oh-my-customcode 0.80.0 → 0.81.0

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-47 agents. 101 skills. 21 rules. One command.
+48 agents. 104 skills. 22 rules. One command.
 
 ```bash
 npm install -g oh-my-customcode && cd your-project && omcustom init
@@ -124,7 +124,7 @@ Agent(arch-documenter):haiku      ┘
 
 ---
 
-### Agents (47)
+### Agents (48)
 
 | Category | Count | Agents |
 |----------|-------|--------|
@@ -145,7 +145,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 
 ---
 
-### Skills (101)
+### Skills (104)
 
 | Category | Count | Includes |
 |----------|-------|----------|
@@ -223,7 +223,7 @@ All commands are invoked inside the Claude Code conversation.
 
 ---
 
-### Rules (21)
+### Rules (22)
 
 | Priority | Count | Purpose |
 |----------|-------|---------|
@@ -284,9 +284,9 @@ omcustom serve-stop            # Stop Web UI
 your-project/
 ├── CLAUDE.md                   # Entry point
 ├── .claude/
-│   ├── agents/                 # 47 agent definitions
-│   ├── skills/                 # 101 skill modules
-│   ├── rules/                  # 21 governance rules (R000-R021)
+│   ├── agents/                 # 48 agent definitions
+│   ├── skills/                 # 104 skill modules
+│   ├── rules/                  # 22 governance rules (R000-R021)
 │   ├── hooks/                  # 15 lifecycle hook scripts
 │   ├── schemas/                # Tool input validation schemas
 │   ├── specs/                  # Extracted canonical specs

package/dist/cli/index.js

@@ -2301,7 +2301,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.80.0",
+    version: "0.81.0",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -1973,7 +1973,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.80.0",
+  version: "0.81.0",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.80.0",
+  "version": "0.81.0",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/agents/wiki-curator.md

@@ -0,0 +1,72 @@
+---
+name: wiki-curator
+description: Dedicated wiki page CRUD agent — creates, updates, and maintains wiki/ markdown pages for the codebase knowledge base
+model: sonnet
+tools:
+  - Read
+  - Write
+  - Edit
+  - Glob
+  - Grep
+  - Bash
+domain: universal
+memory: project
+permissionMode: bypassPermissions
+---
+
+# Wiki Curator
+
+Dedicated agent for wiki file operations. All wiki/ directory writes go through this agent per R010 delegation rules.
+
+## Role
+
+- Create new wiki pages from source file analysis
+- Update existing wiki pages when sources change
+- Maintain index.md and log.md
+- Execute wiki lint fixes (orphan removal, cross-ref repair)
+- Generate synthesis pages (architecture, workflows, concepts)
+
+## Capabilities
+
+- Read source files (.claude/agents/*.md, .claude/skills/*/SKILL.md, .claude/rules/*.md, guides/*/)
+- Write/Edit wiki pages in wiki/ directory
+- Maintain YAML frontmatter consistency across all pages
+- Cross-reference management using [[wikilink]] and standard markdown links
+- Incremental updates based on source modification dates
+
+## Wiki Page Quality Standards
+
+Every page must:
+- Have valid YAML frontmatter (title, type, updated, sources, related)
+- Include 5-10 outbound cross-references
+- Stay concise: 150-300 words for entity pages, 200-400 for synthesis pages
+- Explain purpose and design intent, not just enumerate fields
+- Use both [[wikilink]] and [standard](markdown) link formats
+
+## Workflow Patterns
+
+### Single Page Update
+1. Read source file
+2. Read existing wiki page (if exists)
+3. Determine what changed
+4. Write updated page with current date in `updated` field
+5. Update cross-references in related pages
+6. Update index.md if page is new
+
+### Batch Update (Category)
+1. Glob source files in category
+2. Compare modification dates against wiki pages
+3. Write only changed/new pages
+4. Batch-update index.md once at end
+
+### Lint Fix
+1. Receive lint findings from orchestrator
+2. Fix each category: remove orphans, repair broken refs, update stale pages
+3. Append fix results to log.md
+
+## Limitations
+
+- Does NOT decide what to write — receives instructions from orchestrator or wiki skill
+- Does NOT spawn subagents — works as a leaf agent
+- Does NOT modify source files (.claude/agents/, .claude/skills/, etc.)
