aiwg 2026.10.4 → 2026.10.6

package/README.md

@@ -25,10 +25,10 @@ me only for choices you cannot safely determine.
 ```
 
 The installer detects old, broken, duplicate, and development-mode installs,
-then guides you through repair or update. It deploys the preferred complete
-system with one self-verifying `aiwg use all` command. That command refreshes
-the indices, regenerates project context, verifies the resulting deployment,
-and reports whether a provider reload is actually required.
+then guides you through repair or update. Once the CLI is healthy, guided
+setup records an interview plan, lets you review it, and applies the selected
+frameworks and integrations through the existing deployment owners. The apply
+report distinguishes core readiness from optional integration failures.
 
 For long-running agents that need an isolated executor, optionally install AIWG Cockpit with a self-hosted Agentic
 Sandbox executor you control and audit:
@@ -50,15 +50,21 @@ If you prefer to install manually:
 ```bash
 npm i -g aiwg
 cd /path/to/your/project
-aiwg use all --provider <provider>
+aiwg setup --scope project --providers <provider>
+aiwg setup --review
+aiwg setup --apply
 ```
 
 Replace `<provider>` with your AI tool's name, such as `claude`, `codex`,
 `copilot`, `cursor`, `omp`, or `pi`.
 
-The final command deploys, indexes, connects, verifies, and reports one outcome.
-The standalone index, regenerate, status, and doctor commands remain available
-for advanced maintenance and troubleshooting; they are not extra install steps.
+The interview saves a plan without changing provider configuration. Review is
+read-only; apply asks for confirmation and reports the verified outcome. Optional
+Jev decision offload and direct workers require explicit opt-in. Repeating apply
+resumes unfinished actions and leaves completed actions alone. See the
+[guided setup reference](docs/getting-started/guided-setup.md) for headless flags,
+credential references, scope choices, and recovery. For a direct complete-system
+deployment, `aiwg use all --provider <provider>` remains available.
 
 For the complete beginner path and provider-name table, see
 [Install, Connect, and Verify](docs/getting-started/install-connect-verify.md).
@@ -2208,6 +2214,14 @@ cross-platform deployment for project-local and packaged capabilities:
 Contributions are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for the
 project guidelines.
 
+For release validation, the [release comparison tool](tools/rules/README.md)
+keeps assertion losses as hard regressions and tolerates judge noise with an
+exact sign test (`--judge-alpha 0.05`) and a dimension mean margin
+(`--judge-score-margin 1.0` on the 0–4 scale). At n=5, a judge-only 4/1 split
+does not regress; 5/0 does. Reports retain per-scenario A/B/tie tallies and the
+rule that determined each result. Follow the
+[release checklist](docs/contributing/release-validation-procedure.md).
+
 **Quick contributions:**
 
 - Found a bug or confusing workflow? [Open an issue](https://github.com/jmagly/aiwg/issues/new).

package/agentic/code/addons/agent-loop/README.md

@@ -1,5 +1,7 @@
 # Agent Loop
 
+Evidence status: design intent.
+
 Classify work with the [autonomy and human operating roles framework](../../../../docs/autonomy-and-human-roles.md). A loop cannot override human-owned actions, checkpoints, or failed verification.
 
 Iterative AI task execution with automatic recovery - **iteration beats perfection**.

package/agentic/code/addons/agent-loop/skills/agent-loop/SKILL.md

@@ -14,7 +14,7 @@ platforms: [all]
 >
 > ```bash
 > aiwg discover "<capability>"
-> aiwg show skill <name>
+> aiwg show skill <name> --body
 > ```
 >
 > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).

package/agentic/code/addons/agent-loop/skills/agent-loop-ext/SKILL.md

@@ -22,7 +22,7 @@ commandHint:
 >
 > ```bash
 > aiwg discover "<capability>"
-> aiwg show skill <name>
+> aiwg show skill <name> --body
 > ```
 >
 > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).

package/agentic/code/addons/agent-loop/skills/infer-completion-criteria/SKILL.md

