cc10x Router
EXECUTION ENGINE. When loaded: Detect intent → Load memory → Execute workflow → Update memory.
NEVER list capabilities. ALWAYS execute.
Decision Tree (FOLLOW IN ORDER)
| Priority |
Signal |
Keywords |
Workflow |
| 1 |
ERROR |
error, bug, fix, broken, crash, fail, debug, troubleshoot, issue, problem, doesn't work |
DEBUG |
| 2 |
PLAN |
plan, design, architect, roadmap, strategy, spec, "before we build", "how should we" |
PLAN |
| 3 |
REVIEW |
review, audit, check, analyze, assess, "what do you think", "is this good" |
REVIEW |
| 4 |
DEFAULT |
Everything else |
BUILD |
Conflict Resolution: ERROR signals always win. "fix the build" = DEBUG (not BUILD).
Agent Chains
| Workflow |
Agents |
| BUILD |
component-builder → [code-reviewer ∥ silent-failure-hunter] → integration-verifier |
| DEBUG |
bug-investigator → code-reviewer → integration-verifier |
| REVIEW |
code-reviewer |
| PLAN |
planner |
∥ = PARALLEL - code-reviewer and silent-failure-hunter run simultaneously (both read-only)
Memory (PERMISSION-FREE)
LOAD FIRST (Before routing):
Bash(command="mkdir -p .claude/cc10x")
Read(file_path=".claude/cc10x/activeContext.md")
Read(file_path=".claude/cc10x/patterns.md")
Read(file_path=".claude/cc10x/progress.md")
UPDATE LAST (After workflow): Use Edit tool on activeContext.md (permission-free).
Workflow Execution
BUILD
- Load memory → Check if already done in progress.md
- Clarify requirements (DO NOT SKIP) → Use AskUserQuestion
- Invoke component-builder (TDD: RED→GREEN→REFACTOR)
- PARALLEL: Invoke code-reviewer AND silent-failure-hunter simultaneously
Task(subagent_type="cc10x:code-reviewer", ...)
Task(subagent_type="cc10x:silent-failure-hunter", ...) // Same message = parallel
- Wait for BOTH to complete → Merge findings
- Invoke integration-verifier
- Update memory
DEBUG
- Load memory → Check patterns.md Common Gotchas
- Clarify: What error? Expected vs actual? When started?
- If github-research detected (external service error OR explicit request):
- Execute research FIRST using octocode tools directly
- Search for error patterns, PRs with similar issues
- Invoke bug-investigator (LOG FIRST, pass research results if step 3 executed)
- Invoke code-reviewer
- Invoke integration-verifier
- Update memory → Add to Common Gotchas
REVIEW
- Load memory
- Invoke code-reviewer (check git history, confidence ≥80)
- Update memory
PLAN
- Load memory
- If github-research detected (external tech OR explicit request):
- Execute research FIRST using octocode tools directly (NOT as hint)
- Use:
mcp__octocode__packageSearch, mcp__octocode__githubSearchCode, etc.
- Summarize findings before invoking planner
- Invoke planner (pass research results in prompt if step 2 was executed)
- Update memory → Reference saved plan
TWO-PHASE for External Research (MANDATORY):
If SKILL_HINTS includes github-research:
→ FIRST: Execute research using octocode tools
→ THEN: Task(cc10x:planner, prompt="...Research findings: {results}...")
Research is a PREREQUISITE, not a hint. Planner cannot skip it.
Agent Invocation
Pass context to each agent:
Task(subagent_type="cc10x:component-builder", prompt="
User request: {request}
Requirements: {from AskUserQuestion}
Memory: {from activeContext.md}
Patterns: {from patterns.md}
SKILL_HINTS: {detected skills from table below - agent MUST load these}
")
SKILL_HINTS are MANDATORY. Agent MUST call Skill(skill="...") for each hint immediately after loading memory.
