@event4u/agent-config 6.0.0 → 6.1.0

package/dist/agent-src/commands/roadmap/process-full.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: roadmap-process-full
 pack: product-basic
 tier: 2
+visibility: internal
 cluster: roadmap
 sub: process-full
 skills: [agent-docs-writing, ai-council, roadmap-management]

package/dist/agent-src/commands/roadmap/process-phase.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: roadmap-process-phase
 pack: product-basic
 tier: 2
+visibility: internal
 cluster: roadmap
 sub: process-phase
 skills: [agent-docs-writing, ai-council, roadmap-management]

package/dist/agent-src/commands/roadmap/process-step.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: roadmap-process-step
 pack: product-basic
 tier: 2
+visibility: internal
 cluster: roadmap
 sub: process-step
 skills: [agent-docs-writing, ai-council, roadmap-management]

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

@@ -7,6 +7,7 @@ intent: "Roadmap dispatcher — create, process-step, process-phase, process-ful
 routes_to: [roadmap-create, roadmap-process-step, roadmap-process-phase, roadmap-process-full]
 replaces: []
 tier: 1
+visibility: advanced
 description: Roadmap orchestrator — routes to create (authoring) and process-step / process-phase / process-full (autonomous execution).
 cluster: roadmap
 type: orchestrator

package/dist/agent-src/commands/rule-compliance-audit.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: rule-compliance-audit
 pack: meta
 tier: 2
+visibility: internal
 skills: [rule-compliance-audit]
 description: Audit rule trigger quality, simulate activation, detect overlaps, and find never-activating rules
 suggestion:

package/dist/agent-src/commands/security-audit-config.md

@@ -0,0 +1,84 @@
+---
+model_tier: high
+name: security-audit-config
+pack: engineering-base
+tier: 2
+visibility: internal
+skills: [judge-security-auditor, threat-modeling, security-audit]
+description: Audit an assembled agent config (CLAUDE.md, .cursor/rules, settings, MCP, hooks, skills) for prompt-injection / supply-chain risk — A–F score per category, mapped to OWASP Agentic Top 10
+council_depth: deep
+suggestion:
+  eligible: true
+  trigger_description: "audit my agent config, is my CLAUDE.md / MCP setup safe, scan for prompt injection in my rules"
+  trigger_context: "a repo with agent config files (CLAUDE.md, .cursor/rules, .mcp.json, .claude/settings.json)"
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+---
+
+# security-audit-config
+
+## Instructions
+
+Audit a consumer's **assembled** agent config for the prompt-injection +
+supply-chain risks behind the "rules-file backdoor" and MCP tool-poisoning
+classes; report an A–F score per category mapped to the OWASP Top 10 for
+Agentic Applications. Consumer-facing counterpart to the suite's own
+`lint_agent_security` self-audit gate.
+
+### 1. Run the static audit
+
+```bash
+python3 src/scripts/security_audit_config.py --root <repo> --json
+```
+
+(omit `--root` to audit the current repo). Reuses the Phase-1 detection library
+under the containment convention
+([`security-lint-containment`](../docs/guidelines/agent-infra/security-lint-containment.md)),
+so doc/example files don't tank the score. Scans instruction files (`CLAUDE.md`,
+`AGENTS.md`, `.cursor/rules`, `.github/copilot-instructions.md`, `.clinerules`,
+`.windsurfrules`), MCP configs (`.mcp.json`, `.cursor/mcp.json`,
+`claude_desktop_config.json`), settings/hooks (`.claude/settings.json`),
+installed skills.
+
+### 2. Present the score
+
+Surface the overall grade + five category grades (Secrets · Permissions · Hooks
+· MCP · Agents/Rules), each with its OWASP-ASI tag, then the findings worth
+acting on (HIGH first). Lead with the worst category.
+
+### 3. Optional deep pass
+
+When asked for depth, or any category scores **D/F**, escalate:
+
+- Dispatch [`judge-security-auditor`](../skills/judge-security-auditor/SKILL.md)
+  over the flagged files for a diff-level verdict.
+- For a red/blue/auditor review of the whole config, hand off to the
+  `agent-security-review` skill (`council_depth: deep`).
+
+### 4. Recommend, do not auto-fix
+
+Output is **decision support**, not a gate — detection is probabilistic.
+Recommend the fix per finding (secret → `${env:VAR}`, pin an MCP server, remove
+`bypassPermissions`, strip hidden Unicode), but never rewrite the consumer's
+config without confirmation (per [`scope-control`](../../../src/rules/scope-control.md)).
+
+## Output format
+
+```
+Agent-config security audit — <repo>
+Overall: B (84/100)
+
+  C  Secrets       75/100 · ASI04 Supply Chain
+        [HIGH] .mcp.json:3: inline secret value — use ${env:VAR}
+  F  Agents/Rules  50/100 · ASI01 Goal Hijack
+        [HIGH] CLAUDE.md:1: role-takeover phrase in prose
+  ...
+```
+
+## See also
+
+- [`lint_agent_security`](../../../src/scripts/lint_agent_security.py) — the self-audit (our own corpus) sibling.
+- [`untrusted-input-defense`](../../rules/untrusted-input-defense.md), [`lethal-trifecta-guard`](../../rules/lethal-trifecta-guard.md) — the always-on prevention rules.
+- [`/threat-model`](../threat-model/command.md), [`judge-security-auditor`](../skills/judge-security-auditor/SKILL.md) — deep-pass dispatch.

