@event4u/agent-config 6.0.0 → 6.1.0

package/README.md

@@ -66,7 +66,7 @@ is platform operation, not a user-work flow.)
 </p>
 
 <p align="center">
-  <sub>Distribution: <code>npm install @event4u/agent-config</code> · npm-primary per <a href="docs/decisions/ADR-033-distribution-identity-npm-primary.md">ADR-033</a>. Major bumps follow <a href="CONTRIBUTING.md#versioning-policy">semver</a>; each ships a <a href="CHANGELOG.md#breaking--v400-unified-setup-road-to-unified-setup"><code>### Breaking</code></a> entry — all majors indexed in <a href="BREAKING_CHANGES.md">BREAKING_CHANGES.md</a>.</sub>
+  <sub>Distribution: <code>npm install @event4u/agent-config</code>. Major bumps follow <a href="CONTRIBUTING.md#versioning-policy">semver</a>; each ships a <a href="CHANGELOG.md#breaking--v400-unified-setup-road-to-unified-setup"><code>### Breaking</code></a> entry — all majors indexed in <a href="BREAKING_CHANGES.md">BREAKING_CHANGES.md</a>.</sub>
 </p>
 
 ---
@@ -76,7 +76,7 @@ is platform operation, not a user-work flow.)
 <details>
 <summary><b>Catalog at a glance</b> — raw artefact counts (maintainer reference)</summary>
 
-[![Skills](https://img.shields.io/badge/Skills-227-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-79-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-150-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-78-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-24-orange?style=flat-square)](dist/agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](dist/agent-src/personas/advisors/)
+[![Skills](https://img.shields.io/badge/Skills-230-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-83-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-147-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-81-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-24-orange?style=flat-square)](dist/agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](dist/agent-src/personas/advisors/)
 
 The headline is the **experience** (profile + packs), not the raw counts. Full catalog: [`docs/catalog.md`](docs/catalog.md).
 </details>
@@ -405,7 +405,7 @@ When a prompt matches a command's purpose ("setze ticket ABC-123 um" → `/imple
 | [**Migration**](docs/MIGRATION.md) | Per-version upgrade steps |
 | [**Showcase**](docs/showcase.md) | More examples & expected behavior |
 
-Browse content: [all 150 commands](dist/agent-src/commands/) · [skills catalog](docs/skills-catalog.md) · [full catalog](docs/catalog.md) · [`llms.txt`](llms.txt).
+Browse content: [all 147 commands](dist/agent-src/commands/) · [skills catalog](docs/skills-catalog.md) · [full catalog](docs/catalog.md) · [`llms.txt`](llms.txt).
 
 ---
 

package/dist/agent-src/commands/agent-handoff.md

@@ -6,6 +6,7 @@ intent: "Generate a session-handoff summary to continue work in a fresh chat"
 routes_to: [agent-docs-writing]
 replaces: []
 tier: 0
+visibility: visible
 skills: [agent-docs-writing]
 description: Generate a context summary for continuing work in a fresh chat. Replaces the session system.
 suggestion:
@@ -114,10 +115,10 @@ do not auto-execute.
   fingerprint derived from the platform `session_id` (schema v4, see
   [`chat-history-platform-hooks`](../../agents/settings/contexts/chat-history-platform-hooks.md)).
   Works only on the same machine and same repo, but captures every
-  phase / decision any session logged. Inspect with `/chat-history show`;
-  pull prior-session context into the current chat verbatim with
-  `/chat-history import`; mine a prior session for project-improving
-  learnings with `/chat-history learn`.
+  phase / decision any session logged. Pull prior-session context into
+  the current chat verbatim with `/chat-history import`; mine a prior
+  session for project-improving learnings with
+  `/memory mine-session --mode=proposals`.
 