Skill triggers for agents (DETECT AND PASS AS SKILL_HINTS):
| Detected Pattern |
Skill |
Agents |
| Frontend: components/, ui/, pages/, .tsx, .jsx, CSS, styling, "button", "form", "modal" |
cc10x:frontend-patterns |
planner, component-builder, code-reviewer, integration-verifier |
| API/Backend: api/, routes/, services/, "endpoint", "REST", "GraphQL" |
cc10x:architecture-patterns |
planner, bug-investigator, code-reviewer |
| Vague: "not sure", "maybe", "options", "ideas", unclear requirements |
cc10x:brainstorming |
planner |
| External: new tech (post-2024), unfamiliar library, complex integration (auth, payments) |
cc10x:github-research |
planner, bug-investigator |
| Debug exhausted: 3+ local attempts failed, external service error |
cc10x:github-research |
bug-investigator |
| User explicitly requests: "research", "github", "octocode", "find on github", "how do others", "best practices" |
cc10x:github-research |
planner, bug-investigator |
Detection runs BEFORE agent invocation. Pass detected skills in SKILL_HINTS.
Gates (Must Pass)
- MEMORY_LOADED - Before routing
- RESEARCH_EXECUTED - Before planner (if github-research detected)
- REQUIREMENTS_CLARIFIED - Before invoking agent (BUILD only)
- AGENT_COMPLETED - Before next agent in chain
- MEMORY_UPDATED - Before marking done
Chain Enforcement (CRITICAL)
NEVER stop after one agent. The workflow is NOT complete until the chain finishes.
After EACH agent completes, check its output for:
PARALLEL_AGENTS: X, Y → Invoke BOTH agents in same message (parallel)
PARALLEL_COMPLETE + SYNC_NEXT: X → After BOTH parallel agents complete, invoke X
NEXT_AGENT: X → Invoke that single agent
WORKFLOW_CONTINUES: NO → Chain complete, update memory
Chain Execution Loop
1. Invoke agent via Task tool
2. Read agent output
3. Check output type:
a. PARALLEL_AGENTS: X, Y → Invoke BOTH in single message (parallel execution)
b. PARALLEL_COMPLETE + SYNC_NEXT: X → Wait for parallel peer, then invoke X
c. NEXT_AGENT: X → Invoke single agent
d. WORKFLOW_CONTINUES: NO → Chain complete
4. Return to step 1 until chain complete
Parallel Agent Invocation
When you see PARALLEL_AGENTS:, invoke ALL listed agents in ONE message:
Task(subagent_type="cc10x:code-reviewer", prompt="...")
Task(subagent_type="cc10x:silent-failure-hunter", prompt="...")
CRITICAL: Both tasks in same message = both complete before you continue.
After both return:
- Check BOTH outputs have
PARALLEL_COMPLETE
- Check BOTH have same
SYNC_NEXT: X value
- Invoke X (integration-verifier) with merged findings from both agents
DO NOT invoke integration-verifier until BOTH parallel agents have completed.
Chain Completion Criteria
The workflow is complete ONLY when:
- Final agent (integration-verifier) outputs
WORKFLOW_CONTINUES: NO
- OR a critical error prevents continuation
If you see PARALLEL_AGENTS: → Invoke ALL listed agents in parallel. No exceptions.
If you see NEXT_AGENT: X → Invoke agent X. No exceptions.
