opencode-multiagent 0.2.0 → 0.3.0-next.1

package/skills/debate/SKILL.md

@@ -2,7 +2,7 @@
 name: debate
 description: "Structured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 'stress test idea', 'devil advocate'."
 version: 5.1.0
-argument-hint: "[topic] [--proposer=tool] [--challenger=tool] [--rounds=N] [--effort=level]"
+argument-hint: '[topic] [--proposer=tool] [--challenger=tool] [--rounds=N] [--effort=level]'
 ---
 
 # debate
@@ -12,6 +12,7 @@ Prompt templates, context assembly rules, and synthesis format for structured mu
 ## Arguments
 
 Parse from `$ARGUMENTS`:
+
 - **topic**: The debate question/topic (required)
 - **--proposer**: Tool for the proposer role (claude, gemini, codex, opencode, copilot)
 - **--challenger**: Tool for the challenger role (must differ from proposer)
@@ -130,6 +131,7 @@ Provide your follow-up:
 Include the full text of all prior exchanges in the prompt. Context is small enough (typically under 5000 tokens total).
 
 Format for context block:
+
 ```
 Previous exchanges:
 
@@ -145,6 +147,7 @@ Round 1 - Challenger ({challenger_tool}):
 For rounds 3 and beyond, replace full exchange text from rounds 1 through N-2 with a summary. Only include the most recent round's responses in full.
 
 Format:
+
 ```
 Summary of rounds 1-{N-2}:
 {summary of key positions, agreements, and open disagreements}
@@ -157,6 +160,7 @@ Round {N-1} - Challenger ({challenger_tool}):
 ```
 
 The orchestrator agent (opus) generates the summary. Target: 500-800 tokens. MUST preserve:
+
 - Each side's core position
 - All concessions (verbatim quotes, not paraphrased)
 - All evidence citations that support agreements
@@ -202,6 +206,7 @@ Rate the debate on these dimensions:
 ```
 