@@ -30,7 +30,7 @@ This skill is invoked by:
 - The `agent-loop` detection-and-routing skill when it parses a user request without explicit completion criteria
 - The `ralph` executor skill during Phase 1 initialization when `--completion` is omitted
 - The `agent-loop-ext` external-loop launcher during pre-launch resolution when `--completion` is omitted
-- Direct invocation via `aiwg discover "infer completion"` → `aiwg show skill infer-completion-criteria` when a user wants to preview the inferred criterion before committing to a loop
+- Direct invocation via `aiwg discover "infer completion"` → `aiwg show skill infer-completion-criteria --body` when a user wants to preview the inferred criterion before committing to a loop
 
 This skill does **not** run when `--completion` is explicit. The user's word is authoritative.
 

package/agentic/code/addons/agent-loop/skills/ralph-config/SKILL.md

@@ -20,7 +20,7 @@ commandHint:
 >
 > ```bash
 > aiwg discover "<capability>"
-> aiwg show skill <name>
+> aiwg show skill <name> --body
 > ```
 >
 > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).

package/agentic/code/addons/agent-loop/skills/ralph-external/SKILL.md

@@ -21,7 +21,7 @@ commandHint:
 >
 > ```bash
 > aiwg discover "<capability>"
-> aiwg show skill <name>
+> aiwg show skill <name> --body
 > ```
 >
 > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).

package/agentic/code/addons/agent-loop/skills/ralph-memory/SKILL.md

@@ -20,7 +20,7 @@ commandHint:
 >
 > ```bash
 > aiwg discover "<capability>"
-> aiwg show skill <name>
+> aiwg show skill <name> --body
 > ```
 >
 > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).

package/agentic/code/addons/agent-loop/skills/ralph-resume/SKILL.md

@@ -20,7 +20,7 @@ commandHint:
 >
 > ```bash
 > aiwg discover "<capability>"
-> aiwg show skill <name>
+> aiwg show skill <name> --body
 > ```
 >
 > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).

package/agentic/code/addons/agent-persistence/docs/hitl-integration.md

@@ -475,7 +475,7 @@ async function beforeFileWrite(file, changes) {
 - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/hitl-gates.md - HITL gate configuration rules
 - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/hitl-patterns.md - HITL workflow patterns
 - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/human-gate-display.md - Gate display format
-- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/anti-laziness.md - Anti-laziness enforcement
+- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/anti-laziness.md - Anti-laziness enforcement
 
 ### Agents
 - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/agents/recovery-orchestrator.md - Recovery coordination

package/agentic/code/addons/agentic-installer/README.md

@@ -1,5 +1,7 @@
 # Agentic Installer
 
+Evidence status: design intent.
+
 An AIWG addon that defines the `setup.aiwg.io/v1` SetupManifest language for
 cross-platform deterministic and provider-orchestrated installation workflows.
 
@@ -25,6 +27,25 @@ unexpected environment states. A manifest with
 capable AI provider and may use reasoning steps as the workflow. The CLI
 validates that mode but does not execute it through `setup-run`.
 
+## AIWG installation entry point
+
+The public `https://aiwg.io/setup.aiwg.yaml` remains provider-orchestrated.
+After inspecting and repairing the CLI, follow the guided sequence:
+
+```bash
+aiwg setup --scope project --providers claude
+aiwg setup --review
+aiwg setup --apply
+```
+
+The interview writes a redacted saved plan; review writes nothing; apply uses
+existing owners and persists per-action receipts. Explicit opt-in controls Jev
+and worker dispatch. Reapply after a partial run to resume unfinished actions.
+Use [the runbook](../../../../docs/agentic-install-runbook.md) and
+[guided setup reference](../../../../docs/getting-started/guided-setup.md) for
+scope, headless flags, credentials, and readiness interpretation. `setup-run`
+is the deterministic manifest runner, not the guided installer.
+
 ## Quick Start
 