1---2name: cc10x-router3description: |4 THE ONLY ENTRY POINT FOR CC10X - AUTO-LOAD AND EXECUTE for ANY development task.56 Triggers: build, implement, create, make, write, add, develop, code, feature, component, app, application, review, audit, check, analyze, debug, fix, error, bug, broken, troubleshoot, plan, design, architect, roadmap, strategy, memory, session, context, save, load, test, tdd, frontend, ui, backend, api, pattern, refactor, optimize, improve, enhance, update, modify, change, help, assist, work, start, begin, continue, research, cc10x, c10x.78 CRITICAL: Execute workflow. Never just describe capabilities.9metadata:10 source: https://skillmd.com/skills/bishal-pdmsft/cc10x-router11---1213# cc10x Router1415**EXECUTION ENGINE.** When loaded: Detect intent → Load memory → Execute workflow → Update memory.1617**NEVER** list capabilities. **ALWAYS** execute.1819## Decision Tree (FOLLOW IN ORDER)2021| Priority | Signal | Keywords | Workflow |22|----------|--------|----------|----------|23| 1 | ERROR | error, bug, fix, broken, crash, fail, debug, troubleshoot, issue, problem, doesn't work | **DEBUG** |24| 2 | PLAN | plan, design, architect, roadmap, strategy, spec, "before we build", "how should we" | **PLAN** |25| 3 | REVIEW | review, audit, check, analyze, assess, "what do you think", "is this good" | **REVIEW** |26| 4 | DEFAULT | Everything else | **BUILD** |2728**Conflict Resolution:** ERROR signals always win. "fix the build" = DEBUG (not BUILD).2930## Agent Chains3132| Workflow | Agents |33|----------|--------|34| BUILD | component-builder → **[code-reviewer ∥ silent-failure-hunter]** → integration-verifier |35| DEBUG | bug-investigator → code-reviewer → integration-verifier |36| REVIEW | code-reviewer |37| PLAN | planner |3839**∥ = PARALLEL** - code-reviewer and silent-failure-hunter run simultaneously (both read-only)4041## Memory (PERMISSION-FREE)4243**LOAD FIRST (Before routing):**44```45Bash(command="mkdir -p .claude/cc10x")46Read(file_path=".claude/cc10x/activeContext.md")47Read(file_path=".claude/cc10x/patterns.md")48Read(file_path=".claude/cc10x/progress.md")49```5051**UPDATE LAST (After workflow):** Use Edit tool on activeContext.md (permission-free).5253## Workflow Execution5455### BUILD561. Load memory → Check if already done in progress.md572. **Clarify requirements** (DO NOT SKIP) → Use AskUserQuestion583. Invoke component-builder (TDD: RED→GREEN→REFACTOR)594. **PARALLEL:** Invoke code-reviewer AND silent-failure-hunter simultaneously60 ```61 Task(subagent_type="cc10x:code-reviewer", ...)62 Task(subagent_type="cc10x:silent-failure-hunter", ...) // Same message = parallel63 ```645. Wait for BOTH to complete → Merge findings656. Invoke integration-verifier667. Update memory6768### DEBUG691. Load memory → Check patterns.md Common Gotchas702. Clarify: What error? Expected vs actual? When started?713. **If github-research detected (external service error OR explicit request):**72 - Execute research FIRST using octocode tools directly73 - Search for error patterns, PRs with similar issues744. Invoke bug-investigator (LOG FIRST, pass research results if step 3 executed)755. Invoke code-reviewer766. Invoke integration-verifier777. Update memory → Add to Common Gotchas7879### REVIEW801. Load memory812. Invoke code-reviewer (check git history, confidence ≥80)823. Update memory8384### PLAN851. Load memory862. **If github-research detected (external tech OR explicit request):**87 - Execute research FIRST using octocode tools directly (NOT as hint)88 - Use: `mcp__octocode__packageSearch`, `mcp__octocode__githubSearchCode`, etc.89 - Summarize findings before invoking planner903. Invoke planner (pass research results in prompt if step 2 was executed)914. Update memory → Reference saved plan9293**TWO-PHASE for External Research (MANDATORY):**94```95If SKILL_HINTS includes github-research:96 → FIRST: Execute research using octocode tools97 → THEN: Task(cc10x:planner, prompt="...Research findings: {results}...")98```99Research is a PREREQUISITE, not a hint. Planner cannot skip it.100101## Agent Invocation102103Pass context to each agent:104```105Task(subagent_type="cc10x:component-builder", prompt="106User request: {request}107Requirements: {from AskUserQuestion}108Memory: {from activeContext.md}109Patterns: {from patterns.md}110SKILL_HINTS: {detected skills from table below - agent MUST load these}111")112```113114**SKILL_HINTS are MANDATORY.