 **Synthesis rules:**
+
 - The verdict MUST pick a side. "Both approaches have merit" is NOT acceptable.
 - Cite specific arguments from the debate as evidence for the verdict.
 - The recommendation must be actionable - what should the user DO based on this debate.
@@ -215,17 +220,17 @@ Save to `{AI_STATE_DIR}/debate/last-debate.json`:
 {
   "id": "debate-{ISO timestamp}-{4 char random hex}",
   "topic": "original topic text",
-  "proposer": {"tool": "claude", "model": "opus"},
-  "challenger": {"tool": "gemini", "model": "gemini-3.1-pro-preview"},
+  "proposer": { "tool": "claude", "model": "opus" },
+  "challenger": { "tool": "gemini", "model": "gemini-3.1-pro-preview" },
   "effort": "high",
   "rounds_completed": 2,
   "max_rounds": 2,
   "status": "completed",
   "exchanges": [
-    {"round": 1, "role": "proposer", "tool": "claude", "response": "...", "duration_ms": 8500},
-    {"round": 1, "role": "challenger", "tool": "gemini", "response": "...", "duration_ms": 12000},
-    {"round": 2, "role": "proposer", "tool": "claude", "response": "...", "duration_ms": 9200},
-    {"round": 2, "role": "challenger", "tool": "gemini", "response": "...", "duration_ms": 11000}
+    { "round": 1, "role": "proposer", "tool": "claude", "response": "...", "duration_ms": 8500 },
+    { "round": 1, "role": "challenger", "tool": "gemini", "response": "...", "duration_ms": 12000 },
+    { "round": 2, "role": "proposer", "tool": "claude", "response": "...", "duration_ms": 9200 },
+    { "round": 2, "role": "challenger", "tool": "gemini", "response": "...", "duration_ms": 11000 }
   ],
   "verdict": {
     "winner": "claude",
@@ -238,79 +243,19 @@ Save to `{AI_STATE_DIR}/debate/last-debate.json`:
 }
 ```
 
-Platform state directory:
-- Claude Code: `.claude/`
-- OpenCode: `.opencode/`
-- Codex CLI: `.codex/`
+Platform state directory: `.opencode/`
 
 ## Error Handling
 
-| Error | Action |
-|-------|--------|
-| Proposer fails round 1 | Abort debate. Cannot proceed without opening position. |
-| Challenger fails round 1 | Show proposer's position with note: "[WARN] Challenger failed. Showing proposer's uncontested position." |
-| Any tool fails mid-debate | Synthesize from completed rounds. Note incomplete round in output. |
-| Tool invocation timeout (>240s) | Round 1 proposer: abort. Round 1 challenger: proceed with uncontested. Round 2+: synthesize from completed rounds with timeout note. |
-| Consult result envelope indicates failure (status/exit/error/empty output) | Treat as tool failure for that role/round and apply the same role+round policy above. |
-| Structured parse fails after successful envelope | Treat as tool failure for that role/round, include only sanitized parse metadata (`PARSE_ERROR:<type>:<code>`, redact secrets, strip control chars, max 200 chars), then apply the same role+round policy above. |
-| All rounds timeout | "[ERROR] Debate failed: all tool invocations timed out." |
-| No successful exchanges recorded (non-timeout) | "[ERROR] Debate failed: no successful exchanges were recorded." |
-
-## External Tool Quick Reference
-
-> Canonical source: `plugins/consult/skills/consult/SKILL.md`. Build and execute CLI commands directly using these templates. Do NOT invoke via `Skill: consult` - in Claude Code that loads the interactive command wrapper and causes a recursive loop. Write the question to `{AI_STATE_DIR}/consult/question.tmp` first, then execute the command via Bash.
-
-### Safe Command Patterns
-
-| Provider | Safe Command Pattern |
-|----------|---------------------|
-| Claude | `claude -p - --output-format json --model "MODEL" --max-turns TURNS --allowedTools "Read,Glob,Grep" < "{AI_STATE_DIR}/consult/question.tmp"` |
-| Gemini | `gemini -p - --output-format json -m "MODEL" < "{AI_STATE_DIR}/consult/question.tmp"` |
-| Codex | `codex exec "$(cat "{AI_STATE_DIR}/consult/question.tmp")" --json -m "MODEL" -c model_reasoning_effort="LEVEL"` |
-| OpenCode | `opencode run - --format json --model "MODEL" --variant "VARIANT" < "{AI_STATE_DIR}/consult/question.tmp"` |
-| Copilot | `copilot -p - < "{AI_STATE_DIR}/consult/question.tmp"` |
-
-### Effort-to-Model Mapping
-
-| Effort | Claude | Gemini | Codex | OpenCode | Copilot |
-|--------|--------|--------|-------|----------|---------|
-| low | claude-haiku-4-5 (1 turn) | gemini-3-flash-preview | gpt-5.3-codex (low) | default (low) | no control |
-| medium | claude-sonnet-4-6 (3 turns) | gemini-3-flash-preview | gpt-5.3-codex (medium) | default (medium) | no control |
-| high | claude-opus-4-6 (5 turns) | gemini-3.1-pro-preview | gpt-5.3-codex (high) | default (high) | no control |
-| max | claude-opus-4-6 (10 turns) | gemini-3.1-pro-preview | gpt-5.3-codex (high) | default + --thinking | no control |
-
-### Output Parsing
-
-| Provider | Parse Expression |
-|----------|-----------------|
-| Claude | `JSON.parse(stdout).result` |
-| Gemini | `JSON.parse(stdout).response` |
-| Codex | `JSON.parse(stdout).message` or raw text |
-| OpenCode | Newline-delimited JSON. Concatenate `part.text` from events where `type === "text"`. Session ID from `event.sessionID`. |
-| Copilot | Raw stdout text |
-
-Parse discipline:
-1. Evaluate execution status first (timeout/non-zero/error/empty output) before any parsing.
-2. Parse only when execution status is successful.
-3. If parse fails, surface only sanitized parse metadata (never raw stdout/stderr snippets) and apply role/round failure policy instead of hanging or continuing silently.
-