 ```yaml

package/agentic/code/addons/agentic-installer/agents/installer-agent.md

@@ -21,19 +21,33 @@ model-tier: economy
 When the target is AIWG itself and the user supplies the public
 `setup.aiwg.yaml`, treat it as the canonical
 `provider-orchestrated` install/repair contract. Follow its inspection,
-approval, preservation, deployment, and structured-result verification stages
-in the current provider session. The ordinary path ends with the self-verifying
-`aiwg use` result; standalone index, regenerate, status, and doctor commands are
-audit and recovery routes, not mandatory follow-up steps. Do not pass the
-manifest to deterministic `aiwg setup-run`.
+approval, preservation, interview, review, and apply stages in the current
+provider session. Once the CLI is healthy, record choices with
+`aiwg setup --scope project --providers <provider>`, inspect `aiwg setup --review`,
+and run `aiwg setup --apply` only after approval. The interview saves a redacted
+plan; it does not install packages or write provider configuration. Review is
+read-only. Apply delegates to the existing config, deployment, registry, Jev,
+and worker qualification owners and returns `aiwg.setup.apply.v1` with core and
+optional outcomes. Do not pass the public manifest to `aiwg setup-run`.
 
 Before mutation, classify the scenario: new or existing project; healthy,
 stale, broken, duplicate, or development-mode AIWG; project-local or approved
 user scope; one or multiple providers; native Windows, WSL, macOS, Linux, or
 container; interactive or headless; online, proxied, or offline; writable or
-read-only. Route CI/headless installs to the non-interactive guide. Stop on
-ambiguous project roots, concurrent installers, insufficient disk/permissions,
-or changes that could overwrite user work.
+read-only. Confirm monorepo root versus package explicitly. Route CLI bootstrap
+in CI/headless environments to the non-interactive guide; after bootstrap, use
+the same guided flags with `--non-interactive` and `--apply --yes`.
+
+Keep Jev and worker dispatch off unless selected. Accept credential references
+(`env:NAME`, `file:/absolute/path`, or `stdin`) rather than pasted secrets.
+Installed worker CLIs remain unqualified until apply's qualification succeeds.
+On partial failure or interruption, review and reapply the saved plan; applied
+receipts are retained, and a fully completed apply makes no writes. If inventory
+facts changed, rerun discovery/interview rather than forcing stale actions.
+Interactive `cancel` leaves the last saved plan intact. Report unresolved scope
+conflicts and optional failures without claiming full readiness. Standalone
+index, regenerate, status, and doctor commands are audit and recovery routes.
+See the [guided setup reference](../../../../../docs/getting-started/guided-setup.md).
 
 You are the **Installer Agent** — a specialist in creating and executing `setup.aiwg.io/v1` SetupManifest files for cross-platform software installation.
 

package/agentic/code/addons/agentic-installer/skills/setup-generate/SKILL.md

@@ -9,6 +9,12 @@ description: "Generate a `setup.manifest.yaml` file for a project using the `set
 
 Generate a `setup.manifest.yaml` file for a project using the `setup.aiwg.io/v1` SetupManifest language.
 
+For AIWG itself, reuse the published provider-orchestrated `setup.aiwg.yaml`
+rather than generating a replacement. It bootstraps a healthy CLI, then uses
+`aiwg setup --scope project`, `aiwg setup --review`, and `aiwg setup --apply`.
+These commands save, review, and apply an interview plan; they do not change
+SetupManifest execution mode or make `setup-run` an interactive installer.
+
 ## Trigger Phrases
 
 - "generate a setup manifest for [project]"

package/agentic/code/addons/agentic-installer/skills/setup-run/SKILL.md

@@ -14,6 +14,14 @@ This skill executes deterministic manifests. If
 hand it to the current supported AI provider; do not begin deterministic CLI
 execution.
 
+For AIWG's public installer, keep the provider in control of bootstrap and
+repair. Once the CLI is healthy, use `aiwg setup --scope project --providers
+<provider>` for the interview, `aiwg setup --review` for a read-only preview,
+and `aiwg setup --apply` after approval. These guided commands operate on a
+saved plan, not a SetupManifest. Headless interview uses the same answer flags
+with `--non-interactive`; headless apply requires `--yes`. See the
+[guided setup reference](../../../../../../docs/getting-started/guided-setup.md).
+
 ## Trigger Phrases
 
 - "run the setup manifest"

package/agentic/code/addons/agentic-installer/skills/setup-validate/SKILL.md

@@ -9,6 +9,11 @@ description: "Validate a `setup.aiwg.io/v1` SetupManifest file against the schem
 
 Validate a `setup.aiwg.io/v1` SetupManifest file against the schema and run consistency checks.
 
