — checkbox truth lives in markdown file. Skipping deferred-resolution gate at step 4 is **never** acceptable; it is the canonical "lost-information" failure mode this rule exists to prevent.
-
-Long-form mechanics (failure-mode catalog, Copilot fallback, `[~]` vs `[ ]` semantics, hook + CI defence-in-depth) live in `guideline:agent-infra/roadmap-progress-mechanics`.
-Trigger-set above activates this routing under the `balanced` and `full` profiles.

package/.agent-src/rules/scope-control.md

@@ -1,68 +0,0 @@
----
-type: "always"
-tier: "safety-floor"
-description: "Scope control — no unsolicited architectural changes, refactors, or library replacements"
-alwaysApply: true
-load_context:
-  - ../contexts/authority/scope-mechanics.md
-  - ../contexts/authority/kernel-rule-edits.md
-workspaces:
-  - engineering
-packs:
-  - engineering-base
----
-
-# Scope Control
-
-- Do NOT introduce architectural changes unless explicitly requested.
-- Do NOT replace existing patterns with alternatives.
-- Do NOT refactor existing code solely to comply with current rules.
-- Do NOT suggest new libraries unless explicitly requested.
-- Modify existing code only when directly related to the current change, required for bug fixes / security, or explicitly requested.
-- New / modified code MUST follow all coding rules.
-- Stay within established project structure and conventions.
-- When unsure about scope, ask the user.
-
-## Git operations — permission-gated
-
-The user decides the git shape. Never improvise. Commit specifics: canonical [`commit-policy`](commit-policy.md).
-
-- NEVER commit, push, merge, rebase, or force-push without explicit user permission.
-- NEVER create / switch / delete a branch without explicit permission — includes spike, scratch, throwaway, worktree branches.
-- NEVER create, close, reopen, or change the target of a pull request without permission.
-- NEVER push a tag or create a release without permission.
-- NEVER pin versions, release targets, deprecation dates, or git tags in roadmaps / plans / tickets — they plan **work**, not releases. Detail: [`scope-mechanics § Roadmap shape`](../contexts/authority/scope-mechanics.md).
-- Task seems to need a separate branch / PR → STOP and **brief before asking** ([`scope-mechanics § Brief-before-asking`](../contexts/authority/scope-mechanics.md)).
-- BEFORE the first commit on related work, **inventory** existing branches and open PRs. Plausible base beyond the current branch → STOP and ask with numbered options — never improvise. Commands + 4-option template + diverging-stack failure mode: [`scope-mechanics § Branch-base inventory`](../contexts/authority/scope-mechanics.md).
-
-"Explicit permission" = user said so **this turn or in a standing instruction not yet revoked**. Earlier permission for a different operation does not carry over.
-
-## Authoring vs. implementation
-
-```
-"CREATE / DRAFT" AUTHORIZES THE ARTIFACT, NOT ITS EXECUTION.
-NEW TASK NEVER INHERITS PRIOR AUTONOMY.
-```
-
-`create / draft / write / erstelle …` → artifact only. Execution verbs flip scope; mixed → ask. Detail: [`scope-mechanics`](../contexts/authority/scope-mechanics.md).
-
-## Production, infrastructure, bulk-destructive — Hard Floor
-
-A subset is **never** autonomous, regardless of standing autonomy. Canonical: [`non-destructive-by-default`](non-destructive-by-default.md). Triggers (prod-branch merges, deploys, prod data / infra, bulk-destructive) + this-turn-only clarification: [`scope-mechanics § Production, infrastructure, bulk-destructive`](../contexts/authority/scope-mechanics.md).
-
-## Kernel-rule edits — slow-rollout guarantee
-
-Own PR, ≥ 24 h between merges. Autonomous mandate does not lift — soak guarantee. CI / labels / scope: [`kernel-rule-edits`](../contexts/authority/kernel-rule-edits.md).
-
-## Decline = silence — no re-asking on the same task
-
-After the user **declines** a proposal (branch switch, PR creation, tag/release, separate worktree, version pinning), do **not** raise it again on the same task. Decline stands until reopened. Timing: [`scope-mechanics § Decline = silence`](../contexts/authority/scope-mechanics.md).
-
-## Fenced step — user-set review gates
-
-```
-USER FENCED OFF EXECUTION → DELIVER + HAND BACK.
-NO "READY TO IMPLEMENT?" / "PHASE 1?" RE-ASK.
-```
-
-Fence (*"plan only"*, *"review first"*, German equivalents) stands until reopened — like `Decline = silence`. Follow-ups cover the deliverable, not its execution. Failure modes + bypass: [`scope-mechanics § Fenced step`](../contexts/authority/scope-mechanics.md).

