@soleri/forge 9.3.1 → 9.5.0

package/src/skills/verification-before-completion/SKILL.md

@@ -75,6 +75,18 @@ Capture session summary: `YOUR_AGENT_core op:session_capture params: { summary:
 - Running linter but not build (linter does not check compilation)
 - Skipping the red-green cycle for regression tests
 
+## Rationalization Prevention
+
+Do NOT rationalize away failures. If a check fails, it fails. Period.
+
+- **HARD-GATE: All verification commands must pass (exit 0, 0 failures) before claiming task complete.**
+- **HARD-GATE: Agent system checks (`admin_health`, `admin_diagnostic`) must report no problems before completion.**
+- Do not say "tests probably pass" -- run them and read the output.
+- Do not say "this is a minor issue" to skip a failing check.
+- Do not say "it worked last time" -- stale results are not evidence.
+- Do not downgrade a failure to a warning to avoid blocking completion.
+- If a check fails and you cannot fix it, report the failure honestly. Never hide it.
+
 ## Quick Reference
 
 | Op                      | When to Use                         |

package/src/skills/yolo-mode/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: yolo-mode
+description: >
+  Use when the user says "yolo", "autonomous", "skip approvals", "full auto", "hands off",
+  or asks to execute without approval gates. Activates autonomous execution mode where the
+  agent skips plan approval gates but preserves all safety invariants.
+---
+
+# YOLO Mode
+
+Autonomous execution without approval gates. Plans execute immediately — no Gate 1, no Gate 2, no confirmation prompts.
+
+**Announce at start:** "I'm activating YOLO mode — autonomous execution with safety invariants intact."
+
+## Activation Flow
+
+### Step 1: Verify Safety Hook Pack
+
+```
+YOUR_AGENT_core op:admin_health
+```
+
+Check that the YOLO Safety Hook Pack is installed. This pack intercepts destructive commands (force push, reset --hard, drop table, rm -rf).
+
+**HARD-GATE: Refuse to activate YOLO mode if the safety hook pack is not installed.** Tell the user: "YOLO mode requires the safety hook pack. Run `soleri hooks add-pack yolo-safety` first."
+
+### Step 2: Morph to YOLO Mode
+
+```
+YOUR_AGENT_core op:morph
+  params: { mode: "YOLO-MODE" }
+```
+
+### Step 3: Confirm to User
+
+State clearly: "YOLO mode active. Approval gates are off. Safety invariants remain enforced. Say 'exit YOLO' to return to normal mode."
+
+## What Gets Skipped
+
+- Plan approval Gate 1 (`op:approve_plan`)
+- Plan approval Gate 2 (`op:plan_split` confirmation)
+- User confirmation prompts between steps
+- "Ready for feedback?" checkpoints
+
+## What Is NEVER Skipped
+
+- **`op:orchestrate_complete`** — knowledge capture runs on every task, always
+- **Vault search before decisions** — check vault for patterns/anti-patterns before acting
+- **YOLO Safety Hook Pack** — intercepts destructive commands (force push, drop table, rm -rf, reset --hard)
+- **Test execution** — tests still run; failures still block completion
+- **`op:plan_reconcile`** — drift reports still generated after execution
+
+## Exit Conditions
+
+YOLO mode deactivates when any of these occur:
+
+- User says "exit YOLO", "stop YOLO", or "normal mode"
+- Session ends
+- Explicit deactivation: `op:morph params: { mode: "DEFAULT" }`
+- Safety hook intercepts a destructive command (auto-exits, requires re-activation)
+
+## Anti-Patterns
+
+- Activating YOLO on an unfamiliar codebase — you need vault context first
+- Skipping tests in YOLO — tests are safety, not ceremony
+- Using YOLO for architectural decisions that need human judgment
+- Staying in YOLO after a safety hook triggers — re-evaluate before re-activating
+- Running YOLO without reviewing what the safety hook pack actually covers
+
+## Quick Reference
+
+| Op                     | When to Use                          |
+| ---------------------- | ------------------------------------ |
+| `admin_health`         | Verify safety hook pack is installed |
+| `morph`                | Activate/deactivate YOLO mode        |
+| `orchestrate_complete` | After every task (never skip)        |
+| `search_intelligent`   | Before every decision (never skip)   |
+| `plan_reconcile`       | After execution (never skip)         |
+
+**Related skills:** executing-plans, writing-plans