+For the public AIWG installer, retain `metadata.execution_mode:
+provider-orchestrated`. Validate the manifest's interview → review → apply
+sequence; do not convert it to deterministic execution. Guided plan review
+(`aiwg setup --review`) is distinct from SetupManifest schema validation.
+
 ## Trigger Phrases
 
 - "validate setup manifest"

package/agentic/code/addons/aiwg-dev/README.md

@@ -1,5 +1,7 @@
 # AIWG Developer Tools
 
+Evidence status: design intent.
+
 **For AIWG contributors only.** This addon provides rules and skills to help people building AIWG itself, AIWG addons, and AIWG extensions avoid common structural mistakes.
 
 This addon is **intentionally excluded from `aiwg use all`** and must be installed explicitly.

package/agentic/code/addons/aiwg-dev/skills/devkit-create-command/SKILL.md

@@ -12,7 +12,7 @@ description: Create a new slash command with AI-guided behavior definition
 >
 > ```bash
 > aiwg discover "<capability>"
-> aiwg show skill <name>
+> aiwg show skill <name> --body
 > ```
 >
 > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).

package/agentic/code/addons/aiwg-evals/README.md

@@ -1,5 +1,7 @@
 # AIWG Evaluations
 
+Evidence status: design intent; example scores are illustrative and targets are unmeasured.
+
 Automated evaluation framework for agent quality assessment.
 
 ## Research Foundation
@@ -192,6 +194,8 @@ aiwg eval-report --compare previous-report.json
 
 ### Quality Report
 
+The report below is an illustrative example, not measured results:
+
 ```markdown
 # Agent Quality Report
 
@@ -278,6 +282,8 @@ jobs:
 
 ## Success Metrics
 
+Unmeasured targets (no AIWG measurement yet):
+
 | Metric | Target |
 |--------|--------|
 | Grounding compliance | >90% |

package/agentic/code/addons/aiwg-hooks/README.md

@@ -1,5 +1,7 @@
 # AIWG Hooks
 
+Evidence status: design intent.
+
 Claude Code hook templates for workflow tracing, permissions, and session management.
 
 ## Research Foundation

package/agentic/code/addons/aiwg-hooks/hooks/quality-gates.md

@@ -510,7 +510,7 @@ Quality gates implement patterns from:
 - Issue #289 - Quality gate hook implementation
 - Issue #264 - Anti-laziness enforcement (REF-071, REF-072, REF-073, REF-074)
 - Claude Code v2.1.3 Release Notes - 10-minute timeout
-- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/anti-laziness.md - Avoidance pattern detection
+- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/anti-laziness.md - Avoidance pattern detection
 - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/executable-feedback.md - Execute before return
 - @.aiwg/research/findings/agentic-laziness-research.md - Research compilation
 

package/agentic/code/addons/aiwg-utils/README.md

@@ -1,5 +1,7 @@
 # AIWG Utilities
 
+Evidence status: design intent.
+
 Core meta-utilities for AIWG management. This addon is automatically installed with any AIWG framework.
 
 ## Commands

package/agentic/code/addons/aiwg-utils/agents/aiwg-finder.md

@@ -1,6 +1,6 @@
 ---
 name: aiwg-finder
-description: Capability discovery and tool-selection specialist — the finder for AIWG's operational assets. Takes a natural-language request, runs the `aiwg discover` + `aiwg show` pipeline, and returns the selected artifact(s) with capability summaries and full bodies. Companion to aiwg-steward.
+description: Capability discovery and tool-selection specialist — the finder for AIWG's operational assets. Takes a natural-language request, runs the `aiwg discover` + `aiwg show` card-and-drill-in pipeline, and returns the selected artifact(s) with capability summaries and full bodies. Companion to aiwg-steward.
 model: haiku
 tools:
   - Bash
@@ -26,7 +26,7 @@ and `session-harvest` handles reviewed knowledge extraction.
 1. **Parse** the operator's request — extract the actual capability need from the surface words
 2. **Query** the AIWG artifact index via `aiwg discover` — multiple queries if needed to triangulate
 3. **Rank** candidates by score, type, and fit to the user's actual intent
-4. **Fetch** the selected artifact body via `aiwg show <type> <name>`
+4. **Inspect** the metadata card via `aiwg show <type> <name>`, then fetch the relevant `--section "Heading"` or `--body` and required rules via `--rules --with-rule-bodies` before handing off governed work.
 5. **Return** a structured response: top match (or top-3 alternatives) with capability summary + full text of the chosen artifact, ready for the calling agent to apply
 
 ## Why You Exist
@@ -47,8 +47,8 @@ Request                    Your work                    Response
 ──────────                 ──────────                   ─────────
 "I need to deploy"   →    aiwg discover           →    {
                           → ranked candidates           top: { name, capability, body },
-                          aiwg show <type> <name>       alternatives: [...],
-                          → fetched body                rationale: "..."
+                          aiwg show <type> <name>              alternatives: [...],
+                          → card, then section/body                rationale: "..."
                                                        }
 ```
 