 Prefer `/agent-handoff` for planned context switches across tools or
 machines; use `/chat-history import` after a crash or fresh-chat reopen

package/dist/agent-src/commands/agent-status.md

@@ -6,6 +6,7 @@ intent: "Report the current agent session state, mode, and progress at a glance"
 routes_to: [agent-docs-writing]
 replaces: []
 tier: 0
+visibility: visible
 skills: [agent-docs-writing]
 description: Show current conversation stats — message count, token costs, task progress, next freshness check.
 suggestion:

package/dist/agent-src/commands/agents/audit.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: agents-audit
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: audit
 description: Audit agent infrastructure — token overhead, rule triggers, AGENTS.md health, Capability-over-Structure adherence, stale references. Read-only, suggest-only, never auto-apply.

package/dist/agent-src/commands/agents/init.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: agents-init
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: init
 description: Initialize the agent layer for a consumer project — creates AGENTS.md and .github/copilot-instructions.md from package templates, auto-detects stack, never leaks other projects' identifiers.
@@ -177,6 +178,8 @@ contract). On skip, do nothing — the block stays opt-in.
 
 If `agents/` directory does not exist, suggest running `/optimize agents-dir --scaffold`.
 If `.agent-settings.yml` does not exist, suggest running `scripts/install` (then `/onboard` for first-run setup).
+If module candidates surfaced in Step 7 but the user skipped, note that
+`python3 scripts/propose_modules_config.py` can be re-run anytime.
 
 ## Rules
 

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

@@ -3,6 +3,7 @@ model_tier: inherit
 name: agents-optimize
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: optimize
 description: Refactor AGENTS.md to the Thin-Root contract (caps, pointer ratio, capability bullets, emergency-triage) and propagate to tool stubs. Suggest only, never auto-apply.

package/dist/agent-src/commands/agents/user/accept.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: agents-user-accept
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: user
 skills: [agents]

package/dist/agent-src/commands/agents/user/init.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: agents-user-init
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: user
 skills: [agents]

package/dist/agent-src/commands/agents/user/review.md

@@ -3,6 +3,7 @@ model_tier: high
 name: agents-user-review
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: user
 skills: [agents]

package/dist/agent-src/commands/agents/user/show.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: agents-user-show
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: user
 skills: [agents]

package/dist/agent-src/commands/agents/user/update.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: agents-user-update
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: user
 description: Open .agent-user.md in the user's IDE for manual edit; validates schema and 100-line cap on save.

package/dist/agent-src/commands/agents/user.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: agents-user
 pack: meta
 tier: 2
+visibility: internal
 cluster: agents
 sub: user
 description: User-persona file (.agent-user.md) — interview, render, and maintain who the user is and how they want to be addressed.

package/dist/agent-src/commands/agents.md

@@ -7,6 +7,7 @@ intent: "Manage the AGENTS.md file family — init, optimize, audit, user person
 routes_to: [agents-init, agents-optimize, agents-audit, agents-user]
 replaces: []
 tier: 1
+visibility: advanced
 description: Agent-layer orchestrator — routes to init, optimize, audit. Covers AGENTS.md and its multi-tool stubs (CLAUDE.md, GEMINI.md, copilot-instructions.md, .cursorrules).
 cluster: agents
 type: orchestrator

package/dist/agent-src/commands/analytics/prune.md

@@ -1,8 +1,9 @@
 ---
 model_tier: medium
 name: analytics-prune
-pack: meta
+pack: analytics
 tier: 2
+visibility: internal
 cluster: analytics
 sub: prune
 description: Drop events older than the 90-day retention window from the local analytics log. Atomic and idempotent.
@@ -14,7 +15,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - analytics
 ---
 
 # /analytics prune

package/dist/agent-src/commands/analytics/show.md

@@ -1,8 +1,9 @@
 ---
 model_tier: medium
 name: analytics-show
-pack: meta
+pack: analytics
 tier: 2
+visibility: internal
 cluster: analytics
 sub: show
 description: Render top prompts, launcher → completion rate per role, average session length, and knowledge-source usage from the local analytics log.
@@ -14,7 +15,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - analytics
 ---
 