+- Only writes to wiki/ directory

package/templates/.claude/hooks/hooks.json

@@ -155,6 +155,16 @@
           }
         ],
         "description": "Scan TODO.md files for stale items at session start"
+      },
+      {
+        "matcher": "*",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash .claude/hooks/scripts/adaptive-harness-scan.sh"
+          }
+        ],
+        "description": "Lightweight project profile staleness check for adaptive harness (#831)"
       }
     ],
     "UserPromptSubmit": [

package/templates/.claude/hooks/scripts/adaptive-harness-scan.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+# adaptive-harness-scan.sh — Lightweight project profile staleness check
+# Runs at SessionStart. Must complete in <2s. Advisory only (never blocks).
+
+set -euo pipefail
+
+PROJECT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
+PROFILE="$PROJECT_ROOT/.claude/project-profile.yaml"
+
+# Skip if this IS the oh-my-customcode project itself (meta-project)
+if [ -f "$PROJECT_ROOT/.claude/skills/adaptive-harness/SKILL.md" ] && \
+   [ -f "$PROJECT_ROOT/CLAUDE.md" ] && \
+   grep -q "oh-my-customcode" "$PROJECT_ROOT/CLAUDE.md" 2>/dev/null; then
+  # Only check if profile exists for the meta-project
+  if [ ! -f "$PROFILE" ]; then
+    echo "[adaptive-harness] No project profile found. Run /omcustom:adaptive-harness --scan to generate." >&2
+  fi
+  exit 0
+fi
+
+# For non-omcustom projects
+if [ ! -f "$PROFILE" ]; then
+  echo "[adaptive-harness] No project profile found. Run /omcustom:adaptive-harness --scan to auto-configure harness." >&2
+  exit 0
+fi
+
+# Check staleness: if any key project files changed since last scan
+PROFILE_MTIME=$(stat -f "%m" "$PROFILE" 2>/dev/null || stat -c "%Y" "$PROFILE" 2>/dev/null || echo "0")
+STALE=false
+
+for indicator in package.json go.mod Cargo.toml requirements.txt pyproject.toml build.gradle pom.xml; do
+  if [ -f "$PROJECT_ROOT/$indicator" ]; then
+    FILE_MTIME=$(stat -f "%m" "$PROJECT_ROOT/$indicator" 2>/dev/null || stat -c "%Y" "$PROJECT_ROOT/$indicator" 2>/dev/null || echo "0")
+    if [ "$FILE_MTIME" -gt "$PROFILE_MTIME" ] 2>/dev/null; then
+      STALE=true
+      break
+    fi
+  fi
+done
+
+if [ "$STALE" = true ]; then
+  echo "[adaptive-harness] Project profile may be stale. Consider running /omcustom:adaptive-harness --scan" >&2
+fi
+
+exit 0

package/templates/.claude/rules/MUST-continuous-improvement.md

@@ -32,12 +32,22 @@ Update the relevant rule rather than just acknowledging the violation.
 | CI/infra defect | — | ✅ | ✅ |
 | Process gap (workflow hole) | ✅ | ✅ | ✅ |
 | Repeatable system bug | — | ✅ | ✅ |
+| Agent selection failure (wrong agent routed) | — | ✅ | — |
 
 When CI failure, process gap, or repeatable system defect is found:
 1. Record feedback memory (defend current session)
 2. Register GitHub issue (trackable improvement item)
 3. Both required — memory alone is NOT sufficient for system-level defects
 
+### Adaptive Harness Integration
+
+When repeating agent failures or suboptimal routing is detected:
+1. Record as feedback memory (immediate session defense)
+2. Run `/omcustom:adaptive-harness --learn` to update project profile with failure patterns
+3. Profile updates improve future agent selection and harness optimization
+
+This connects R016's continuous improvement loop with the adaptive-harness skill's learning capability.