@@ -88,14 +88,14 @@ alternatives:
   - { type, name, capability, score }
 
 body: |
-  <full SKILL.md / agent.md / etc. content as fetched by `aiwg show`>
+  <full SKILL.md / agent.md / etc. content as fetched by `aiwg show <type> <name> --body`>
 
 rationale: |
   <1-3 sentences: why this top match, what the alternatives offer, any
    caveats the calling agent should know>
 ```
 
-When the operator wants only a recommendation without the full body (cheap mode), set `body: null` and explain in `rationale` that the body is fetchable via `aiwg show <type> <name>`.
+When the operator wants only a recommendation without the full body (cheap mode), set `body: null` and explain in `rationale` that the body is fetchable via `aiwg show <type> <name> --body`.
 
 When discovery returns nothing relevant (all scores below ~0.20), report:
 
@@ -135,7 +135,7 @@ Default form:
 aiwg discover "<phrase>" --json --limit 5
 ```
 
-JSON output is essential — it's stable, parseable, and includes the stable `id`, `name`, `title`, `score`, `triggers`, `capability`, `kernel`, `type`, and provenance for every result. Discovery intentionally omits paths; `aiwg show <type> <id> --json` supplies the resolved path with the selected body.
+JSON output is essential — it's stable, parseable, and includes the stable `id`, `name`, `title`, `score`, `triggers`, `capability`, `kernel`, `type`, and provenance for every result. Discovery intentionally omits paths; `aiwg show <type> <id> --body --json` supplies the resolved path with the selected body.
 
 For ambiguous needs, run **two or three queries** with different phrasings to triangulate:
 
@@ -162,10 +162,14 @@ Demote results where:
 
 ### Step 4: Fetch
 
-For the top match, fetch the body:
+For the top match, inspect the card and fetch the needed instructions:
 
 ```bash
 aiwg show <type> <name>
+aiwg show <type> <name> --section "Heading from the outline"
+aiwg show <type> <name> --rules --with-rule-bodies
+# When the calling agent needs the complete authored instructions:
+aiwg show <type> <name> --body
 ```
 
 Stream the result into your `body` field. If the operator's request was ambiguous and you want to compare two candidates, fetch both and let the rationale field do the comparison.
@@ -209,7 +213,7 @@ But the moment you need this fallback, log it in your rationale and recommend th
 aiwg discover "deploy production" --json --limit 3
 # top match: flow-deploy-to-production, score 0.51
 
-aiwg show skill flow-deploy-to-production
+aiwg show skill flow-deploy-to-production --body
 ```
 
 **Output**:
@@ -271,7 +275,7 @@ Three queries, three different top matches. Pick the most-frequently-appearing a
 aiwg discover "review architecture security" --type agent --json --limit 5
 # top: security-architect, score 0.62
 
-aiwg show agent security-architect
+aiwg show agent security-architect --body
 ```
 
 **Output**: `security-architect` selected with full agent definition body.
@@ -339,7 +343,7 @@ You are typically called *first* in a chain — the orchestrator's "what tool do
 ## References
 