package/src/templates/clean-worktrees.ts

@@ -0,0 +1,58 @@
+/**
+ * Generate a POSIX sh script that cleans up stale Claude Code worktrees.
+ * Registered as a SessionStart hook in scaffolded agents.
+ */
+export function generateCleanWorktreesScript(): string {
+  return `#!/bin/sh
+# Clean stale Claude Code worktrees on session start.
+# Registered as a SessionStart hook by Soleri scaffolding.
+# Safe: skips active worktrees, checks for unpushed commits.
+
+WORKTREE_DIR=".claude/worktrees"
+
+# Exit silently if no worktrees directory
+[ -d "$WORKTREE_DIR" ] || exit 0
+
+# Prune worktrees whose branches have been deleted
+git worktree prune 2>/dev/null
+
+# Get list of active worktrees (skip the main one)
+active_worktrees="$(git worktree list --porcelain 2>/dev/null | grep '^worktree ' | sed 's/^worktree //')"
+
+cleaned=0
+skipped=0
+
+for dir in "$WORKTREE_DIR"/*/; do
+  [ -d "$dir" ] || continue
+
+  # Resolve to absolute path for comparison
+  abs_dir="$(cd "$dir" 2>/dev/null && pwd)" || continue
+
+  # Skip if still in git worktree list (active)
+  if echo "$active_worktrees" | grep -qF "$abs_dir"; then
+    skipped=$((skipped + 1))
+    continue
+  fi
+
+  # Safety: check for unpushed commits before removing
+  branch="$(git -C "$dir" rev-parse --abbrev-ref HEAD 2>/dev/null)" || branch=""
+  if [ -n "$branch" ] && [ "$branch" != "HEAD" ]; then
+    upstream="$(git -C "$dir" rev-parse --abbrev-ref "@{upstream}" 2>/dev/null)" || upstream=""
+    if [ -n "$upstream" ]; then
+      unpushed="$(git -C "$dir" log "$upstream..$branch" --oneline 2>/dev/null)"
+      if [ -n "$unpushed" ]; then
+        skipped=$((skipped + 1))
+        continue
+      fi
+    fi
+  fi
+
+  rm -rf "$dir" 2>/dev/null && cleaned=$((cleaned + 1))
+done
+
+# Silent unless something was cleaned
+if [ "$cleaned" -gt 0 ]; then
+  echo "Cleaned $cleaned stale worktree(s), $skipped active/protected"
+fi
+`;
+}

package/src/templates/setup-script.ts

@@ -53,11 +53,18 @@ if [ ! -f "$SETTINGS_FILE" ]; then
         "type": "prompt",
         "prompt": "Before context is compacted, capture a session summary by calling ${config.id}_core op:session_capture with a brief summary of what was accomplished, the topics covered, files modified, and tools used."
       }
+    ],
+    "SessionStart": [
+      {
+        "type": "command",
+        "command": "sh $AGENT_DIR/scripts/clean-worktrees.sh",
+        "timeout": 10
+      }
     ]
   }
 }
 SETTINGS
-  echo "[ok] Created $SETTINGS_FILE with PreCompact hook"
+  echo "[ok] Created $SETTINGS_FILE with PreCompact + SessionStart hooks"
 else
   if grep -q "PreCompact" "$SETTINGS_FILE" 2>/dev/null; then
     echo "[ok] PreCompact hook already configured — skipping"
@@ -75,6 +82,24 @@ else
     "
     echo "[ok] Added PreCompact hook to $SETTINGS_FILE"
   fi
+  # Add SessionStart worktree cleanup hook
+  if grep -q "clean-worktrees" "$SETTINGS_FILE" 2>/dev/null; then
+    echo "[ok] SessionStart worktree cleanup hook already configured"
+  else
+    node -e "
+      const fs = require('fs');
+      const settings = JSON.parse(fs.readFileSync('$SETTINGS_FILE', 'utf-8'));
+      if (!settings.hooks) settings.hooks = {};
+      if (!settings.hooks.SessionStart) settings.hooks.SessionStart = [];
+      settings.hooks.SessionStart.push({
+        type: 'command',
+        command: 'sh $AGENT_DIR/scripts/clean-worktrees.sh',
+        timeout: 10
+      });
+      fs.writeFileSync('$SETTINGS_FILE', JSON.stringify(settings, null, 2) + '\\n');
+    "
+    echo "[ok] Added SessionStart worktree cleanup hook"
+  fi
 fi
 