 # /analytics show

package/dist/agent-src/commands/analytics.md

@@ -1,8 +1,9 @@
 ---
 model_tier: medium
 name: analytics
-pack: meta
+pack: analytics
 tier: 2
+visibility: internal
 description: Analytics orchestrator — routes to show, prune. Local-only workspace event log under `~/.event4u/agent-config/workspace/analytics/`.
 cluster: analytics
 type: orchestrator
@@ -14,7 +15,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - analytics
 ---
 
 # /analytics

package/dist/agent-src/commands/analyze-reference-repo.md

@@ -3,6 +3,7 @@ model_tier: high
 name: analyze-reference-repo
 pack: engineering-base
 tier: 2
+visibility: internal
 skills: [project-analyzer, learning-to-rule-or-skill]
 description: Analyze an external reference repository (competitor, inspiration, peer) and produce a structured comparison + adoption plan for this project.
 suggestion:

package/dist/agent-src/commands/bug-fix.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: bug-fix
 pack: engineering-base
 tier: 2
+visibility: internal
 skills: [bug-analyzer, pest-testing]
 description: Plan and implement a bug fix — based on investigation, with quality checks and test verification
 council_depth: deep

package/dist/agent-src/commands/bug-investigate.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: bug-investigate
 pack: engineering-base
 tier: 2
+visibility: internal
 skills: [bug-analyzer, sentry-integration]
 description: Investigate a bug — auto-detect ticket from branch, gather Jira/Sentry/description context, trace root cause
 council_depth: deep

package/dist/agent-src/commands/challenge-me/vision.md

@@ -1,8 +1,9 @@
 ---
 model_tier: inherit
 name: challenge-me-vision
-pack: meta
+pack: product-reasoning
 tier: 2
+visibility: internal
 cluster: challenge-me
 sub: vision
 description: "Stress-test a plan or idea by one-question-at-a-time interview until 95% confidence — emits a copyable Markdown vision pitch for tickets, roadmaps, or fresh-chat handoff."
@@ -13,7 +14,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - product-reasoning
 ---
 
 # /challenge-me vision

package/dist/agent-src/commands/challenge-me/with-docs.md

@@ -1,8 +1,9 @@
 ---
 model_tier: medium
 name: challenge-me-with-docs
-pack: meta
+pack: product-reasoning
 tier: 2
+visibility: internal
 cluster: challenge-me
 sub: with-docs
 description: "Doc-aware /challenge-me — 95%-confidence interview with session glossary vs CONTEXT.md, load-bearing claim-vs-code verification, optional CONTEXT.md patch + ADR candidates in the pitch."
@@ -13,7 +14,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - product-reasoning
 ---
 
 # /challenge-me with-docs

package/dist/agent-src/commands/challenge-me.md

@@ -1,8 +1,9 @@
 ---
 model_tier: medium
 name: challenge-me
-pack: meta
+pack: product-reasoning
 tier: 2
+visibility: internal
 description: Challenge-me orchestrator — routes to vision, with-docs
 cluster: challenge-me
 type: orchestrator
@@ -13,7 +14,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - product-reasoning
 ---
 
 # /challenge-me

package/dist/agent-src/commands/chat-history/import.md

@@ -1,8 +1,9 @@
 ---
 model_tier: medium
 name: chat-history-import
-pack: meta
+pack: memory
 tier: 2
+visibility: internal
 cluster: chat-history
 sub: import
 description: Surface prior chat-history sessions as a numbered table, let the user pick one, read it silently, and emit a short summary plus a resume offer — selective, user-driven cross-session import
@@ -13,7 +14,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - memory
 ---
 <!-- cloud_safe: noop -->
 
@@ -31,15 +32,15 @@ This is the opt-in counterpart to the read-path filter (Phase 3 of
 `road-to-chat-history-session-isolation`): default reads stay
 session-scoped; `import` is the explicit surface for crossing the
 session boundary. For project-improving learnings derived from a
-prior session, see [`/chat-history learn`](learn.md).
+prior session, see [`/memory mine-session --mode=proposals`](../memory/mine-session/command.md).
 