 - `aiwg discover` — top-level capability search command
-- `aiwg show <type> <name>` — companion fetch command (#1218)
+- `aiwg show <type> <name>` — metadata card; `--section` / `--body` fetch instructions
 - `skill-discovery` HIGH rule — the framing rule this agent operationalizes
 - `aiwg-utils-quickref` — kernel quickref describing the discover→show pipeline
 - `docs/discovery-and-kernel-skills.md` — full operator guide with verification steps

package/agentic/code/addons/aiwg-utils/agents/aiwg-model-coding-worker.md

@@ -17,7 +17,7 @@ model-tier: standard
 
 You are a model-pinned subagent wrapper for bounded implementation and technical delivery.
 
-Accept an arbitrary scoped assignment from the parent agent. Use `aiwg discover` to locate relevant capabilities and `aiwg show` to load the selected agent, skill, rule, or workflow before applying it. Preserve the parent agent's scope and authorization boundaries. Implement and verify the requested work, then return changed artifacts, test evidence, remaining risks, and follow-up work.
+Accept an arbitrary scoped assignment from the parent agent. Use `aiwg discover` to locate relevant capabilities and `aiwg show <type> <name> --body` to load the selected agent, skill, rule, or workflow before applying it. Preserve the parent agent's scope and authorization boundaries. Implement and verify the requested work, then return changed artifacts, test evidence, remaining risks, and follow-up work.
 
 ## Worker boundaries
 

package/agentic/code/addons/aiwg-utils/agents/aiwg-model-efficiency-worker.md

@@ -17,7 +17,7 @@ model-tier: economy
 
 You are a model-pinned subagent wrapper for bounded, cost-efficient AIWG work.
 
-Accept an arbitrary scoped assignment from the parent agent. Use `aiwg discover` to locate relevant capabilities and `aiwg show` to load the selected agent, skill, rule, or workflow before applying it. Preserve the parent agent's scope and authorization boundaries. Complete the focused task with proportionate validation, then return changed artifacts, evidence, uncertainties, and follow-up work.
+Accept an arbitrary scoped assignment from the parent agent. Use `aiwg discover` to locate relevant capabilities and `aiwg show <type> <name> --body` to load the selected agent, skill, rule, or workflow before applying it. Preserve the parent agent's scope and authorization boundaries. Complete the focused task with proportionate validation, then return changed artifacts, evidence, uncertainties, and follow-up work.
 
 ## Worker boundaries
 

package/agentic/code/addons/aiwg-utils/agents/aiwg-model-reasoning-worker.md

@@ -18,7 +18,7 @@ model-rationale: Cross-domain architecture and synthesis assignments have high d
 
 You are a model-pinned subagent wrapper for bounded, reasoning-heavy AIWG work.
 
-Accept an arbitrary scoped assignment from the parent agent. Use `aiwg discover` to locate relevant capabilities and `aiwg show` to load the selected agent, skill, rule, or workflow before applying it. Preserve the parent agent's scope and authorization boundaries. Complete the work with concrete evidence, then return changed artifacts, validation results, decisions, risks, and follow-up work.
+Accept an arbitrary scoped assignment from the parent agent. Use `aiwg discover` to locate relevant capabilities and `aiwg show <type> <name> --body` to load the selected agent, skill, rule, or workflow before applying it. Preserve the parent agent's scope and authorization boundaries. Complete the work with concrete evidence, then return changed artifacts, validation results, decisions, risks, and follow-up work.
 
 ## Worker boundaries
 

package/agentic/code/addons/aiwg-utils/agents/aiwg-steward.md

@@ -23,7 +23,7 @@ You are the **AIWG Steward**: the thin Tier-1 routing core for AIWG installation
 ## Tier Loading Contract
 
 - **Tier 1, this file:** role, guardrails, context discipline, decision loop, and exact next-hop routes.
-- **Tier 2, quickrefs:** `[[steward-quickref]]`, `[[aiwg-utils-quickref]]`, and framework quickrefs. Use `aiwg discover "<phrase>"`, then `aiwg show <type> <name>`.
+- **Tier 2, quickrefs:** `[[steward-quickref]]`, `[[aiwg-utils-quickref]]`, and framework quickrefs. Use `aiwg discover "<phrase>"`, then `aiwg show <type> <name> --body`.
 - **Tier 3, references:** `[[aiwg-steward routing reference]]` and `[[aiwg-steward worked examples]]` for lookup tables, report scaffolds, deploy errata, badge snippets, and diagnostics.
 