-### ACP Transport Commands
-
-> ACP is an alternative transport available when providers support it. Build and execute CLI commands directly - do NOT use `Skill: consult` (recursive loop in Claude Code).
-
-| Provider | ACP Command Pattern |
-|----------|-------------------|
-| Claude | `node acp/run.js --provider="claude" --question-file="{AI_STATE_DIR}/consult/question.tmp" --timeout=240000 --model="MODEL"` |
-| Gemini | `node acp/run.js --provider="gemini" --question-file="{AI_STATE_DIR}/consult/question.tmp" --timeout=240000 --model="MODEL"` |
-| Codex | `node acp/run.js --provider="codex" --question-file="{AI_STATE_DIR}/consult/question.tmp" --timeout=240000 --model="MODEL"` |
-| OpenCode | `node acp/run.js --provider="opencode" --question-file="{AI_STATE_DIR}/consult/question.tmp" --timeout=240000 --model="MODEL"` |
-| Copilot | `node acp/run.js --provider="copilot" --question-file="{AI_STATE_DIR}/consult/question.tmp" --timeout=240000` |
-| Kiro | `node acp/run.js --provider="kiro" --question-file="{AI_STATE_DIR}/consult/question.tmp" --timeout=240000` |
-
-Note the 240000ms timeout (240s) for debate rounds vs 120000ms (120s) for consult.
-
-**Kiro**: ACP-only provider. No CLI mode. Available when `kiro-cli` is on PATH.
+| Error                                                                      | Action                                                                                                                                                                                                           |
+| -------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Proposer fails round 1                                                     | Abort debate. Cannot proceed without opening position.                                                                                                                                                           |
+| Challenger fails round 1                                                   | Show proposer's position with note: "[WARN] Challenger failed. Showing proposer's uncontested position."                                                                                                         |
+| Any tool fails mid-debate                                                  | Synthesize from completed rounds. Note incomplete round in output.                                                                                                                                               |
+| Tool invocation timeout (>240s)                                            | Round 1 proposer: abort. Round 1 challenger: proceed with uncontested. Round 2+: synthesize from completed rounds with timeout note.                                                                             |
+| Consult result envelope indicates failure (status/exit/error/empty output) | Treat as tool failure for that role/round and apply the same role+round policy above.                                                                                                                            |
+| Structured parse fails after successful envelope                           | Treat as tool failure for that role/round, include only sanitized parse metadata (`PARSE_ERROR:<type>:<code>`, redact secrets, strip control chars, max 200 chars), then apply the same role+round policy above. |
+| All rounds timeout                                                         | "[ERROR] Debate failed: all tool invocations timed out."                                                                                                                                                         |
+| No successful exchanges recorded (non-timeout)                             | "[ERROR] Debate failed: no successful exchanges were recorded."                                                                                                                                                  |
 
-### ACP Output Parsing
 
-ACP transport output is parsed identically to CLI transport - the ACP runner (`acp/run.js`) normalizes responses into the same JSON envelope format. The `transport` field in the envelope indicates `"acp"` or `"cli"`.

package/skills/debate/manifest.json

@@ -2,18 +2,8 @@
   "name": "debate",
   "version": "1.0.0",
   "description": "Structured debate templates for stress-testing positions and solutions",
-  "triggers": [
-    "debate",
-    "argue",
-    "stress test",
-    "devils advocate",
-    "counter argument"
-  ],
-  "applicable_agents": [
-    "critic",
-    "strategist",
-    "librarian"
-  ],
+  "triggers": ["debate", "argue", "stress test", "devils advocate", "counter argument"],
+  "applicable_agents": ["critic", "strategist", "librarian"],
   "max_context_tokens": 2200,
   "entry_file": "SKILL.md"
 }

package/skills/design-first/manifest.json

@@ -2,19 +2,8 @@
   "name": "design-first",
   "version": "1.0.0",
   "description": "Design the approach before implementation starts",
-  "triggers": [
-    "design",
-    "architecture",
-    "plan",
-    "schema",
-    "api",
-    "interface"
-  ],
-  "applicable_agents": [
-    "planner",
-    "worker",
-    "heavy-worker"
-  ],
+  "triggers": ["design", "architecture", "plan", "schema", "api", "interface"],
+  "applicable_agents": ["planner", "strategist", "heavy-worker", "deep-worker", "advisor"],
   "max_context_tokens": 1500,
   "entry_file": "SKILL.md"
 }

package/skills/dispatching-parallel-agents/SKILL.md

@@ -32,12 +32,14 @@ digraph when_to_use {
 ```
 
