@event4u/agent-config 5.6.1 → 5.8.0

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agent-handoff
 tier: 0
 skills: [agent-docs-writing]

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agent-status
 tier: 0
 skills: [agent-docs-writing]

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agents:audit
 tier: 2
 cluster: agents

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agents:init
 tier: 2
 cluster: agents

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agents:user-accept
 tier: 2
 cluster: agents
@@ -17,7 +17,7 @@ packs:
 # /agents user accept
 
 Apply a buffered observation from
-[`.agent-user.observations.jsonl`](../../../../../docs/contracts/agent-user-schema.md#observation-buffer)
+[`.agent-user.observations.jsonl`](../../../../../../docs/contracts/agent-user-schema.md#observation-buffer)
 to `.agent-user.md` after explicit confirmation.
 
 Use when:
@@ -116,6 +116,6 @@ Do NOT commit. Do NOT auto-chain to a second field.
 
 ## See also
 
-- Schema + buffer contract: [`agent-user-schema § Observation buffer`](../../../../../docs/contracts/agent-user-schema.md#observation-buffer).
+- Schema + buffer contract: [`agent-user-schema § Observation buffer`](../../../../../../docs/contracts/agent-user-schema.md#observation-buffer).
 - Parent: [`/agents user`](../user.md).
 - Sibling: [`/agents user review`](review.md), [`/agents user update`](update.md).

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agents:user-init
 tier: 2
 cluster: agents
@@ -18,7 +18,7 @@ packs:
 
 Short interactive interview that creates **`.agent-user.md`** at the
 project root from the locked v1 schema in
-[`docs/contracts/agent-user-schema.md`](../../../../../../../../docs/contracts/agent-user-schema.md).
+[`docs/contracts/agent-user-schema.md`](../../../../../../../../../docs/contracts/agent-user-schema.md).
 
 Use when:
 
@@ -95,7 +95,7 @@ Before writing, scan the collected `voice_sample` and `role` for:
 - Health/legal status keywords.
 
 Hit → surface the line and ask the user to redact before proceeding.
-Per [`agent-user-schema § Explicit exclusions`](../../../../../../../../docs/contracts/agent-user-schema.md#explicit-exclusions).
+Per [`agent-user-schema § Explicit exclusions`](../../../../../../../../../docs/contracts/agent-user-schema.md#explicit-exclusions).
 
 ### 5. Render and write
 
@@ -157,5 +157,5 @@ Do NOT commit. Do NOT run any other `/agents user` sub-sub-command.
 
 ## See also
 
-- Schema: [`agent-user-schema`](../../../../../../../../docs/contracts/agent-user-schema.md).
+- Schema: [`agent-user-schema`](../../../../../../../../../docs/contracts/agent-user-schema.md).
 - Parent: [`/agents user`](../user.md).

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agents:user-show
 tier: 2
 cluster: agents
@@ -18,7 +18,7 @@ packs:
 # /agents user show
 
 Read-only render of the project-root `.agent-user.md` per
-[`docs/contracts/agent-user-schema.md`](../../../../../../../docs/contracts/agent-user-schema.md).
+[`docs/contracts/agent-user-schema.md`](../../../../../../../../docs/contracts/agent-user-schema.md).
 
 Use when:
 
@@ -108,6 +108,6 @@ Do NOT chain to other `/agents user *` commands. Do NOT commit.
 
 ## See also
 
-- Schema: [`agent-user-schema`](../../../../../../../docs/contracts/agent-user-schema.md).
+- Schema: [`agent-user-schema`](../../../../../../../../docs/contracts/agent-user-schema.md).
 - Parent: [`/agents user`](../user.md).
 - Sibling: [`/agents user init`](init.md), [`/agents user update`](update.md).

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agents:user-update
 tier: 2
 cluster: agents
@@ -59,7 +59,7 @@ When called with `--validate` (or after the user confirms "done"):
 
 1. Read `.agent-user.md`.
 2. Parse frontmatter; check every required field per
-   [`agent-user-schema § Field reference`](../../../../../docs/contracts/agent-user-schema.md#field-reference).
+   [`agent-user-schema § Field reference`](../../../../../../docs/contracts/agent-user-schema.md#field-reference).
 3. Check file size ≤100 lines.
 4. Run the privacy-floor scan (same as `init` step 4): credentials,
    third-party PII, financial figures, health/legal status.
@@ -97,6 +97,6 @@ Do NOT commit. Do NOT chain to another `/agents user *` command.
 