package/dist/agent-src/commands/set-cost-profile.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: set-cost-profile
 pack: meta
 tier: 2
+visibility: internal
 description: Change the rule_loading_tier in .agent-settings.yml — shows each profile's meaning and applies the selection
 skills: [file-editor]
 suggestion:

package/dist/agent-src/commands/skill/preview.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: skill-preview
 pack: meta
 tier: 2
+visibility: internal
 cluster: skill
 sub: preview
 description: Non-destructive preview of a skill — its declared steps, execution type, allowed tools, and file/command targets — before you run it. Read-only, no execution.

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: skill
 pack: meta
 tier: 2
+visibility: internal
 description: Single-skill orchestrator — routes to preview. Non-destructive "what will this skill do?" before you run it.
 cluster: skill
 type: orchestrator

package/dist/agent-src/commands/skills/discover.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: skills-discover
 pack: meta
 tier: 2
+visibility: internal
 cluster: skills
 sub: discover
 description: Recommend skills for a role — ranked by four explained classes (most-useful-for-role, related-to-current-task, recently-adopted, popular-in-role). Local-only; every result carries a why.

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: skills
 pack: meta
 tier: 2
+visibility: internal
 description: Skill discovery orchestrator — routes to discover. Local, explained skill recommendations over the catalog + role shortlists + optional local analytics.
 cluster: skills
 type: orchestrator

package/dist/agent-src/commands/sync-agent-settings.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: sync-agent-settings
 pack: meta
 tier: 2
+visibility: internal
 skills: [sync-agent-settings]
 description: Sync `.agent-settings.yml` against the current template + profile — adds new sections/keys, preserves user values, shows a diff before writing
 suggestion:

package/dist/agent-src/commands/sync-gitignore/fix.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: sync-gitignore-fix
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: sync-gitignore
 sub: fix
 skills: [sync-gitignore]

package/dist/agent-src/commands/sync-gitignore.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: sync-gitignore
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: sync-gitignore
 skills: [sync-gitignore]
 description: Sync the `event4u/agent-config` block in the consumer project's .gitignore — adds missing entries, preserves user-added lines, shows a diff before writing