 **Use when:**
+
 - 3+ test files failing with different root causes
 - Multiple subsystems broken independently
 - Each problem can be understood without context from others
 - No shared state between investigations
 
 **Don't use when:**
+
 - Failures are related (fix one might fix others)
 - Need to understand full system state
 - Agents would interfere with each other
@@ -47,6 +49,7 @@ digraph when_to_use {
 ### 1. Identify Independent Domains
 
 Group failures by what's broken:
+
 - File A tests: Tool approval flow
 - File B tests: Batch completion behavior
 - File C tests: Abort functionality
@@ -56,6 +59,7 @@ Each domain is independent - fixing tool approval doesn't affect abort tests.
 ### 2. Create Focused Agent Tasks
 
 Each agent gets:
+
 - **Specific scope:** One test file or subsystem
 - **Clear goal:** Make these tests pass
 - **Constraints:** Don't change other code
@@ -65,15 +69,16 @@ Each agent gets:
 
 ```typescript
 // In Claude Code / AI environment
-Task("Fix agent-tool-abort.test.ts failures")
-Task("Fix batch-completion-behavior.test.ts failures")
-Task("Fix tool-approval-race-conditions.test.ts failures")
+Task('Fix agent-tool-abort.test.ts failures');
+Task('Fix batch-completion-behavior.test.ts failures');
+Task('Fix tool-approval-race-conditions.test.ts failures');
 // All three run concurrently
 ```
 
 ### 4. Review and Integrate
 
 When agents return:
+
 - Read each summary
 - Verify fixes don't conflict
 - Run full test suite
@@ -82,6 +87,7 @@ When agents return:
 ## Agent Prompt Structure
 
 Good agent prompts are:
+
 1. **Focused** - One clear problem domain
 2. **Self-contained** - All context needed to understand the problem
 3. **Specific about output** - What should the agent return?
@@ -133,6 +139,7 @@ Return: Summary of what you found and what you fixed.
 **Scenario:** 6 test failures across 3 files after major refactoring
 
 **Failures:**
+
 - agent-tool-abort.test.ts: 3 failures (timing issues)
 - batch-completion-behavior.test.ts: 2 failures (tools not executing)
 - tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)
@@ -140,6 +147,7 @@ Return: Summary of what you found and what you fixed.
 **Decision:** Independent domains - abort logic separate from batch completion separate from race conditions
 
 **Dispatch:**
+
 ```
 Agent 1 → Fix agent-tool-abort.test.ts
 Agent 2 → Fix batch-completion-behavior.test.ts
@@ -147,6 +155,7 @@ Agent 3 → Fix tool-approval-race-conditions.test.ts
 ```
 
 **Results:**
+
 - Agent 1: Replaced timeouts with event-based waiting
 - Agent 2: Fixed event structure bug (threadId in wrong place)
 - Agent 3: Added wait for async tool execution to complete
@@ -165,6 +174,7 @@ Agent 3 → Fix tool-approval-race-conditions.test.ts
 ## Verification
 