 ## See also
 
-- Schema: [`agent-user-schema`](../../../../../docs/contracts/agent-user-schema.md).
+- Schema: [`agent-user-schema`](../../../../../../docs/contracts/agent-user-schema.md).
 - Parent: [`/agents user`](../user.md).
 - Sibling: [`/agents user init`](init.md), [`/agents user show`](show.md), [`/agents user review`](review.md).

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agents:user
 tier: 2
 cluster: agents

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: agents
 tier: 1
 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).

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: analytics:prune
 tier: 2
 cluster: analytics

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: analytics:show
 tier: 2
 cluster: analytics

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: analytics
 tier: 2
 description: Analytics orchestrator — routes to show, prune. Local-only workspace event log under `~/.event4u/agent-config/workspace/analytics/`.

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: bug-fix
 tier: 1
 skills: [bug-analyzer, pest-testing]

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: challenge-me
 tier: 2
 description: Challenge-me orchestrator — routes to vision, with-docs

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: chat-history:import
 tier: 2
 cluster: chat-history

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: chat-history:learn
 tier: 2
 cluster: chat-history

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: chat-history:show
 tier: 2
 cluster: chat-history

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: chat-history
 tier: 2
 description: Chat-history orchestrator — routes to show, import, learn

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: check-current-md
 tier: 2
 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.

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: condense
 tier: 1
 skills: []

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: context
 tier: 2
 description: Context orchestrator — routes to create, refactor

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: cost-report
 tier: 2
 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.
@@ -56,15 +56,20 @@ profile recommendation per the table:
 |---|---|---|
 | 🟢 OK | < 50% | within budget — no action |
 | 🟡 INFO | ≥ 50% | log notification, no UX disruption |
-| 🟠 WARNING | ≥ 75% | suggest [`/set-cost-profile balanced→minimal`](set-cost-profile.md) |
-| 🔴 CRITICAL | ≥ 90% | recommend model downgrades, consider [`/set-cost-profile minimal`](set-cost-profile.md) |
+| 🟠 WARNING | ≥ 75% | suggest dropping the **model tier** — `model.auto_switch: auto`, or pick a lighter `model_tier` for routine work (the dominant spend lever) |
+| 🔴 CRITICAL | ≥ 90% | recommend a lighter model tier first; only as a last resort suggest [`/set-cost-profile minimal`](set-cost-profile.md) **with a capability-loss warning** |
 | 🛑 HARD_STOP | ≥ 100% | halt non-essential work; review before continuing (`budget.mjs check` exits 1) |
 
-If `level` ≥ WARNING and the current `cost_profile` in `.agent-settings.yml`
-is not already `minimal`, add an explicit suggestion sentence:
+**Lever order matters.** Per-turn spend is dominated by the **model** (a high→lite
+tier swap is roughly a 10× cost delta) and by query/response volume — not by how many
+rules load. `rule_loading_tier` loads its rule bodies roughly once per session (a small,
+fixed cost), so lowering it saves little and *reduces the agent's guardrail coverage*.
+Recommend the model lever first:
 
-> Run [`/set-cost-profile`](set-cost-profile.md) to switch from your
-> current profile to a leaner one.
+> Budget ≥ {level}. The biggest lever is the **model tier** — set
+> `model.auto_switch: auto` (or pick a lighter `model_tier` for routine turns).
+> Lowering `rule_loading_tier` saves far less and drops behavioural guardrails —
+> use [`/set-cost-profile minimal`](set-cost-profile.md) only as a last resort.
 
 ### 4. First-run: prompt to set a budget
 
@@ -109,7 +114,7 @@ Allowed values: `today`, `week`, `month`, `all` (default).
 
 ## See also
 
-- [`/set-cost-profile`](set-cost-profile.md) — change `cost_profile` in
+- [`/set-cost-profile`](set-cost-profile.md) — change `rule_loading_tier` in
   `.agent-settings.yml`.
 - [`/agent-status`](agent-status.md) — per-conversation token estimate
   (different scope: in-flight estimate, not historical actuals).

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: council
 tier: 1
 description: Council orchestrator — routes to default, pr, design, optimize, analysis, debate
@@ -65,7 +65,7 @@ Invariants:
 | `/council debate` | `commands/council/debate.md` | Multi-round debate with progressive cost disclosure — initial positions + rebuttals across N rounds |
 
 Sub-command names match the locked contract in
-[`docs/contracts/command-clusters.md`](../../docs/contracts/command-clusters.md).
+[`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md).
 