+
 ## Anti-Patterns
 
 | Anti-Pattern | Why It's Wrong | Correct Action |

package/templates/.claude/rules/MUST-sync-verification.md

@@ -28,11 +28,22 @@ Also run: mgr-claude-code-bible:verify (official spec compliance)
 | 2 | References: no orphans, no circular refs, valid skill/memory refs |
 | 3 | Philosophy: R006 separation, R009 parallel, R010 delegation, R007/R008 identification |
 
-### Phase 3: Fix all discovered issues
+### Phase 3: Wiki Sync Verification
 
-### Phase 4: Commit via mgr-gitnerd
+| Check | Action |
+|-------|--------|
+| Missing pages | Source entities without wiki pages → run `/omcustom:wiki` |
+| Stale pages | Source modification date newer than wiki `updated` field → run `/omcustom:wiki ingest <path>` |
+| Broken cross-refs | Wiki links pointing to non-existent pages → run `/omcustom:wiki lint` |
+| index.md accuracy | Wiki index page count matches actual page count |
 
-### Phase 5: Push via mgr-gitnerd (only after sauron passes)
+Wiki verification is also enforced by CI (`.github/workflows/wiki-sync.yml`).
+
+### Phase 4: Fix all discovered issues
+
+### Phase 5: Commit via mgr-gitnerd
+
+### Phase 6: Push via mgr-gitnerd (only after sauron passes)
 
 ## Self-Check Before Commit and Push
 
@@ -45,6 +56,7 @@ Also run: mgr-claude-code-bible:verify (official spec compliance)
 ║  3. Did I fix all discovered issues?                             ║
 ║  4. Are all counts matching across all sources?                  ║
 ║  5. Am I delegating to mgr-gitnerd for the commit?               ║
+║  6. Are wiki pages in sync with source changes?                  ║
 ║                                                                   ║
 ║  If NO to any → wait until verification completes                ║
 ╚══════════════════════════════════════════════════════════════════╝
@@ -64,11 +76,11 @@ Also run: mgr-claude-code-bible:verify (official spec compliance)
 
 ## When Required
 
-Any change to: agents, agent frontmatter, skills, guides, routing patterns, rules.
+Any change to: agents, agent frontmatter, skills, guides, routing patterns, rules, wiki pages.
 
 ## Quick Verification Commands
 
-Key checks: agent count (`ls .claude/agents/*.md | wc -l`), skill count (`find .claude/skills -name "SKILL.md" | wc -l`), guide count (`find guides -mindepth 1 -maxdepth 1 -type d | wc -l`).
+Key checks: agent count (`ls .claude/agents/*.md | wc -l`), skill count (`find .claude/skills -name "SKILL.md" | wc -l`), guide count (`find guides -mindepth 1 -maxdepth 1 -type d | wc -l`), wiki page count (`find wiki -name "*.md" ! -name "index.md" ! -name "log.md" | wc -l`).
 
 <!-- DETAIL: Full verification bash scripts
 ```bash

package/templates/.claude/rules/SHOULD-wiki-sync.md

@@ -0,0 +1,67 @@
+# [SHOULD] Wiki Sync Rules
+
+> **Priority**: SHOULD | **ID**: R022
+
+## Core Rule
+
+When agents, skills, rules, or guides are created or modified, corresponding wiki pages SHOULD be updated to keep the knowledge base current. The wiki is the project's compiled knowledge — stale wikis degrade team and LLM onboarding speed.