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

@@ -1,49 +0,0 @@
----
-type: "always"
-tier: "1"
-description: "User interrupts override the current task — STOP, complete new task in full, then ASK before resuming; never silently return to prior work"
-alwaysApply: true
-load_context:
-  - ../contexts/execution/interrupt-examples.md
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
----
-
-# User-Interrupt Priority
-
-A new instruction mid-flight is **not** a continuation. Examples and failure modes: [`contexts/execution/interrupt-examples.md`](../contexts/execution/interrupt-examples.md).
-
-## The Iron Law
-
-```
-NEW TASK FROM USER MID-FLIGHT → STOP CURRENT TASK.
-COMPLETE NEW TASK IN FULL.
-THEN ASK BEFORE RESUMING THE OLD TASK.
-NEVER SILENTLY RESUME.
-```
-
-Holds regardless of `personal.autonomy`, a standing autonomy directive, or roadmap authorization. Autonomy narrows trivial workflow questions — it does not authorize ignoring a fresh instruction.
-
-## Classify every user turn
-
-| Bucket | Signal | Action |
-|---|---|---|
-| **Continuation** | Same deliverable + target + success criterion. "weiter", "next step". | Keep working. |
-| **Clarification** | Question / correction about the current task. No new deliverable. | Answer, then continue. |
-| **Interrupt** | Different deliverable, target, or success criterion. Meta-tasks ("audit", "stop and analyze") count. | STOP. Run new task. ASK before resume. |
-
-In doubt → treat as interrupt. Cost of a spurious ask is one turn; cost of silent-resume is the rest of the unwanted work.
-
-## Stop-ask-resume protocol
-
-1. **STOP** — abandon the current tool plan. No "one more check" unless the new instruction says so.
-2. **EXECUTE** the new task in full. All other rules (Hard Floor, scope, autonomy) apply.
-3. **ASK** when done — name the interrupted task and request a resume decision:
-
-```
-Done with <new task>. Resume <interrupted task name>? (yes / no / different)
-```
-
-Only resume on `yes` or a restatement. "and then continue with X" = explicit resume authorization; no re-ask.

package/.agent-src/rules/verify-before-complete.md

@@ -1,78 +0,0 @@
----
-type: "always"
-tier: "2a"
-description: "Verify before completion — run tests and quality tools before claiming done"
-alwaysApply: true
-load_context:
-  - ../contexts/execution/verification-mechanics.md
-workspaces:
-  - engineering
-packs:
-  - engineering-base
----
-
-# Verify Before Completion
-
-## The Iron Law
-
-```
-NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
-```
-
-If you haven't run the verification command **in this message**, you cannot claim it passes.
-
-## The Gate
-
-Before claiming ANY work is complete:
-
-1. **IDENTIFY** — What command proves this claim? (tests, type-checker, linter, build — whichever the project actually runs)
-2. **RUN** — Execute the full command (fresh, complete, not cached)
-3. **READ** — Full output, check exit code, count failures
-4. **VERIFY** — Does the output actually confirm the claim?
-5. **ONLY THEN** — Make the claim
-
-Skip any step = the claim is unverified.
-
-## When this applies
-
-- About to claim **all work is done** (not after individual edits)
-- About to say "done" or "complete"
-- Before suggesting to commit, push, or create a PR
-- Any statement implying all work is finished
-
-## Red flags — STOP immediately
-
-- Using "should pass", "probably works", "seems fine"
-- Expressing satisfaction before running verification
-- About to commit/push without running tests + quality
-- Trusting a previous run from earlier in the conversation
-- Relying on partial verification (ran tests but skipped the type-checker / linter)
-- ANY wording implying success without fresh evidence
-
-## Verification commands
-
-For specific commands → see the `quality-tools` skill.
-
-For the detailed evidence-gate playbook (claim→command mapping, output
-inspection, end-of-work sequence) → see the `verify-completion-evidence`
-skill.
-
-## Mechanics — when to run what, per-task evidence, confidence, break-glass
-
-The decision logic for **when** to run quality tools vs. tests, the
-per-task-type minimum-evidence table, confidence gating (High /
-Medium / Low), and the break-glass reduction during live incidents
-all live in
-[`verification-mechanics`](../contexts/execution/verification-mechanics.md).
-The Iron Law and the Gate above are the obligation surface; the
-mechanics context is the lookup material the agent pulls when the
-gate fires.
-
-## Examples
-
-Pattern Memory — wrong / right / why demos for the Iron Law and the
-red-flags list:
-[`verify-before-complete-demos`](../docs/guidelines/agent-infra/verify-before-complete-demos.md)
-(hedged claims, trusting earlier runs, partial-verification creep).
-Outcome baseline locked at
-[`tests/golden/outcomes/verify_before_complete.json`](../../tests/golden/outcomes/verify_before_complete.json).