 After agents return:
+
 1. **Review each summary** - Understand what changed
 2. **Check for conflicts** - Did agents edit same code?
 3. **Run full suite** - Verify all fixes work together
@@ -173,6 +183,7 @@ After agents return:
 ## Real-World Impact
 
 From debugging session (2025-10-03):
+
 - 6 failures across 3 files
 - 3 agents dispatched in parallel
 - All investigations completed concurrently

package/skills/dispatching-parallel-agents/manifest.json

@@ -9,10 +9,7 @@
     "independent subtasks",
     "parallelize"
   ],
-  "applicable_agents": [
-    "critic",
-    "strategist"
-  ],
+  "applicable_agents": ["critic", "strategist"],
   "max_context_tokens": 1800,
   "entry_file": "SKILL.md"
 }

package/skills/drift-analysis/SKILL.md

@@ -30,21 +30,25 @@ Knowledge and patterns for analyzing project state, detecting plan drift, and cr
 ### Types of Drift
 
 **Plan Drift**: When documented plans diverge from actual implementation
+
 - PLAN.md items remain unchecked for extended periods
 - Roadmap milestones slip without updates
 - Sprint/phase goals not reflected in code changes
 
 **Documentation Drift**: When documentation falls behind implementation
+
 - New features exist without corresponding docs
 - README describes features that don't exist
 - API docs don't match actual endpoints
 
 **Issue Drift**: When issue tracking diverges from reality
+
 - Stale issues that no longer apply
 - Completed work without closed issues
 - High-priority items neglected
 
 **Scope Drift**: When project scope expands beyond original plans
+
 - More features documented than can be delivered
 - Continuous addition without completion
 - Ever-growing backlog with no pruning
@@ -83,17 +87,17 @@ function calculatePriority(item, weights) {
     critical: 15,
     high: 10,
     medium: 5,
-    low: 2
+    low: 2,
   };
   score += severityScores[item.severity] || 5;
 
   // Category multiplier
   const categoryWeights = {
-    security: 2.0,    // Security issues get 2x
-    bugs: 1.5,        // Bugs get 1.5x
+    security: 2.0, // Security issues get 2x
+    bugs: 1.5, // Bugs get 1.5x
     infrastructure: 1.3,
     features: 1.0,
-    documentation: 0.8
+    documentation: 0.8,
   };
   score *= categoryWeights[item.category] || 1.0;
 
@@ -109,21 +113,21 @@ function calculatePriority(item, weights) {
 
 ### Time Bucket Thresholds
 
-| Bucket | Criteria | Max Items |
-|--------|----------|-----------|
-| Immediate | severity=critical OR priority >= 15 | 5 |
-| Short-term | severity=high OR priority >= 10 | 10 |
-| Medium-term | priority >= 5 | 15 |
-| Backlog | everything else | 20 |
+| Bucket      | Criteria                            | Max Items |
+| ----------- | ----------------------------------- | --------- |
+| Immediate   | severity=critical OR priority >= 15 | 5         |
+| Short-term  | severity=high OR priority >= 10     | 10        |
+| Medium-term | priority >= 5                       | 15        |
+| Backlog     | everything else                     | 20        |
 
 ### Priority Weights (Default)
 
 ```yaml
-security: 10     # Security issues always top priority
-bugs: 8          # Bugs affect users directly
-features: 5      # New functionality
+security: 10 # Security issues always top priority
+bugs: 8 # Bugs affect users directly
+features: 5 # New functionality
 documentation: 3 # Important but not urgent
-tech-debt: 4     # Keeps codebase healthy
+tech-debt: 4 # Keeps codebase healthy
 ```
 