 When a route is ambiguous, ask **one** clarifying question before acting. When a linked route is missing, stale, or contradicted by current CLI output, file a detailed AIWG correction issue through `aiwg-issue` / `steward-prep-delivery` with the broken target, expected route, observed output, and reproduction command.
@@ -89,8 +89,8 @@ Use these only after the Tier-2 route says the detail is needed:
 
 - `aiwg discover "aiwg-steward routing reference"` -> `[[aiwg-steward routing reference]]`: full CLI table, kernel/deploy paths, capability examples, invocation patterns, `$AIWG_ROOT` readability diagnostic, cross-provider diagnostic, orchestration routing table.
 - `aiwg discover "aiwg-steward worked examples"` -> `[[aiwg-steward worked examples]]`: report templates, refresh/deploy transcripts, session reload table, Hermes composition, deploy errata, badge helper snippets.
-- `aiwg show skill steward-quickref`: expansion/persona/project quick anchors.
-- `aiwg show skill aiwg-utils-quickref`: core utility routing and skill-first CLI policy.
+- `aiwg show skill steward-quickref --body`: expansion/persona/project quick anchors.
+- `aiwg show skill aiwg-utils-quickref --body`: core utility routing and skill-first CLI policy.
 
 ## Capability Matrix Rule
 

package/agentic/code/addons/aiwg-utils/agents/session-analyst.md

@@ -9,8 +9,8 @@ model-tier: standard
 
 # Session Analyst
 
-Use `aiwg show skill session-explore` for catalog investigation, and
-`aiwg show skill session-harvest` only when candidate extraction or promotion
+Use `aiwg show skill session-explore --body` for catalog investigation, and
+`aiwg show skill session-harvest --body` only when candidate extraction or promotion
 is requested. Return an answer grounded in normalized evidence and its coverage.
 Accept a natural-language question, authorized workspace, optional catalog path,
 provider/time filters, and output bounds. Ask only for missing scope that changes

package/agentic/code/addons/aiwg-utils/docs/agent-examples/aiwg-steward-examples.md

@@ -223,7 +223,7 @@ detail and edge cases were externalized here.
 - **Discover defaults (rc.23)**: `aiwg discover --limit` defaults to 5 (was 10) per
   peer-reviewed K=3 hit-rate findings.
 - **Show single-name fallback (rc.23)**: `aiwg show <name>` works when the name is
-  unambiguous across artifact types. `aiwg show <type> <name>` still works and is preferred
+  unambiguous across artifact types. `aiwg show <type> <name> --body` still works and is preferred
   when the type is known. Multi-type matches still error with the disambiguation list.
 
 ## Post-Deploy Session Reload (#1240)

package/agentic/code/addons/aiwg-utils/docs/agent-examples/aiwg-steward-routing-reference.md

@@ -29,7 +29,7 @@ The steward default dispatch is Tier 1. Follow this path for detail:
 
 1. Start from the inline Tier-2 Routing Map in `aiwg-steward.md`.
 2. For quick anchors, load `steward-quickref` or `aiwg-utils-quickref` with
-   `aiwg show skill <name>`.
+   `aiwg show skill <name> --body`.
 3. For enumerated tables, load this reference with
    `aiwg discover "aiwg-steward routing reference"` and then `aiwg show`.
 4. If a route is ambiguous, ask one clarifying question.
@@ -154,7 +154,7 @@ aiwg-refresh, aiwg-status, aiwg-help, use, aiwg-regenerate). Behavior summary:
 stale-skill cleanup prunes skills whose source no longer exists via the `.aiwg-managed`
 marker; `--copy-all` opts into the legacy per-project mirror for sandboxed runtimes where
 `$AIWG_ROOT` isn't readable; `aiwg discover --limit` defaults to 5; `aiwg show <name>`
-resolves an unambiguous single name (use `aiwg show <type> <name>` when the type is
+resolves an unambiguous single name (use `aiwg show <type> <name> --body` when the type is
 known). Version-specific provenance and edge cases (rc.17/rc.21/rc.23 changelog detail)
 live in the worked-examples catalog.
 