+
+## When to Sync
+
+| Change Type | Wiki Action |
+|-------------|-------------|
+| New agent created | Create wiki/agents/{name}.md |
+| Agent modified | Update wiki/agents/{name}.md |
+| New skill created | Create wiki/skills/{name}.md |
+| Skill modified | Update wiki/skills/{name}.md |
+| Rule created/modified | Update wiki/rules/r{nnn}.md |
+| Guide created/modified | Update wiki/guides/{name}.md |
+| Architecture change | Update wiki/architecture/ pages |
+| Multiple changes | Run `/omcustom:wiki` for full update |
+
+## How to Sync
+
+| Method | When |
+|--------|------|
+| `/omcustom:wiki ingest <path>` | Single file/directory changed |
+| `/omcustom:wiki` | Multiple files changed or periodic refresh |
+| `/omcustom:wiki lint` | After major structural changes |
+| Automatic (CI) | `.github/workflows/wiki-sync.yml` checks on PR |
+
+## Delegation
+
+All wiki writes MUST go through the `wiki-curator` agent (R010). The orchestrator reads wiki pages freely but never writes them directly.
+
+```
+Orchestrator
+├── Detects source change
+├── Delegates to wiki-curator
+│   ├── Reads source file
+│   ├── Creates/updates wiki page
+│   ├── Updates cross-references
+│   └── Updates index.md
+└── Verifies via wiki lint
+```
+
+## Integration
+
+| Rule | Interaction |
+|------|-------------|
+| R010 | Wiki writes delegated to wiki-curator agent |
+| R017 | Wiki sync added to sauron verification Phase 3 |
+| R020 | Wiki-dependent tasks verify wiki is current before [Done] |
+| R006 | Wiki pages follow same separation of concerns as source |
+| R021 | SHOULD priority — advisory enforcement, CI check |
+
+## CI Enforcement
+
+`.github/workflows/wiki-sync.yml` checks for missing wiki pages on every PR. Missing pages cause CI failure with guidance to run `/omcustom:wiki`.
+
+## Self-Check
+
+Before completing a session that modified agents/skills/rules/guides:
+1. Were wiki pages updated for all changes?
+2. Was index.md refreshed?
+3. Did wiki lint pass?
+
+If any NO → run `/omcustom:wiki ingest` for affected paths.

package/templates/.claude/skills/adaptive-harness/SKILL.md

@@ -0,0 +1,335 @@
+---
+name: adaptive-harness
+description: Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile
+scope: harness
+version: 1.0.0
+user-invocable: true
+argument-hint: "[--optimize|--scan|--learn|--export|--import|--dry-run] [target-dir]"
+effort: high
+---
+
+# Adaptive Harness Self-Customization Skill
+
+Automatically detects project context and optimizes the oh-my-customcode harness (agents, skills, rules) to fit the project. Generates a persistent project profile that drives agent activation decisions and records learned patterns over time.
+
+## Usage
+
+```
+/omcustom:adaptive-harness              # Full scan + optimize
+/omcustom:adaptive-harness --scan       # Scan only (generate/update project profile)
+/omcustom:adaptive-harness --optimize   # Deactivate unused, suggest missing
+/omcustom:adaptive-harness --learn      # Analyze failure patterns, update profile
+/omcustom:adaptive-harness --export     # Export profile as portable bundle
+/omcustom:adaptive-harness --import <path>  # Import profile from another project
+/omcustom:adaptive-harness --dry-run    # Show what would change without modifying
+```
+
+Default (no flag): runs `--scan` then `--optimize` in sequence.
+
+## Project Profile Format
+
+The skill generates and maintains `.claude/project-profile.yaml`. Manual edits to this file are preserved across runs — the skill merges new detections with existing content rather than overwriting.
+
+```yaml
+# Auto-generated by adaptive-harness. Manual edits will be preserved.