 # Install skills to ~/.claude/commands/

package/src/templates/shared-rules.ts

@@ -114,6 +114,19 @@ const ENGINE_RULES_LINES: string[] = [
   '- Persist lessons: capture + link. An unlinked entry is incomplete.',
   '- Exceptions: runtime errors with stack traces → codebase first; user explicitly asks to search web.',
   '',
+  '### Vault Search Strategy',
+  '',
+  "Default to **two-pass search** — scan first, load only what's relevant. This saves tokens and keeps context lean.",
+  '',
+  '| Situation | Strategy |',
+  '|-----------|----------|',
+  '| Broad/exploratory query | `mode: "scan"` → triage by score → `op:load_entries` for top matches |',
+  '| Specific known entry | `mode: "full"` directly |',
+  '| Work task (need vault context before coding) | Scan → pick relevant → load |',
+  '| Existence check ("do we have X?") | `mode: "scan"` only, no load needed |',
+  '',
+  '**Never load all scan results.** Pick the top 2-4 by relevance score and skip entries below 0.30 unless the query is very specific.',
+  '',
 
   // ─── Planning ────────────────────────────────────────────
   '## Planning',
@@ -210,6 +223,38 @@ const ENGINE_RULES_LINES: string[] = [
   '```',
   '',
 
+  // ─── YOLO Mode ──────────────────────────────────────────
+  '## YOLO Mode',
+  '<!-- soleri:yolo-mode -->',
+  '',
+  'YOLO mode skips plan approval gates for faster execution. The agent executes tasks directly without waiting for Gate 1 (`op:approve_plan`) or Gate 2 (`op:plan_split`) confirmation.',
+  '',
+  '### What Changes',
+  '',
+  '- Plan approval gates are **auto-approved** — no user confirmation needed.',
+  '- Task routing skips the two-gate ceremony — plans are created, approved, and split in one pass.',
+  '',
+  '### What Does NOT Change',
+  '',
+  '- `op:orchestrate_complete` **always runs** — knowledge capture is never skipped.',
+  '- Vault search **always runs** — decisions must be informed by existing patterns.',
+  '- Brain feedback loop remains active.',
+  '- Grade gate still applies — plans must grade A or higher.',
+  '',
+  '### Prerequisites',
+  '',
+  '- **YOLO Safety Hook Pack** must be installed: `soleri hooks add-pack yolo-safety`',
+  '- The hook pack intercepts destructive commands (force push, reset --hard, drop table) and requires explicit confirmation.',
+  '- Staging backups are created before destructive operations.',
+  '',
+  '### Activation & Deactivation',
+  '',
+  '| Action | Method |',
+  '|--------|--------|',
+  '| Activate | `soleri yolo` or `op:morph params:{ mode: "YOLO-MODE" }` |',
+  '| Deactivate | "exit YOLO", session end, or `op:activate params:{ deactivate: true }` |',
+  '',
+
   // ─── Output Formatting ───────────────────────────────────
   '## Output Formatting',
   '<!-- soleri:output-formatting -->',
@@ -299,7 +344,7 @@ const ENGINE_RULES_LINES: string[] = [
   '`op:orchestrate_complete` runs for EVERY task — simple or complex. This captures:',
   '- Knowledge to vault (patterns learned, decisions made)',
   '- Session summary (what was done, files changed)',
-  '- Brain feedback (what worked, what didn\'t)',
+  "- Brain feedback (what worked, what didn't)",
   '',
   'Without completion, the knowledge trail is lost. The code is in git, but the WHY disappears.',