package/agentic/code/addons/aiwg-utils/manifest.json

@@ -139,6 +139,7 @@
     "customize-upstream-sync",
     "customize-contribute-back",
     "context-firewall",
+    "harness-memory-maintenance",
     "session-explore",
     "session-harvest"
   ],

package/agentic/code/addons/aiwg-utils/prompts/core/multi-agent-pattern.md

@@ -7,7 +7,7 @@ Standard pattern for artifact generation using coordinated agents.
 ```
 Primary Author (opus) → Creates initial draft
         ↓
-Parallel Reviewers (sonnet) → Independent review
+Parallel Reviewers (sonnet) → Separate initial judgments
   - Security review
   - Technical review
   - Standards review
@@ -18,6 +18,10 @@ Synthesizer (sonnet) → Merges feedback into final
 Archive → .aiwg/[category]/
 ```
 
+## Review evidence
+
+Agreement is not proof, including same-vendor and cross-vendor agreement. Consequential claims require an executable check or accountable human acceptance. Prefer independent voting, or structured review with diverse initial answers and calibrated confidence, over plain debate. Record observed evaluator model/vendor/family, acceptance criteria reference, generator/evaluator disagreements and a re-review link after material fixes. Do not claim reduced human-review time. See `$AIWG_ROOT/docs/decision/evaluator-calibration.md` for calibration and REF-2922, REF-2923, REF-2919/2921 public sources.
+
 ## Implementation
 
 ### Step 1: Primary Author
@@ -98,6 +102,10 @@ Each reviewer should produce:
 # [Review Type] Review
 
 **Reviewer**: [Agent Name]
+**Observed evaluator model/vendor/family**: [Runtime identity or unknown]
+**Acceptance criteria reference**: [Version/digest]
+**Disagreements**: [Generator and evaluator positions, check/acceptance references]
+**Re-review of**: [Earlier review reference after material fixes]
 **Artifact**: [What was reviewed]
 **Date**: [Timestamp]
 

package/agentic/code/addons/aiwg-utils/prompts/core/orchestrator.md

@@ -8,7 +8,7 @@ You are the active provider's SDLC orchestrator. You:
 
 1. Interpret the user's desired outcome and right-size the workflow.
 2. Consult the always-loaded `sdlc-quickref` kernel skill.
-3. Use `aiwg discover "<need>"` then `aiwg show skill <name>` when the quickref does not already name the capability.
+3. Use `aiwg discover "<need>"` then `aiwg show skill <name> --body` when the quickref does not already name the capability.
 4. Treat canonical skills and their referenced playbooks as authoritative.
 5. Coordinate work through provider-native delegation mechanics and synthesize the result.
 

package/agentic/code/addons/aiwg-utils/rules/anti-laziness.core.md

@@ -0,0 +1,13 @@
+# Core: Anti-Laziness
+
+Always applies to every task and agent. Overrides convenience, brevity and speed preferences.
+
+- Finish the authorized task within its scope. Do not stop at a plan, partial fix, or first green signal when remaining steps are known and permitted.
+- Do not hand work back that you can do yourself. Ask only when blocked on a decision, credential or authorization that belongs to the user.
+- Verify before claiming done: run the checks the change needs and read their results. "Should work" is not done.
+- Fix root causes. Never delete or skip tests, weaken assertions, suppress CI or lint signals, or remove features to make something pass.
+- Read failures fully and investigate before retrying; no blind retries or approach-swapping to dodge a problem.
+- Report outcomes faithfully: say what failed, was skipped and remains. Never present partial work as complete.
+- On detecting avoidance, stop, name it, and resume the full task.
+
+Full rule (on demand, not an import): `aiwg show rule anti-laziness`