** Agent MUST call `Skill(skill="...")` for each hint immediately after loading memory.115116**Skill triggers for agents (DETECT AND PASS AS SKILL_HINTS):**117118| Detected Pattern | Skill | Agents |119|------------------|-------|--------|120| Frontend: components/, ui/, pages/, .tsx, .jsx, CSS, styling, "button", "form", "modal" | cc10x:frontend-patterns | planner, component-builder, code-reviewer, integration-verifier |121| API/Backend: api/, routes/, services/, "endpoint", "REST", "GraphQL" | cc10x:architecture-patterns | planner, bug-investigator, code-reviewer |122| Vague: "not sure", "maybe", "options", "ideas", unclear requirements | cc10x:brainstorming | planner |123| External: new tech (post-2024), unfamiliar library, complex integration (auth, payments) | cc10x:github-research | planner, bug-investigator |124| Debug exhausted: 3+ local attempts failed, external service error | cc10x:github-research | bug-investigator |125| User explicitly requests: "research", "github", "octocode", "find on github", "how do others", "best practices" | cc10x:github-research | planner, bug-investigator |126127**Detection runs BEFORE agent invocation. Pass detected skills in SKILL_HINTS.**128129## Gates (Must Pass)1301311. **MEMORY_LOADED** - Before routing1322. **RESEARCH_EXECUTED** - Before planner (if github-research detected)1333. **REQUIREMENTS_CLARIFIED** - Before invoking agent (BUILD only)1344. **AGENT_COMPLETED** - Before next agent in chain1355. **MEMORY_UPDATED** - Before marking done136137## Chain Enforcement (CRITICAL)138139**NEVER stop after one agent.** The workflow is NOT complete until the chain finishes.140141After EACH agent completes, check its output for:142- `PARALLEL_AGENTS: X, Y` → **Invoke BOTH agents in same message (parallel)**143- `PARALLEL_COMPLETE` + `SYNC_NEXT: X` → **After BOTH parallel agents complete, invoke X**144- `NEXT_AGENT: X` → **Invoke that single agent**145- `WORKFLOW_CONTINUES: NO` → Chain complete, update memory146147### Chain Execution Loop148```1491. Invoke agent via Task tool1502. Read agent output1513. Check output type:152 a. PARALLEL_AGENTS: X, Y → Invoke BOTH in single message (parallel execution)153 b. PARALLEL_COMPLETE + SYNC_NEXT: X → Wait for parallel peer, then invoke X154 c. NEXT_AGENT: X → Invoke single agent155 d. WORKFLOW_CONTINUES: NO → Chain complete1564. Return to step 1 until chain complete157```158159### Parallel Agent Invocation160When you see `PARALLEL_AGENTS:`, invoke ALL listed agents in ONE message:161```162Task(subagent_type="cc10x:code-reviewer", prompt="...")163Task(subagent_type="cc10x:silent-failure-hunter", prompt="...")164```165**CRITICAL:** Both tasks in same message = both complete before you continue.166167After both return:1681. Check BOTH outputs have `PARALLEL_COMPLETE`1692. Check BOTH have same `SYNC_NEXT: X` value1703. Invoke X (integration-verifier) with merged findings from both agents171172**DO NOT invoke integration-verifier until BOTH parallel agents have completed.**173174### Chain Completion Criteria175The workflow is complete ONLY when:176- Final agent (integration-verifier) outputs `WORKFLOW_CONTINUES: NO`177- OR a critical error prevents continuation178179**If you see `PARALLEL_AGENTS:` → Invoke ALL listed agents in parallel. No exceptions.**180**If you see `NEXT_AGENT: X` → Invoke agent X. No exceptions.**