 ## When NOT to use
 
-- Inspect the current session — that is the default of
-  `/chat-history show` plus `scripts/chat_history.py read`.
+- Inspect the current session — use the host's native transcript /
+  session view, or `scripts/chat_history.py read`.
 - Generate a learning proposal from a prior session — use
-  [`/chat-history learn`](learn.md), which orchestrates
-  `learning-to-rule-or-skill` on the picked session.
+  [`/memory mine-session --mode=proposals`](../memory/mine-session/command.md),
+  which frames the session's signals and runs `learning-to-rule-or-skill`.
 - Bulk-import all sessions — out of scope for v1. One session per
   invocation; multi-pick is v2.
 - Search prior sessions by content — out of scope for v1; no fuzzy
@@ -164,8 +165,7 @@ instruction.
 
 ## See also
 
-- [`/chat-history learn`](learn.md) — pick a prior session and turn it into a project-improving proposal via `learning-to-rule-or-skill`
-- [`/chat-history show`](show.md) — current-session inspector
+- [`/memory mine-session --mode=proposals`](../memory/mine-session/command.md) — pick a prior session and turn it into a project-improving proposal via `learning-to-rule-or-skill` (the former `/chat-history learn`)
 - [`chat-history-platform-hooks`](../../../agents/settings/contexts/chat-history-platform-hooks.md) — read contract, isolation default, opt-in cross-session path
 - [`scripts/chat_history.py`](../../../scripts/chat_history.py) — `sessions` and `read --session` CLI surface
 - [`user-interaction`](../../rules/user-interaction.md) — numbered-options Iron Law

package/dist/agent-src/commands/chat-history.md

@@ -2,59 +2,61 @@
 model_tier: medium
 name: chat-history
 disable-model-invocation: true
-pack: meta
+pack: memory
 tier: 2
-description: Chat-history orchestrator — routes to show, import, learn
+visibility: internal
+description: Chat-history orchestrator — routes to import (selective cross-session resume). Mining moved to /memory mine-session; raw-log inspection uses the host's native transcript view.
 cluster: chat-history
 type: orchestrator
 suggestion:
   eligible: true
-  trigger_description: "show chat-history status, inspect agents/runtime/.agent-chat-history log, import a prior session into the current chat, mine a prior session for project-improving learnings"
-  trigger_context: "user wants to inspect the persistent agents/runtime/.agent-chat-history log, pull a prior session in verbatim, or extract learnings from a prior session"
+  trigger_description: "import a prior session into the current chat, resume a previous session, pull a prior session in verbatim"
+  trigger_context: "user wants to pull a prior session from the agents/runtime/.agent-chat-history log into the current chat verbatim and optionally resume it"
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - memory
 ---
 
 <!-- cloud_safe: noop -->
 
 # /chat-history
 
-Top-level orchestrator for the `/chat-history` family. After the
-hook-only reduction (`road-to-chat-history-hook-only`) writes and
-overflow handling are driven entirely by platform hooks +
-`scripts/chat_history.py` internals; the surfaced sub-commands are
-read-only on the log itself. Sessions coexist in one log file —
-each entry self-tags via the `s` field — so there is no ownership
-layer to recover from.
+Top-level orchestrator for the `/chat-history` family. Writes and overflow
+handling are driven entirely by platform hooks + `scripts/chat_history.py`
+internals (`road-to-chat-history-hook-only`); the surfaced sub-command is
+read-only on the cross-host log (`agents/runtime/.agent-chat-history`).
+Sessions coexist in one log file — each entry self-tags via the `s` field —
+so there is no ownership layer to recover from.
 