+project:
+  name: detected-project-name
+  scanned_at: "2026-04-12T10:00:00Z"
+
+tech_stack:
+  languages: [python, typescript]
+  frameworks: [fastapi, next.js]
+  databases: [postgres, redis]
+  infra: [docker, aws]
+
+detection_evidence:
+  - indicator: "requirements.txt found"
+    confidence: high
+    suggests: [lang-python-expert, be-fastapi-expert]
+  - indicator: "package.json with next dependency"
+    confidence: high
+    suggests: [lang-typescript-expert, fe-vercel-agent]
+
+active_agents:
+  - lang-python-expert
+  - be-fastapi-expert
+  - lang-typescript-expert
+  - fe-vercel-agent
+  - db-postgres-expert
+  - db-redis-expert
+  - infra-docker-expert
+  - infra-aws-expert
+  # manager agents always active
+  - mgr-creator
+  - mgr-gitnerd
+  - mgr-sauron
+  - mgr-supplier
+  - mgr-updater
+  - mgr-claude-code-bible
+
+inactive_agents:
+  - lang-golang-expert    # no Go files detected
+  - lang-rust-expert      # no Rust files detected
+
+usage_stats:
+  most_used_agents: []     # populated by --learn
+  failure_patterns: []     # populated by --learn
+
+overrides:
+  rules: {}                # e.g., R009: { max_parallel: 5 }
+
+last_optimized: "2026-04-12T10:00:00Z"
+```
+
+## Workflow: --scan
+
+Scans the TARGET project (the project using oh-my-customcode, not the harness itself) and generates or updates the project profile. Uses Read, Glob, and Grep only — no side effects.
+
+### Step 1: Detect Tech Stack
+
+Check for language manifest files and framework indicators:
+
+| Indicator Files | Tech | Suggests Agents |
+|----------------|------|-----------------|
+| `go.mod`, `*.go` | Go | lang-golang-expert, be-go-backend-expert |
+| `Cargo.toml`, `*.rs` | Rust | lang-rust-expert |
+| `requirements.txt`, `pyproject.toml`, `*.py` | Python | lang-python-expert |
+| `fastapi` in deps/imports | FastAPI | be-fastapi-expert |
+| `django` in deps/imports | Django | be-django-expert |
+| `package.json`, `tsconfig.json`, `*.ts`, `*.tsx` | TypeScript | lang-typescript-expert |
+| `next` in package.json deps | Next.js | fe-vercel-agent |
+| `vue` in package.json deps | Vue.js | fe-vuejs-agent |
+| `svelte.config.*`, `*.svelte` | Svelte | fe-svelte-agent |
+| `pubspec.yaml`, `*.dart` | Flutter | fe-flutter-agent |
+| `*.kt`, `build.gradle.kts` | Kotlin | lang-kotlin-expert |
+| `*.java`, `pom.xml` | Java | lang-java21-expert |
+| `spring-boot` in deps | Spring Boot | be-springboot-expert |
+| `express` in package.json deps | Express | be-express-expert |
+| `@nestjs` in package.json deps | NestJS | be-nestjs-expert |
+| `Dockerfile`, `docker-compose.*` | Docker | infra-docker-expert |
+| `cdk.json`, `template.yaml`, `.aws/` | AWS | infra-aws-expert |
+| `terraform/`, `*.tf` | Terraform | infra-aws-expert |
+| `.github/workflows/` | CI/CD | mgr-gitnerd |
+| `*.sql`, `alembic/`, `pg` in deps | PostgreSQL | db-postgres-expert |
+| `redis` in deps/config | Redis | db-redis-expert |
+| `supabase` in deps/config | Supabase | db-supabase-expert |
+| `prisma/`, `drizzle/` | ORM | db-postgres-expert |
+| `dags/*.py`, `airflow` in deps | Airflow | de-airflow-expert |
+| `dbt_project.yml` | dbt | de-dbt-expert |
+| `kafka` in deps/config | Kafka | de-kafka-expert |
+| `spark` in deps/config | Spark | de-spark-expert |
+| `snowflake` in deps/config | Snowflake | de-snowflake-expert |
+
+### Step 2: Build Detection Evidence
+
+For each indicator found, record:
+- `indicator`: human-readable description of what was found
+- `confidence`: `high` (direct manifest file) | `medium` (dependency reference) | `low` (indirect signal)
+- `suggests`: list of agent names this indicator implies
+
+### Step 3: Write Project Profile
+
+Delegate write to a subagent (R010). Merge with existing profile if present — preserve `overrides`, `usage_stats`, and any manual entries.