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

@@ -3,6 +3,7 @@ model_tier: medium
 name: tests-create
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: tests
 sub: create
 skills: [pest-testing, quality-tools]

package/dist/agent-src/commands/tests/execute.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: tests-execute
 pack: engineering-base
 tier: 2
+visibility: internal
 cluster: tests
 sub: execute
 skills: [pest-testing, quality-tools]

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

@@ -4,6 +4,7 @@ name: tests
 disable-model-invocation: true
 pack: engineering-base
 tier: 2
+visibility: internal
 description: Tests orchestrator — routes to create, execute
 cluster: tests
 type: orchestrator

package/dist/agent-src/commands/threat-model.md

@@ -3,6 +3,7 @@ model_tier: high
 name: threat-model
 pack: engineering-base
 tier: 2
+visibility: internal
 skills: [threat-modeling, authz-review, security-sensitive-stop]
 description: Run a pre-implementation threat model on a proposed change — enumerates abuse cases, trust boundaries, and authorization gaps before the first line of code is written
 council_depth: deep

package/dist/agent-src/commands/update-form-request-messages.md

@@ -3,6 +3,7 @@ model_tier: medium
 name: update-form-request-messages
 pack: engineering-base
 tier: 2
+visibility: internal
 framework: laravel
 skills: [laravel-validation]
 description: "Sync the messages() method of a FormRequest class — add missing entries, link them to language keys, and clean up stale ones."

package/dist/agent-src/commands/upstream-contribute.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: upstream-contribute
 pack: meta
 tier: 2
+visibility: internal
 skills: [upstream-contribute, skill-writing, learning-to-rule-or-skill]
 description: Contribute a learning, skill, rule, or fix from a consumer project back to the shared agent-config package
 suggestion:

package/dist/agent-src/commands/video/from-script.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-from-script
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: from-script
 description: Drive a script end-to-end through the AI video pipeline — scenes → blueprint → image → operator pick → motion → video → stitch. Preview default; --mode commit spends behind the cost gate.

package/dist/agent-src/commands/video/from-song.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-from-song
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: from-song
 description: Music-video from a song + reference images — accept or derive a timed scene script, optional character-lock, render, stitch, mux song as master track. Preview default; --mode commit gates the spend.

package/dist/agent-src/commands/video/scene.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-scene
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: scene
 description: Render a single scene from a one-line idea — scene-expander → blueprint → image → operator pick → motion → video. Preview mode default (no spend); --mode commit renders live behind the cost gate.

package/dist/agent-src/commands/video/stitch.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-stitch
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: stitch
 description: Re-stitch existing clips in `<project>/scenes/*/` after operator edits — no re-render. ffmpeg concat driven by manifest.json.

package/dist/agent-src/commands/video/storyboard.md

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video-storyboard
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 sub: storyboard
 description: Image-only storyboard — script → scenes → blueprint → image render → contact-sheet PNG via ffmpeg montage. No video calls.

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

@@ -3,6 +3,7 @@ model_tier: inherit
 name: video
 pack: ai-video
 tier: 2
+visibility: internal
 cluster: video
 description: Video-creation orchestrator — Hollywood-level AI video pipeline. Routes to from-script, from-song, scene, storyboard, stitch.
 type: orchestrator

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

@@ -6,6 +6,7 @@ intent: "Pick up the next sensible task and execute it autonomously"
 routes_to: [refine-prompt, command-routing]
 replaces: []
 tier: 0
+visibility: visible
 skills: [refine-prompt, command-routing]
 description: Drive a free-form prompt end-to-end through refine → score → plan → implement → test → verify → report — Option-A loop over the `work_engine` Python engine, confidence-band gated, no auto-git.
 suggestion:

package/dist/agent-src/contexts/augment-infrastructure.md

@@ -105,7 +105,7 @@ Commands organized by workflow:
 | **Modules** | `module-create`, `module-explore` |
 | **Roadmaps** | `roadmap:create`, `roadmap:process-step`, `roadmap:process-phase`, `roadmap:process-full` |
 | **Quality** | `quality-fix`, `review-changes`, `prepare-for-review`, `update-form-request-messages`, `fix-seeder` |
-| **CI/PR** | `fix-ci`, `create-pr`, `create-pr-description`, `fix-pr-comments`, `fix-pr-bot-comments`, `fix-pr-developer-comments` |
+| **CI/PR** | `fix-ci`, `create-pr`, `create-pr-description`, `fix-pr-comments` |
 | **Testing** | `tests-create`, `tests-execute` |
 | **E2E** | `e2e-plan`, `e2e-heal` |
 | **Agents** | `agents-prepare`, `agents-audit`, `agents-cleanup`, `copilot-agents-optimize`, `agent-handoff`, `agent-status`, `optimize-agents`, `optimize-augmentignore`, `optimize-skills`, `optimize-rtk-filters` |

package/dist/agent-src/contexts/communication/rules-auto/skill-quality-mechanics.md

@@ -25,7 +25,7 @@ Make descriptions "pushy" — explicit about when to fire:
   adjectives, drop the second example phrasing, or collapse a list — do
   **not** drop the trigger vocabulary or the `even if ...` tail.
 
-Source: [`skills/skill-creator` in `anthropics/skills`](https://github.com/anthropics/skills/blob/main/skills/skill-creator/SKILL.md).
+Source: [`skills/skill-creator` in `an external reference`](https://github.com/an external reference/blob/main/skills/skill-creator/SKILL.md).
 
 **Litmus test:** Read the description cold, without the skill's body. If you
 cannot name at least two phrasings a user would realistically type that should

package/dist/agent-src/contexts/communication/rules-auto/slash-command-routing-policy-mechanics.md

@@ -4,7 +4,7 @@ Lookup table for the `slash-command-routing-policy` rule. Lists the
 locked clusters and their sub-commands so the rule itself can stay at
 its current LOC while still reflecting the full surface. Source of
 truth for the cluster names is
-[`docs/contracts/command-clusters.md`](../../../../../docs/contracts/command-clusters.md);
+[`docs/contracts/command-clusters.md`](../../../../../../docs/contracts/command-clusters.md);
 this file mirrors that contract for runtime lookup. Linter:
 `scripts/check_cluster_patterns.py` (verifies dispatcher shape).
 
@@ -12,7 +12,7 @@ this file mirrors that contract for runtime lookup. Linter:
 
 | Cluster | Phase | Sub-commands | Replaces                                                                                                                                        |
 |---|:-:|---|-------------------------------------------------------------------------------------------------------------------------------------------------|
-| `/fix` | 1 | `ci` · `pr-comments` · `pr-bot-comments` · `pr-developer-comments` · `portability` · `refs` · `seeder` | `/fix-ci` · `/fix-pr-comments` · `/fix-pr-bot-comments` · `/fix-pr-developer-comments` · `/fix-portability` · `/fix-references` · `/fix-seeder` |
+| `/fix` | 1 | `ci` · `pr-comments` · `portability` · `refs` · `seeder` | `/fix-ci` · `/fix-pr-comments` · `/fix-portability` · `/fix-references` · `/fix-seeder` |
 | `/optimize` | 1 | `agents` · `augmentignore` · `rtk` · `skills` | `/optimize-agents` · `/optimize-augmentignore` · `/optimize-rtk-filters` · `/optimize-skills`                                                   |
 | `/feature` | 1 | `explore` · `plan` · `refactor` · `roadmap` | `/feature-explore` · `/feature-plan` · `/feature-refactor` · `/feature-roadmap`                                                                 |
 | `/chat-history` | 2 | `show` | `/chat-history` (legacy status) — `resume` / `clear` / `checkpoint` removed in `road-to-chat-history-hook-only`                                 |

package/dist/agent-src/contexts/communication/rules-auto/think-before-action-mechanics.md

@@ -42,12 +42,12 @@ behavior. Cannot → read more.
 