   '',
@@ -350,6 +395,54 @@ const ENGINE_RULES_LINES: string[] = [
   '- Brain tells you **which** patterns matter (names + strength scores). Vault tells you **what** they are (rules, examples).',
   "- Pull only what's relevant to the current task — don't load everything at session start.",
   '',
+  '### Second Brain Features',
+  '',
+  '| Feature | How to use |',
+  '|---------|-----------|',
+  '| **Two-pass search** | `op:search_intelligent` with `mode: "scan"` for lightweight results, then `op:load_entries` for full content. See **Vault Search Strategy**. |',
+  '| **Session briefing** | `op:session_briefing` on session start — surfaces last session, active plans, recent captures, brain recommendations |',
+  '| **Evidence reconciliation** | `op:plan_reconcile_with_evidence` — cross-references plan tasks against git diff |',
+  '| **Learning radar** | `op:radar_analyze` to detect patterns from corrections, search misses, workarounds. `op:radar_candidates` to review, `op:radar_approve`/`op:radar_dismiss` |',
+  '| **External ingestion** | `op:ingest_url` for articles, `op:ingest_text` for transcripts/notes, `op:ingest_batch` for multiple items |',
+  '| **Content synthesis** | `op:synthesize` — turn vault knowledge into briefs, outlines, talking points, or post drafts |',
+  '| **Skill chains** | `op:chain_execute` — multi-step workflows with data flow between steps and approval gates |',
+  '',
+  '### Brain Feedback Loop',
+  '',
+  'After using a vault search result to inform a decision, action, or response, call `op:record_feedback` with:',
+  '- `query`: the original search query',
+  '- `entryId`: the vault entry ID that was used',
+  '- `action`: "accepted" (result was useful) or "rejected" (result was irrelevant/wrong)',
+  '- `confidence`: 0.0–1.0 how relevant the result was to the task',
+  '',
+  'Do this for:',
+  '- `search_intelligent` results that influence your next action',
+  '- `orchestrate_plan` vault recommendations you follow',
+  '- Vault entries you cite or reference in responses',
+  '',
+  'Do NOT record feedback for:',
+  '- Existence checks ("do we have X?" — just scanning, not using)',
+  "- Results you browse but don't act on",
+  '- Duplicate feedback for the same entry in the same task',
+  '',
+
+  // ─── Model Routing Guidance ─────────────────────────────
+  '## Model Routing Guidance',
+  '<!-- soleri:model-routing -->',
+  '',
+  'Different workflow stages benefit from different model strengths. Use this as a default when multiple models are available.',
+  '',
+  '| Stage | Recommended Model | Why |',
+  '|-------|------------------|-----|',
+  '| Research / Exploration | Opus | Cross-file reasoning, broad context synthesis |',
+  '| Planning / Architecture | Opus | Complex tradeoff analysis, alternative evaluation |',
+  '| Implementation | Sonnet | Speed, cost-efficiency for focused coding |',
+  '| Code Review / Verification | Opus | Deep analysis, false-positive filtering |',
+  '| Validation Gates | Haiku | Fast, cheap pass/fail checks |',
+  '| Knowledge Capture | Sonnet | Structured extraction, good enough quality |',
+  '',
+  'This is guidance, not enforcement. Use the best model available. When only one model is available, use it for all stages.',
+  '',
 