 ## Cross-Reference Patterns
@@ -133,29 +137,32 @@ tech-debt: 4     # Keeps codebase healthy
 ```javascript
 // Fuzzy matching for feature names
 function featureMatch(docFeature, codeFeature) {
-  const normalize = s => s
-    .toLowerCase()
-    .replace(/[-_\s]+/g, '')
-    .replace(/s$/, ''); // Remove trailing 's'
+  const normalize = (s) =>
+    s
+      .toLowerCase()
+      .replace(/[-_\s]+/g, '')
+      .replace(/s$/, ''); // Remove trailing 's'
 
   const docNorm = normalize(docFeature);
   const codeNorm = normalize(codeFeature);
 
-  return docNorm.includes(codeNorm) ||
-         codeNorm.includes(docNorm) ||
-         levenshteinDistance(docNorm, codeNorm) < 3;
+  return (
+    docNorm.includes(codeNorm) ||
+    codeNorm.includes(docNorm) ||
+    levenshteinDistance(docNorm, codeNorm) < 3
+  );
 }
 ```
 
 ### Common Mismatches
 
-| Documented As | Implemented As |
-|---------------|----------------|
-| "user authentication" | auth/, login/, session/ |
-| "API endpoints" | routes/, api/, handlers/ |
-| "database models" | models/, entities/, schemas/ |
-| "caching layer" | cache/, redis/, memcache/ |
-| "logging system" | logger/, logs/, telemetry/ |
+| Documented As         | Implemented As               |
+| --------------------- | ---------------------------- |
+| "user authentication" | auth/, login/, session/      |
+| "API endpoints"       | routes/, api/, handlers/     |
+| "database models"     | models/, entities/, schemas/ |
+| "caching layer"       | cache/, redis/, memcache/    |
+| "logging system"      | logger/, logs/, telemetry/   |
 
 ## Output Templates
 
@@ -165,6 +172,7 @@ function featureMatch(docFeature, codeFeature) {
 ## Drift Analysis
 
 ### {drift_type}
+
 **Severity**: {severity}
 **Detected In**: {source}
 
@@ -189,6 +197,7 @@ function featureMatch(docFeature, codeFeature) {
 **Impact**: {impact_description}
 
 **To Address**:
+
 1. {action_item_1}
 2. {action_item_2}
 ```
@@ -199,15 +208,19 @@ function featureMatch(docFeature, codeFeature) {
 ## Reconstruction Plan
 
 ### Immediate Actions (This Week)
+
 {immediate_items_numbered}
 
 ### Short-Term (This Month)
+
 {short_term_items_numbered}
 
 ### Medium-Term (This Quarter)
+
 {medium_term_items_numbered}
 
 ### Backlog
+
 {backlog_items_numbered}
 ```
 
@@ -253,6 +266,7 @@ function featureMatch(docFeature, codeFeature) {
 The collectors.js module extracts data without LLM overhead:
 
 ### GitHub Data
+
 - Open issues categorized by labels
 - Open PRs with draft status
 - Milestones with due dates
@@ -260,12 +274,14 @@ The collectors.js module extracts data without LLM overhead:
 - Theme analysis from titles
 
 ### Documentation Data
-- Parsed README, PLAN.md, CLAUDE.md, CHANGELOG.md
+
+- Parsed README, PLAN.md, AGENTS.md, CHANGELOG.md
 - Checkbox completion counts
 - Section analysis
 - Feature lists
 
 ### Code Data
+
 - Directory structure
 - Framework detection
 - Test framework presence
@@ -309,16 +325,21 @@ The plan-synthesizer receives all collected data and performs:
 # Reality Check Report
 
 ## Executive Summary
+
 Project has moderate drift: 8 stale priority issues and 20% plan completion.
 Strong code health (tests + CI) but documentation lags implementation.
 