 ## Sub-commands
 
 | Sub-command | Routes to | Purpose |
 |---|---|---|
-| `/chat-history show` | `commands/chat-history/show.md` | Inspect the log — size, entries, header, last entries |
-| `/chat-history import` | `commands/chat-history/import.md` | List prior sessions, pick one, render its entries verbatim — selective cross-session import |
-| `/chat-history learn` | `commands/chat-history/learn.md` | List prior sessions, pick one, mine it for project-improving learnings via `learning-to-rule-or-skill` |
+| `/chat-history import` | `commands/chat-history/import.md` | List prior sessions, pick one, render its entries verbatim — selective cross-session import + resume |
+
+**Consolidated elsewhere** (see `road-to-memory-pipeline-consolidation.md`):
+
+- **Mining a session for learnings** — use
+  [`/memory mine-session --mode=proposals`](../memory/mine-session/command.md)
+  (the former `/chat-history learn`; now the single mining command, reading the
+  same cross-host log).
+- **Inspecting the raw log** (size, entries, header) — use the host's native
+  transcript / session view; the bespoke `/chat-history show` was dropped as
+  redundant.
 
 ## Dispatch
 
 1. Parse the user's argument: `/chat-history <sub-command> [args]`.
-2. Look up the sub-command in the table above.
-3. Load the body of the routed file and follow its `## Steps`
-   section verbatim with the remaining args.
-4. If the sub-command is unknown or missing (including the bare
-   `/chat-history` invocation), route to `show` — the safe,
-   current-session inspector default. `import` and `learn` are
-   opt-in only.
+2. The only sub-command is `import`. Bare `/chat-history` (or an unknown
+   sub-command) → route to `import`.
+3. Load `commands/chat-history/import.md` and follow its `## Steps` verbatim
+   with the remaining args.
 
 ## Rules
 
-- **Do NOT commit, push, or open a PR** — `show` and `import` are
-  read-only; `learn` writes proposal drafts under
-  `agents/proposals/` only and does not commit them.
-- **Do NOT chain sub-commands.** One `/chat-history <sub>` per turn.
-- **`import` and `learn` cross the session boundary** — only run
-  them when the user explicitly asked for cross-session reading.
-  The default read path (filtered to current session) stays in
-  effect for every other tool.
+- **Do NOT commit, push, or open a PR** — `import` is read-only (it renders a
+  prior session into the current chat; it writes nothing).
+- **Do NOT chain sub-commands.** One `/chat-history import` per turn.
+- **`import` crosses the session boundary** — only run it when the user
+  explicitly asked for cross-session reading.

package/dist/agent-src/commands/check-current-md.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: check-current-md
 pack: meta
 tier: 2
+visibility: internal
 description: "Check the open .md file (or a passed path) for German outside DE:/EN: anchor blocks — umlauts, function words, untranslated quotes. Reports and offers fixes."
 suggestion:
   eligible: false

package/dist/agent-src/commands/commit/in-chunks.md

@@ -4,6 +4,7 @@ name: git-commit-in-chunks
 pack: git
 replaces: [commit-in-chunks, commit:in-chunks]
 tier: 2
+visibility: internal
 cluster: git-commit
 sub: in-chunks
 skills: [git-workflow]

package/dist/agent-src/commands/commit.md

@@ -7,6 +7,7 @@ intent: "Stage and commit changes in logical chunks with a Conventional Commits
 routes_to: [git-workflow, conventional-commits-writing]
 replaces: [commit]
 tier: 0
+visibility: visible
 cluster: git-commit
 skills: [git-workflow]
 description: Stage and commit all uncommitted changes — splits into logical commits following Conventional Commits

package/dist/agent-src/commands/condense.md

@@ -6,6 +6,7 @@ intent: "Condense src/ sources into the shipped dist/agent-src trees"
 routes_to: [skill-management]
 replaces: []
 tier: 1
+visibility: advanced
 skills: []
 description: Condense .md files from src/ into telegraph format and write to dist/agent-src/
 suggestion:

package/dist/agent-src/commands/context/create.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: context-create
 pack: meta
 tier: 2
+visibility: internal
 cluster: context
 sub: create
 skills: [agent-docs-writing]

package/dist/agent-src/commands/context/refactor.md

@@ -3,6 +3,7 @@ model_tier: high
 name: context-refactor
 pack: meta
 tier: 2
+visibility: internal
 cluster: context
 sub: refactor
 skills: [agent-docs-writing]