   // ─── Cross-Project Memory ────────────────────────────────
   '## Cross-Project Memory',
@@ -416,11 +509,27 @@ const ENGINE_RULES_LINES: string[] = [
   '',
   '### Character Persistence',
   '',
-  '- All communication flows through your persona\'s voice — tone, vocabulary, opinions',
+  '- **MANDATORY**: Prefix every response with `{AgentName} >` when activated (e.g., `Ernesto >`, `Salvador >`). This signals to the user that the agent persona is active.',
+  "- All communication flows through your persona's voice — tone, vocabulary, opinions",
   '- Stay in character until explicitly deactivated',
   '- Context compaction does not change who you are — these rules persist in CLAUDE.md',
   '- If you notice yourself dropping character, re-read your activation context',
   '',
+  '### Operator Learning (automatic, silent)',
+  'When calling `op:orchestrate_complete`, fill the `operatorSignals` field with your observations from this session:',
+  '',
+  '- **Expertise**: which topics did the operator demonstrate knowledge in? Where did they need explanation? Report topic + level (learning/intermediate/expert).',
+  "- **Corrections**: did they tell you to change behavior? Quote their exact words. Note if it's global or project-specific.",
+  '- **Interests**: did they share anything personal? Hobbies, background, music, culture? Report the tag and context.',
+  '- **Patterns**: did you notice work habits? Batching, scoping, pacing, communication style? Report what you observed.',
+  '',
+  'Rules:',
+  "- Fill what you observed. Empty arrays for what you didn't notice.",
+  '- Store facts, not assumptions. "User asked about React hooks" not "User doesn\'t know React."',
+  '- Never announce you are learning. Never ask for confirmation.',
+  '- Decline to store: health, medical, political, religious, sexual, financial, legal content.',
+  '- The engine handles compounding and persistence — just report honestly.',
+  '',
   '### What NOT to Route Through Tools',
   '',
   '- Pure file read/write/edit operations (use Read, Edit, Write tools directly)',
@@ -436,8 +545,8 @@ const ENGINE_RULES_LINES: string[] = [
   '',
   '### Session Start Protocol',
   '',
-  'On activation, discover capabilities via `op:admin_tool_list`. Call `op:register` when project context is needed for a task.',
-  'Call `op:activate` only when checking evolved capabilities or recovering session state.',
+  'On activation, discover capabilities via `op:admin_tool_list`. Call `op:session_briefing` to surface last session context, active plans, and brain recommendations.',
+  'Call `op:register` when project context is needed for a task. Call `op:activate` only when checking evolved capabilities or recovering session state.',
   'After context compaction, re-discover capabilities — do not assume your tool inventory is still cached.',
   '',
   '### Context Compaction',
@@ -445,6 +554,21 @@ const ENGINE_RULES_LINES: string[] = [
   'A PreCompact hook calls `op:session_capture` before context compaction.',
   'Manual capture: `op:session_capture params:{ summary: "..." }`',
   '',
+  '### Handoff Protocol',
+  '',
+  'Before crossing a context window boundary (`/clear`, context compaction, or switching tasks), generate a handoff document:',
+  '',
+  '1. **Before transition**: `op:handoff_generate` — produces a structured markdown document with active plan state, recent decisions, and pending tasks.',
+  '2. **After restart**: Reference the handoff document to restore context. It contains plan IDs, task status, decisions, and next actions.',
+  '',
+  'Handoff documents are **ephemeral** — they are returned as markdown, not persisted to vault or memory. They are a snapshot for context transfer only.',
+  '',
+  '| Trigger | Action |',
+  '|---------|--------|',
+  '| `/clear` or manual reset | `op:handoff_generate` before clearing |',
+  '| Context compaction warning | `op:handoff_generate` (alongside `op:session_capture`) |',
+  '| Switching to a different task mid-plan | `op:handoff_generate` to bookmark state |',
+  '',
 
   // ─── Soleri CLI ─────────────────────────────────────────
   '## Soleri CLI',
@@ -516,6 +640,39 @@ const ENGINE_RULES_LINES: string[] = [
   '| Template drift suspected | `soleri agent diff` to see what changed |',
   '',
 