 ## Drift Analysis
+
 ### Priority Neglect
+
 **Severity**: high
 8 high-priority issues inactive for 60+ days...
 
 ## Prioritized Plan
+
 ### Immediate
+
 1. Close #45 (already implemented)
 2. Update README API section...
 ```

package/skills/drift-analysis/manifest.json

@@ -2,18 +2,8 @@
   "name": "drift-analysis",
   "version": "1.0.0",
   "description": "Analyze plan drift between documented intent and repository reality",
-  "triggers": [
-    "drift",
-    "reality check",
-    "plan drift",
-    "implementation gap",
-    "roadmap alignment"
-  ],
-  "applicable_agents": [
-    "planner",
-    "auditor",
-    "strategist"
-  ],
+  "triggers": ["drift", "reality check", "plan drift", "implementation gap", "roadmap alignment"],
+  "applicable_agents": ["planner", "auditor", "strategist"],
   "max_context_tokens": 2000,
   "entry_file": "SKILL.md"
 }

package/skills/evaluation/manifest.json

@@ -2,18 +2,8 @@
   "name": "evaluation",
   "version": "1.0.0",
   "description": "Lightweight evaluation framework for judgments and comparisons",
-  "triggers": [
-    "evaluate",
-    "assess",
-    "judge",
-    "compare",
-    "rate"
-  ],
-  "applicable_agents": [
-    "reviewer",
-    "critic",
-    "advisor"
-  ],
+  "triggers": ["evaluate", "assess", "judge", "compare", "rate"],
+  "applicable_agents": ["reviewer", "librarian"],
   "max_context_tokens": 1500,
   "entry_file": "SKILL.md"
 }

package/skills/executing-plans/SKILL.md

@@ -11,11 +11,12 @@ Load plan, review critically, execute all tasks, report when complete.
 
 **Announce at start:** "I'm using the executing-plans skill to implement this plan."
 
-**Note:** Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
+**Note:** This skill works best on platforms with subagent support (such as OpenCode). If subagents are available, prefer using them for parallel task execution.
 
 ## The Process
 
 ### Step 1: Load and Review Plan
+
 1. Read plan file
 2. Review critically - identify any questions or concerns about the plan
 3. If concerns: Raise them with your human partner before starting
@@ -24,6 +25,7 @@ Load plan, review critically, execute all tasks, report when complete.
 ### Step 2: Execute Tasks
 
 For each task:
+
 1. Mark as in_progress
 2. Follow each step exactly (plan has bite-sized steps)
 3. Run verifications as specified
@@ -32,13 +34,15 @@ For each task:
 ### Step 3: Complete Development
 
 After all tasks complete and verified:
-- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
-- **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch
-- Follow that skill to verify tests, present options, execute choice
+
+- Verify all tests pass and the build succeeds
+- Present completion options to the user (merge, PR, etc.)
+- Execute the user's chosen completion strategy
 
 ## When to Stop and Ask for Help
 
 **STOP executing immediately when:**
+
 - Hit a blocker (missing dependency, test fails, instruction unclear)
 - Plan has critical gaps preventing starting
 - You don't understand an instruction
@@ -49,12 +53,14 @@ After all tasks complete and verified:
 ## When to Revisit Earlier Steps
 
 **Return to Review (Step 1) when:**
+
 - Partner updates the plan based on your feedback
 - Fundamental approach needs rethinking
 
 **Don't force through blockers** - stop and ask.
 
 ## Remember
+
 - Review plan critically first
 - Follow plan steps exactly
 - Don't skip verifications
@@ -64,7 +70,8 @@ After all tasks complete and verified:
 
 ## Integration
 
-**Required workflow skills:**
-- **superpowers:using-git-worktrees** - REQUIRED: Set up isolated workspace before starting
-- **superpowers:writing-plans** - Creates the plan this skill executes
-- **superpowers:finishing-a-development-branch** - Complete development after all tasks
+**Recommended workflow practices:**
+
+- Set up an isolated workspace (e.g., git worktree or feature branch) before starting
+- Have a written plan ready before executing (this skill executes plans, not creates them)
+- Follow a structured completion process after all tasks are done (verify, review, merge)

package/skills/executing-plans/manifest.json

@@ -9,9 +9,7 @@
     "carry out plan",
     "execution checkpoints"
   ],
-  "applicable_agents": [
-    "executor"
-  ],
+  "applicable_agents": ["executor"],
   "max_context_tokens": 2000,
   "entry_file": "SKILL.md"
 }