 ## Consult memory before editing
 
-Prior decisions and invariants live in the memory layer. Via
-[`memory-access`](../../../../../docs/guidelines/agent-infra/memory-access.md),
-call `retrieve(types=["architecture-decisions", "domain-invariants"], keys=<touched paths>, limit=3)`.
-A matching `architecture-decision` explains *why* the current shape
-exists; a matching `domain-invariant` is a hard constraint. Cite the
-`id` if a match influences the plan.
+Invariants live in the memory layer; architectural rationale lives in ADRs.
+Via [`memory-access`](../../../../../docs/guidelines/agent-infra/memory-access.md),
+call `retrieve(types=["domain-invariants"], keys=<touched paths>, limit=3)` —
+a matching `domain-invariant` is a hard constraint. For *why* the current
+shape exists, check the ADR index `docs/decisions/INDEX.md`. Cite the `id` /
+ADR number if a match influences the plan.
 
 ## Verify with real tools
 

package/dist/agent-src/contexts/contracts/consumer-agents-md-guide.md

@@ -38,10 +38,10 @@ covers). Default: leave AGENTS.md thin and put detail under `agents/`.
 ```markdown
 ## Development Setup
 
-​```bash
+```bash
 {{dev_start_command}}    # make start / docker compose up / npm run dev / php artisan serve
 {{dev_test_command}}     # make test / docker compose exec app bash / npm test / php artisan test
-​```
+```
 
 ### Environment files
 

package/dist/agent-src/contexts/execution/rdp-gate.md

@@ -0,0 +1,75 @@
+# RDP Gate — Table-Free Cost Gate
+
+Shared mechanic for the **Reasoning Discipline Protocol**. Loaded by the RDP
+artifacts (the `notes-first-reasoning` rule, the `reasoning-orchestrator` skill,
+and the Phase-5 extensions of `think-before-action` / `improve-before-implement` /
+`adversarial-review` / `subagent-orchestration` / `autonomous-execution`) when
+deciding **whether to engage the discipline at all**. Design rationale +
+sourcing: `docs/guidelines/agent-infra/frontier-reasoning-operating-profile.md`
+and roadmap decisions L1/L10/L17.
+
+## The one rule
+
+```
+RDP NEVER ENGAGES BY DEFAULT ON EVERY TURN.
+IT ENGAGES ONLY WHERE IT PAYS — DECIDED BY TABLE-FREE SIGNALS.
+NO RUNTIME MODEL -> BAND TABLE EXISTS (ADR-035).
+```
+
+`model_tier` (ADR-035, `lite|medium|high`) is the **skill's** needed model band,
+**not** the host's reasoning strength. RDP must never reuse it for gating, never
+maintain a model list, and never ship heavy/light content variants (two variants
+*are* a hidden band table).
+
+## Three signals (all table-free)
+
+1. **User settings** — read the `reasoning:` block in `.agent-settings.yml`:
+   - `enabled: false` → the whole layer is inert. Stop here.
+   - per-component switch off (e.g. `components.verifier_default: false`) → that
+     component never fires.
+   - `auto_gate: false` → skip signal 3 (self-assessment); gate on signal 2 only.
+2. **Task signal** (knowable per turn, no model lookup):
+   - **Skip** RDP when the task is trivial / short / fully-specified (rename,
+     typo, format, one-line edit, list files, bump a version).
+   - **Engage** when the task is complex / ambiguous / multi-component /
+     long-horizon / stateful / irreversible.
+3. **Host reasoning strength** (agent self-assessment — introspection, no
+   maintained list; same pattern as `provider-lifecycle-discipline` and
+   `media-governance-routing`):
+   - A **strong-reasoning** host applies the discipline **lightly / as a
+     suggestion** (it self-coordinates; heavy scaffolding wastes tokens and can
+     degrade it — see the dossier's `reasoning_extraction` + over-prescription
+     evidence).
+   - A **standard** host applies it **fully**.
+
+## One constraint-light scaffold + expand on request (L1)
+
+Every RDP artifact ships **one** constraint-light version. There is no heavy