+  // ─── Persona Self-Update ────────────────────────────────────
+  '## Persona Self-Update',
+  '<!-- soleri:persona-self-update -->',
+  '',
+  'When the user asks to change your personality, voice, quirks, or character:',
+  '',
+  '1. **Edit your own `agent.yaml`** — the `persona:` block is the source of truth for your character.',
+  '2. **NEVER modify Soleri engine code** — `@soleri/core`, `packages/core/src/persona/defaults.ts`, or any engine package. Those define the default template for ALL agents.',
+  '3. After editing `agent.yaml`, tell the user to run `soleri agent refresh` to regenerate CLAUDE.md, then reactivate.',
+  '',
+  '### What You Can Change',
+  '',
+  '| Field | Purpose |',
+  '|-------|---------|',
+  '| `persona.template` | Template ID (informational, can be custom) |',
+  '| `persona.inspiration` | Who/what inspires the character |',
+  '| `persona.culture` | Cultural background |',
+  '| `persona.voice` | How you sound (tone, cadence, vocabulary) |',
+  '| `persona.traits` | Personality traits |',
+  '| `persona.quirks` | Memorable behaviors and expressions |',
+  '| `persona.opinions` | Beliefs about craft and quality |',
+  '| `persona.metaphors` | Domains you draw metaphors from |',
+  '| `persona.languageRule` | How you mix languages |',
+  '| `persona.greetings` | Session start messages |',
+  '| `persona.signoffs` | Session end messages |',
+  '',
+  '### What You Must NOT Change',
+  '',
+  '- Engine defaults in `packages/core/src/persona/defaults.ts`',
+  '- The `PERSONA_TEMPLATES` registry',
+  '- Any file inside `@soleri/core` or `@soleri/forge`',
+  '',
+
   // ─── Verification Protocol ─────────────────────────────────
   '## Verification Protocol',
   '<!-- soleri:verification-protocol -->',
@@ -528,11 +685,12 @@ const ENGINE_RULES_LINES: string[] = [
   '2. **Prove** — reproduce the issue (test case, error log, stack trace)',
   '3. **Fix** — only after the issue is proven reproducible',
   '',
-  '### Anti-pattern',
+  '### Anti-patterns',
   '',
   '- Fixing code "just in case" or for aesthetics without a proven issue',
   '- Claiming a bug exists without reproduction evidence',
   '- Refactoring working code under the guise of a bug fix',
+  '- **Dismissing test failures as "flaky" or "pre-existing" without reading the test code and the handler it exercises.** A test that fails consistently is broken, not flaky. Investigate the root cause before classifying.',
   '',
   '### Scope',
   '',

package/src/templates/skills.ts

@@ -6,34 +6,8 @@ import type { AgentConfig } from '../types.js';
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const SKILLS_DIR = join(__dirname, '..', 'skills');
 
-/** Skills that use YOUR_AGENT_core placeholder and need agent-specific substitution. */
-const AGENT_SPECIFIC_SKILLS = new Set([
-  'agent-dev',
-  'agent-guide',
-  'agent-persona',
-  'brain-debrief',
-  'brainstorming',
-  'code-patrol',
-  'context-resume',
-  'deep-review',
-  'deliver-and-ship',
-  'executing-plans',
-  'fix-and-learn',
-  'health-check',
-  'knowledge-harvest',
-  'onboard-me',
-  'parallel-execute',
-  'retrospective',
-  'second-opinion',
-  'systematic-debugging',
-  'test-driven-development',
-  'vault-capture',
-  'vault-curate',
-  'vault-navigator',
-  'vault-smells',
-  'verification-before-completion',
-  'writing-plans',
-]);
+/** Placeholder token in skill templates that gets replaced with agent-specific tool name. */
+const AGENT_PLACEHOLDER = 'YOUR_AGENT_core';
 
 /**
  * Generate skill files for the scaffolded agent.
@@ -85,7 +59,7 @@ export function generateSkills(config: AgentConfig): Array<[string, string]> {
 
     let content = readFileSync(contentPath, 'utf-8');
 
-    if (AGENT_SPECIFIC_SKILLS.has(skillName)) {
+    if (content.includes(AGENT_PLACEHOLDER)) {
       content = content.replace(/YOUR_AGENT_core/g, `${config.id}_core`);
     }
 

package/src/templates/vitest-config.ts

@@ -15,6 +15,7 @@ export default defineConfig({
     testTimeout: 30_000,
     hookTimeout: 10_000,
     teardownTimeout: 5_000,
+    exclude: ['**/node_modules/**', '**/.claude/worktrees/**'],
     coverage: {
       provider: 'v8',
       include: ['src/**/*.ts'],

package/vitest.config.ts

@@ -5,6 +5,7 @@ export default defineConfig({
     environment: 'node',
     pool: 'threads',
     testTimeout: 30_000,
+    exclude: ['**/node_modules/**', '**/.claude/worktrees/**'],
     coverage: {
       provider: 'v8',
       include: ['src/**/*.ts'],