+
+Output format:
+
+```
+[adaptive-harness --scan] Target: /path/to/project
+
+Tech Stack Detected:
+  - Python     (requirements.txt + pyproject.toml found)      [confidence: high]
+  - FastAPI    ("fastapi" in requirements.txt)                [confidence: high]
+  - TypeScript (tsconfig.json found)                          [confidence: high]
+  - Next.js    ("next" in package.json deps)                  [confidence: high]
+  - Docker     (Dockerfile found)                             [confidence: high]
+  - PostgreSQL ("psycopg2" in requirements.txt)               [confidence: medium]
+  - Redis      ("redis" in requirements.txt)                  [confidence: medium]
+  - AWS        (cdk.json found)                               [confidence: high]
+
+Active agents identified: 8
+Profile written: .claude/project-profile.yaml
+```
+
+## Workflow: --optimize
+
+Reads the project profile and adjusts which agent files are active.
+
+### Step 1: Load Profile
+
+Read `.claude/project-profile.yaml`. If the profile does not exist, run `--scan` first.
+
+### Step 2: Identify Inactive Agents
+
+Compare all agent files in `.claude/agents/*.md` against `active_agents` list from the profile. Agents not in the active list (and not in the always-active set below) are candidates for deactivation.
+
+### Always-Active Agents (never deactivate)
+
+```
+mgr-creator, mgr-gitnerd, mgr-sauron, mgr-supplier, mgr-updater, mgr-claude-code-bible
+sys-memory-keeper, sys-naggy
+arch-documenter, arch-speckit-agent
+```
+
+### Step 3: Move Inactive Agents
+
+Delegate to subagent (R010):
+- Create `.claude/agents/.inactive/` directory if it does not exist
+- Move inactive agent `.md` files to `.claude/agents/.inactive/`
+- Update `inactive_agents` list in project profile
+
+### Step 4: Detect Gaps
+
+Check `active_agents` list against files actually present in `.claude/agents/`. If an active agent file is missing, flag it as a gap and suggest `mgr-creator` to fill it.
+
+### Step 5: Log Adaptations
+
+Append a record to `.claude/outputs/harness-adaptations/YYYY-MM-DD.md`:
+
+```markdown
+## Optimization Run — 2026-04-12T10:00:00Z
+
+Deactivated (moved to .inactive/):
+  - lang-golang-expert
+  - lang-rust-expert
+  - de-airflow-expert
+
+Gaps detected (agents needed but missing):
+  - (none)
+
+Profile: .claude/project-profile.yaml
+```
+
+### Restore
+
+Run `--optimize --restore` to move all files from `.claude/agents/.inactive/` back to `.claude/agents/`. This reverses the last optimization.
+
+Output format:
+
+```
+[adaptive-harness --optimize]
+
+Always-active agents: 10 (protected)
+Active per profile:   8
+Candidates for deactivation: 29
+
+Deactivated:
+  - lang-golang-expert      → .claude/agents/.inactive/
+  - lang-rust-expert        → .claude/agents/.inactive/
+  - de-airflow-expert       → .claude/agents/.inactive/
+  ... (26 more)
+
+Gaps detected: 0
+
+Log: .claude/outputs/harness-adaptations/2026-04-12.md
+Summary: 29 deactivated, 18 active, 0 gaps
+```
+
+**--dry-run** mode outputs `[would deactivate]` / `[would restore]` without moving any files.
+
+## Workflow: --learn
+
+Analyzes session history and eval-core data to populate `usage_stats` and `failure_patterns` in the project profile.