package/dist/agent-src/commands/context.md

@@ -4,6 +4,7 @@ name: context
 disable-model-invocation: true
 pack: meta
 tier: 2
+visibility: internal
 description: Context orchestrator — routes to create, refactor
 cluster: context
 type: orchestrator

package/dist/agent-src/commands/cost-report.md

@@ -1,8 +1,9 @@
 ---
 model_tier: medium
 name: cost-report
-pack: meta
+pack: analytics
 tier: 2
+visibility: internal
 description: Capture token cost from the active Claude Code session, append to the local sessions store, and surface the 50/75/90/100% budget alert ladder with cost-profile suggestions.
 skills: [file-editor]
 suggestion:
@@ -12,7 +13,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - analytics
 ---
 
 <!-- cloud_safe: noop -->
@@ -125,7 +126,7 @@ Allowed values: `today`, `week`, `month`, `all` (default).
 ## Attribution
 
 Forked from
-[`ruvnet/ruflo`](https://github.com/ruvnet/ruflo)
-`plugins/ruflo-cost-tracker/scripts/{track,budget}.mjs`. The MCP
+an external reference
+`plugins/external-cost-tracker/scripts/{track,budget}.mjs`. The MCP
 `memory_store` dependency was replaced with a local JSONL append; the
 50/75/90/100% alert ladder and pricing tiers are preserved verbatim.

package/dist/agent-src/commands/council/analysis.md

@@ -1,8 +1,9 @@
 ---
 model_tier: high
 name: council-analysis
-pack: meta
+pack: product-reasoning
 tier: 2
+visibility: internal
 cluster: council
 sub: analysis
 skills: [ai-council]
@@ -14,7 +15,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - product-reasoning
 ---
 
 # /council analysis

package/dist/agent-src/commands/council/debate.md

@@ -1,8 +1,9 @@
 ---
 model_tier: inherit
 name: council-debate
-pack: meta
+pack: product-reasoning
 tier: 2
+visibility: internal
 cluster: council
 sub: debate
 skills: [ai-council]
@@ -14,7 +15,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - product-reasoning
 ---
 
 # /council debate
@@ -51,7 +52,7 @@ the agent's framing.
 ### 2. Decide round count + auto-continue
 
 Default: 2 rounds (initial position + one rebuttal). Cap: the value of
-`defaults.debate_max_rounds` in [`agents/settings/.ai-council.yml`](../../../agents/settings/.ai-council.yml)
+`defaults.debate_max_rounds` in `~/.event4u/agent-config/settings/.ai-council.yml`
 (default 4). `--rounds N` overrides the default; values above the cap
 are rejected by the CLI.
 
@@ -129,6 +130,6 @@ session directory is the canonical audit trail.
 
 If `DebateCapExceeded` fires, the CLI exits with code 3 and the partial
 debate is persisted. Surface the partial-debate path to the user and
-ask whether to (a) raise the cap in `agents/settings/.ai-council.yml` and rerun,
+ask whether to (a) raise the cap in `~/.event4u/agent-config/settings/.ai-council.yml` and rerun,
 (b) stop here and render the partial result, or (c) start a new debate
 with a smaller scope.

package/dist/agent-src/commands/council/default.md

@@ -1,8 +1,9 @@
 ---
 model_tier: inherit
 name: council-default
-pack: meta
+pack: product-reasoning
 tier: 2
+visibility: internal
 cluster: council
 sub: default
 skills: [ai-council]
@@ -13,7 +14,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - product-reasoning
 ---
 
 # /council default

package/dist/agent-src/commands/council/design.md

@@ -1,8 +1,9 @@
 ---
 model_tier: inherit
 name: council-design
-pack: meta
+pack: product-reasoning
 tier: 2
+visibility: internal
 cluster: council
 sub: design
 skills: [ai-council]
@@ -14,7 +15,7 @@ suggestion:
 workspaces:
   - agent-config-maintainer
 packs:
-  - meta
+  - product-reasoning
 ---
 
 # /council design