+variant. A standard host that needs more **asks for it at turn time** ("give me
+the explicit alternative-enumeration" / "spell out the file-size bounds") rather
+than selecting a pre-written heavy file. This keeps the surface DRY, table-free,
+and vendor-neutral.
+
+## Verifier has its own gate (L12)
+
+The fresh-context verifier subagent is the most expensive primitive (a full extra
+inference pass). On top of the three signals above it fires **only** when the task
+shows **≥ 2 of**: branching/conditional logic · ≥ 3 explicit must/must-not
+constraints · stateful operations · irreversibility flag — **and** the estimated
+work is **≥ ~1k tokens**. Token length alone is never the trigger.
+
+## What this gate does NOT touch
+
+- **No frontmatter field.** The gate is read at runtime; RDP artifacts need no
+  new schema key, so there is **no projection/condensation change** and nothing
+  new compiles into `dist/router.json`.
+- **No kernel change.** RDP artifacts are tier-2 (router-loaded on match); the
+  always-on kernel stays the same size.
+- **No model list.** If a new model ships tomorrow, nothing here goes stale.
+
+## How an RDP artifact cites this
+
+Open with a one-line gate check, e.g.: *"Engage per `contexts/execution/rdp-gate.md`
+(settings + task-signal + host self-assessment); skip on trivial tasks and apply
+lightly on a strong-reasoning host."* Then the artifact's own body assumes it has
+already been cleared to engage.

package/dist/agent-src/contexts/subagent-configuration.md

@@ -59,4 +59,5 @@ The commands read `.agent-settings.yml` fresh on each run.
 
 - [`subagent-orchestration`](../skills/subagent-orchestration/SKILL.md) — the skill
 - [`model-recommendations`](model-recommendations.md) — tier definitions
+- `guideline:agent-infra/model-recommendation` § Orchestrator → subagent model routing — per-subtask model right-sizing (downgrade easy work, keep strong model for hard)
 - [`/do-and-judge`](../commands/do-and-judge.md), [`/do-in-steps`](../commands/do-in-steps.md), [`/judge`](../commands/judge.md) — commands that read these keys

package/dist/agent-src/personas/advisors/contrarian.md

@@ -90,6 +90,6 @@ straw man.
 ---
 
 *This persona is consumed by the AI Council advisor system
-(replace-mode). When activated via `agents/settings/.ai-council.yml`'s
+(replace-mode). When activated via `~/.event4u/agent-config/settings/.ai-council.yml`'s
 `advisors:` block, the entire file body below the frontmatter becomes
 the system prompt for the targeted member.*

package/dist/agent-src/personas/advisors/executor.md

@@ -94,6 +94,6 @@ can start on.
 ---
 
 *This persona is consumed by the AI Council advisor system
-(replace-mode). When activated via `agents/settings/.ai-council.yml`'s
+(replace-mode). When activated via `~/.event4u/agent-config/settings/.ai-council.yml`'s
 `advisors:` block, the entire file body below the frontmatter becomes
 the system prompt for the targeted member.*

package/dist/agent-src/personas/advisors/expansionist.md

@@ -93,6 +93,6 @@ the proposal as written can survive its own success.
 ---
 
 *This persona is consumed by the AI Council advisor system
-(replace-mode). When activated via `agents/settings/.ai-council.yml`'s
+(replace-mode). When activated via `~/.event4u/agent-config/settings/.ai-council.yml`'s
 `advisors:` block, the entire file body below the frontmatter becomes
 the system prompt for the targeted member.*

package/dist/agent-src/personas/advisors/first-principles.md

@@ -93,6 +93,6 @@ inherit an accidental complexity from convention.
 ---
 
 *This persona is consumed by the AI Council advisor system
-(replace-mode). When activated via `agents/settings/.ai-council.yml`'s
+(replace-mode). When activated via `~/.event4u/agent-config/settings/.ai-council.yml`'s