+
+### Step 1: Collect Data Sources
+
+- `.claude/outputs/` — session artifacts and eval results
+- `.claude/agent-memory/` — agent memory files with usage patterns
+- Any harness eval output from `/omcustom:harness-eval`
+
+### Step 2: Extract Patterns
+
+```
+Most-used agents:   Count agent invocations across outputs
+Failure patterns:   Identify agents that frequently retried or errored
+Unused agents:      Active agents with zero invocations in recent N sessions
+```
+
+### Step 3: Update Profile
+
+Merge findings into `usage_stats` and `failure_patterns` sections of the project profile. Preserve existing entries; append new ones.
+
+### Step 4: Generate Suggestions
+
+Based on failure patterns, suggest:
+- Rule overrides (e.g., increase `max_parallel` if timeout patterns detected)
+- Agent replacements (e.g., suggest escalation to `opus` model for frequently failing tasks)
+- Additional skills that may reduce failure rate
+
+Output format:
+
+```
+[adaptive-harness --learn]
+
+Sessions analyzed: 12
+Agent invocations found: 847
+
+Most-used agents (top 5):
+  1. lang-python-expert    (312 invocations)
+  2. be-fastapi-expert     (189 invocations)
+  3. mgr-gitnerd           (97 invocations)
+  4. db-postgres-expert    (84 invocations)
+  5. lang-typescript-expert (71 invocations)
+
+Failure patterns:
+  - db-postgres-expert: 3 retries in session 2026-04-10 (timeout pattern)
+  
+Suggestions:
+  - db-postgres-expert: consider effort: high for complex query generation
+  - de-kafka-expert: 0 invocations — candidate for deactivation
+
+Profile updated: .claude/project-profile.yaml
+```
+
+## Workflow: --export / --import
+
+### Export
+
+Bundles the project profile and active agent list for sharing with another project or team member.
+
+Output: `.claude/outputs/harness-bundle-YYYY-MM-DD.json`
+
+```json
+{
+  "version": "1.0.0",
+  "exported_at": "2026-04-12T10:00:00Z",
+  "source_project": "detected-project-name",
+  "profile": { ... },
+  "active_agent_names": [ ... ]
+}
+```
+
+### Import
+
+```
+/omcustom:adaptive-harness --import .claude/outputs/harness-bundle-2026-04-12.json
+```
+
+Reads the bundle and applies the `active_agents` list to the current project by running `--optimize` with the imported profile. Does not overwrite `usage_stats` or `failure_patterns` from the current project.
+
+## Execution Rules
+
+- `--scan` uses Read, Glob, Grep only — no writes, safe to run anytime
+- All file writes (profile, logs, agent moves) are delegated to subagents (R010)
+- `--dry-run` suppresses all writes; outputs `[would ...]` for every action
+- Profile changes are always logged to `.claude/outputs/harness-adaptations/` for auditability
+- When profile already exists, the skill merges new detections rather than overwriting
+- Parallel Glob/Grep calls are used during `--scan` for performance (R009)
+
+## Integration
+
+| Component | Interaction |
+|-----------|-------------|
+| `/omcustom:analysis` | Calls adaptive-harness `--scan` after initial tech stack detection to persist the profile |
+| `SessionStart` hook | Lightweight profile existence check only — no full scan at startup |
+| `mgr-creator` | Invoked when gaps are detected during `--optimize` to create missing agent files |
+| `R016` (Continuous Improvement) | Failure patterns from `--learn` may trigger rule updates |
+| `eval-core` | Primary data source for `--learn` invocation and usage pattern extraction |
+| `mgr-sauron` | Run after `--optimize` to verify structural integrity (R017) |
+
+## Notes
+
+- Always run `--dry-run` first on a new project to preview deactivation scope
+- `--optimize --restore` is the safe exit if deactivation causes unexpected routing failures
+- The `.inactive/` directory is git-tracked so deactivation decisions are visible in history
+- Manager and system agents are unconditionally protected from deactivation
+- Target directory defaults to the project root where Claude Code is running, not the omcustom harness directory