 ## Advisor mode (replace-mode personas)
 
@@ -76,7 +76,7 @@ swaps its bound member's plain call for the same provider running the
 advisor persona — **same call count, same budget**. `council:estimate`
 surfaces every active swap on a dedicated line. Full contract: skills
 `ai-council` § "Thinking-style advisors" and
-[`docs/contracts/ai-council-config.md`](../../docs/contracts/ai-council-config.md).
+[`docs/contracts/ai-council-config.md`](../docs/contracts/ai-council-config.md).
 
 ## Dispatch
 

package/.agent-src/commands/create-pr/description-only.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: create-pr:description-only
 tier: 1
 cluster: create-pr

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: create-pr
 tier: 1
 cluster: create-pr

package/.agent-src/commands/e2e-heal.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: e2e-heal
 tier: 2
 skills: [playwright-testing]

package/.agent-src/commands/e2e-plan.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: e2e-plan
 tier: 2
 skills: [playwright-testing]

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: feature
 tier: 1
 description: Feature orchestrator — routes to explore, plan, refactor, roadmap, dev

package/.agent-src/commands/fix/ci.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: fix:ci
 tier: 2
 cluster: fix

package/.agent-src/commands/fix/portability.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: fix:portability
 tier: 2
 cluster: fix

package/.agent-src/commands/fix/pr-bot-comments.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: fix:pr-bot-comments
 tier: 2
 cluster: fix

package/.agent-src/commands/fix/pr-comments.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: fix:pr-comments
 tier: 2
 cluster: fix

package/.agent-src/commands/fix/pr-developer-comments.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: fix:pr-developer-comments
 tier: 2
 cluster: fix

package/.agent-src/commands/fix/refs.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: fix:refs
 tier: 2
 cluster: fix

package/.agent-src/commands/fix/seeder.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: fix:seeder
 tier: 2
 cluster: fix

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: fix
 tier: 1
 description: Fix orchestrator — routes to ci, references, portability, seeder, pr-comments, pr-bot-comments, pr-developer-comments

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: judge
 tier: 1
 description: Judge orchestrator — routes to solo, steps, on-diff

package/.agent-src/commands/knowledge/cross-repo.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: knowledge:cross-repo
 tier: 2
 cluster: knowledge

package/.agent-src/commands/knowledge/forget.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: knowledge:forget
 tier: 2
 cluster: knowledge

package/.agent-src/commands/knowledge/ingest.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: knowledge:ingest
 tier: 2
 cluster: knowledge

package/.agent-src/commands/knowledge/list.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: knowledge:list
 tier: 2
 cluster: knowledge

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: knowledge
 tier: 2
 description: Knowledge orchestrator — routes to ingest, list, forget. Local-only file ingestion into the agent memory namespace.

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: memory:add
 tier: 2
 cluster: memory

package/.agent-src/commands/memory/learn-low-impact.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: memory:learn-low-impact
 tier: 2
 cluster: memory

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: memory:load
 tier: 2
 cluster: memory

package/.agent-src/commands/memory/mine-session.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: memory:mine-session
 tier: 2
 cluster: memory

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: memory:promote
 tier: 2
 cluster: memory

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: memory:propose
 tier: 2
 cluster: memory

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: memory
 tier: 1
 description: Memory orchestrator — routes to add, load, mine-session, promote, propose

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: mode
 tier: 1
 description: Set the active role mode — prints the contract, lists default skills, and refuses work outside the contract (see role-contracts)

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: optimize:agents-dir
 tier: 2
 cluster: optimize

package/.agent-src/commands/optimize/augmentignore.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 skills: [agent-docs-writing]
 name: optimize:augmentignore
 tier: 2

package/.agent-src/commands/optimize/rtk.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: optimize:rtk
 tier: 2
 cluster: optimize

package/.agent-src/commands/optimize/skills.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: optimize:skills
 tier: 2
 cluster: optimize

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: optimize
 tier: 1
 description: Optimize orchestrator — routes to skills, agents-dir, augmentignore, rtk-filters

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: orchestrate
 tier: 2
 cluster: orchestrate

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: override:create
 tier: 2
 cluster: override

package/.agent-src/commands/override/manage.md

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: override:manage
 tier: 2
 cluster: override

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: override
 tier: 2
 description: Override orchestrator — routes to create, manage

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

@@ -1,5 +1,5 @@
 ---
-model_tier: inherit
+model_tier: medium
 name: package-reset
 tier: 2
 skills: [composer, npm]