 `advisors:` block, the entire file body below the frontmatter becomes
 the system prompt for the targeted member.*

package/dist/agent-src/personas/advisors/outsider.md

@@ -97,6 +97,6 @@ synthesis stage can use to see the proposal from outside.
 ---
 
 *This persona is consumed by the AI Council advisor system
-(replace-mode). When activated via `agents/settings/.ai-council.yml`'s
+(replace-mode). When activated via `~/.event4u/agent-config/settings/.ai-council.yml`'s
 `advisors:` block, the entire file body below the frontmatter becomes
 the system prompt for the targeted member.*

package/dist/agent-src/rules/autonomous-execution.md

@@ -90,6 +90,18 @@ Crossing the 20-entry threshold counts as the 3rd validation-target failure for
 
 When validating a single target, run the **specific** check, not a meta-task that fans out to dozens of sub-tasks. Use the failing tool's direct entry point (the specific script invocation, the specific runner target, the single-test filter for the project's test runner) rather than the full CI meta-pipeline. Full-pipeline runs are appropriate at phase boundaries, not as a per-iteration probe.
 
+Concrete tool mapping — verify with the narrowest tool that proves the target green: a single `curl` / Playwright spec / browser run for HTTP behavior, the project's test runner with a `--filter` for one test, a debugger / `xdebug` step-through for one frame. Never substitute a meta-pipeline for a tool that pinpoints the failure.
+
+## Adaptive effort & stop (RDP)
+
+Scale effort to task difficulty, and stop when marginal evidence drops — coupled
+to the N=3 budget above, never replacing it. On a host with a native effort knob
+(e.g. an `effort` parameter), the right move is to **set it high** for hard tasks
+rather than scaffold; the scaffold here is for a standard host **without** such a
+knob. The per-dimension uncertainty score (see
+[`notes-first-reasoning`](notes-first-reasoning.md)) feeds this decision. Engage
+per [`rdp-gate`](../contexts/execution/rdp-gate.md).
+
 ## See also
 
 - [`user-interrupt-priority`](user-interrupt-priority.md) — STOP-ASK-RESUME on new tasks; overrides autonomy

package/dist/agent-src/rules/external-reference-deep-dive.md

@@ -58,7 +58,7 @@ Triggered when the user points to an external artifact (repo URL, `owner/repo`,
 | **Repeat-the-guess after pushback** | User says "really look" → agent re-paraphrases the same surface read. Burns trust. | On any pushback that names the source again, restart from a tree listing, not from prior notes. |
 | **Cross-tool path inference from a single example** | One config file ≠ a convention. | Inspect ≥2 unrelated tool integrations before claiming a pattern is the project's universal anchor strategy. |
 
-**Case-zero anchor.** May 2026 — `nextlevelbuilder/ui-ux-pro-max-skill` was named as the source of truth for 23 AI-tool anchors. Three rounds of "we have no content for these tools" were reported from README inference. The actual `tool-configs/*.json` files in the reference repo gave the exact directory layout per tool in one fetch. Cost: ~2 hours of user frustration. Lesson: when an external source is named, the first action is `GET /repos/{o}/{r}/contents/{interesting-subtree}` — not paraphrase.
+**Case-zero anchor.** May 2026 — an external reference suite was named as the source of truth for 23 AI-tool anchors. Three rounds of "we have no content for these tools" were reported from README inference. The actual `tool-configs/*.json` files in the reference repo gave the exact directory layout per tool in one fetch. Cost: ~2 hours of user frustration. Lesson: when an external source is named, the first action is `GET /repos/{o}/{r}/contents/{interesting-subtree}` — not paraphrase.
 
 ## Escape hatch