cc10x — The Loop Engine for Claude Code

Stop chasing better models. Engineer the loop.

Same model. Same Claude Code. Different outcome.
The agent forgets between turns. The harness remembers across runs.
cc10x writes every workflow to disk — intent, evidence, verdicts, failures — so resume, review, and verification read from the artifact, not from a context window that's already gone.

1 router  ·  11 specialist agents  ·  19 skills  ·  4 workflows

Fail-closed gates  ·  survives compaction  ·  dispatch-by-reference  ·  test honesty gates  ·  anti-anchored review

Current version: 12.7.0

Install

Step 1 — Add the marketplace:

/plugin marketplace add romiluz13/cc10x

Step 2 — Install the plugin:

/plugin install cc10x@cc10x

Then say "set up cc10x for me" in Claude Code and restart. Done.

Why cc10x

Ask Claude for something complex. It works for a while. Then it declares "Done!" — tests still red, refactor half-finished, and by message 40 it's contradicting itself because the context is gone.

cc10x fixes the loop, not the prompt. A better model running free loses to the same model, constrained and looped correctly. That's the whole bet.

Everything below is the architecture. Keep reading if you want to know how before you install.

Runtime Model

1. Router owns orchestration

cc10x-router is the only orchestration authority.

The router now uses a kernel + mandatory reference shape:

• universal orchestration law stays inline in cc10x-router/SKILL.md
• workflow-specific playbooks and appendix-heavy artifact/remediation law live in cc10x-router/references/*.md
• the kernel explicitly tells Claude which reference must be read before BUILD / DEBUG / REVIEW / PLAN branch logic continues

That keeps orchestration salient without turning the router into a context dump.

It decides:

• which workflow to run
• which subagent to invoke next
• when to pause for clarification or scope decisions
• when remediation is required
• when a workflow is allowed to advance
• when memory and workflow artifacts are finalized

Agents do not own workflow state. They return structured results. The router interprets them.

2. Agents are narrow specialists

The shipped subagents are intentionally specialized:

• planner
• plan-gap-reviewer
• component-builder
• bug-investigator
• code-reviewer
• failure-hunter
• integration-verifier
• researcher
• doc-syncer

Each agent is optimized for one role. This keeps prompts sharper and makes workflow behavior easier to reason about.

3. Skills are reusable local instructions

Skills are the reusable instruction layer that agents and the router depend on.

They provide:

• planning patterns
• TDD rules
• debugging patterns
• review rules
• research synthesis
• memory handling
• verification-before-completion discipline

4. Workflow artifacts are the durable truth

cc10x writes proof-of-work workflow state under:

.cc10x/workflows/{wf}.json
.cc10x/workflows/{wf}.events.jsonl

These artifacts track:

• workflow type and task ids
• intent/spec context
• agent results
• evidence and quality state
• remediation history
• lifecycle events

This is what makes resume, review, and debugging more reliable than relying on chat context alone.

5. Hooks are guardrails, not a second orchestrator

cc10x ships a minimal Claude Code-native hook set:

• PreToolUse
• SessionStart
• PostToolUse
• TaskCompleted

Hooks do not replace the router. They provide lightweight enforcement and diagnostics:

• protected file and workflow write checks
• resume context hydration
• workflow artifact integrity audit
• task metadata validation

This follows the official Claude Code pattern: hooks are small guardrails around tool use, not a parallel control plane.

6. MCP is optional acceleration only

cc10x does not ship MCP server config inside the plugin.

If the user already has Claude Code MCP servers named:

• octocode
• brightdata

then research gets better automatically.

If not, the plugin still works. Research falls back to built-in Claude Code tools and records degraded confidence where appropriate.

How It Works

┌──────────────────────────────────────────────────────────────────────────────┐
│                                                                              │
│   YOU: "build a user auth system"                                            │
│                                     ┌────────────────────────────────────┐   │
│                              ┌─────►│  component-builder                 │   │
│                              │      │  + TDD enforcement                 │   │
│   ┌────────────────────┐     │      │  + code-generation skill           │   │
│   │                    │     │      └──────────────┬─────────────────────┘   │
│   │   cc10x-router     │─────┤                     │                         │
│   │   (auto-detects    │     │      ┌──────────────▼─────────────────────┐   │
│   │    BUILD intent)   │     │      │  code-reviewer ∥ silent-failure    │   │
│   │                    │     │      │  (parallel execution)              │   │
│   └────────────────────┘     │      └──────────────┬─────────────────────┘   │
│                              │                     │                         │
│                              │      ┌──────────────▼─────────────────────┐   │
│                              └─────►│  integration-verifier              │   │
│                                     │  + E2E validation                  │   │
│                                     └────────────────────────────────────┘   │
│                                                                              │
└──────────────────────────────────────────────────────────────────────────────┘

You describe the work. cc10x routes it, brings in the right specialists, and keeps the bar for "done" higher than a convincing paragraph.

                        YOU
                         │
                         ▼
            ┌────────────────────────┐
            │      cc10x-router      │  ◄── only entry point
            │   detects intent       │
            └────────────┬───────────┘
                         │
          ┌──────────────┼──────────────┬─────────────┐
          │              │              │             │
          ▼              ▼              ▼             ▼
        BUILD          DEBUG         REVIEW         PLAN
          │              │              │             │
          ▼              ▼              ▼             ▼
    component-      bug-          code-          planner
      builder    investigator   reviewer            │
          │              │              │             ▼
          ▼              ▼           (done)     plan-gap-
  [code-reviewer    code-reviewer             reviewer
   ∥ silent-            │
   failure-            ▼
    hunter]      integration-
          │         verifier
          ▼
   integration-
     verifier

                 ┌──────────────────────────┐
                 │  STATE (every workflow)  │
                 │  activeContext.md        │
                 │  patterns.md            │
                 │  progress.md            │
                 │  {wf}.json + .events    │
                 └──────────────────────────┘

Claude Setup Instructions

This section is written for Claude Code to follow when the user says "set up cc10x for me".

When user says "set up cc10x", "install cc10x", or similar:

Step 1: Check Existing Files

• Read ~/.claude/CLAUDE.md (may not exist)
• Read ~/.claude/settings.json (may not exist)

Step 2: Update ~/.claude/CLAUDE.md

If file doesn't exist: CREATE with the template below. If file exists: PREPEND the cc10x section below, keep user's existing content.

Multi-project note: The global ~/.claude/CLAUDE.md activates cc10x in every project automatically — you do not need to reinstall or reconfigure per project. Only add the cc10x section to a project's .claude/CLAUDE.md if that project has its own conflicting CLAUDE.md already.

# CC10x Orchestration (Always On)

IMPORTANT: ALWAYS invoke cc10x-router on ANY development task. First action, no exceptions.
IMPORTANT: Do only minimal orientation if needed, then invoke the router immediately.
IMPORTANT: Prefer retrieval-led reasoning over pre-training-led reasoning for orchestration decisions.
IMPORTANT: Never bypass the router. It is the system.
IMPORTANT: NEVER use Edit, Write, or Bash (for code changes) without first invoking cc10x-router.

**Skip CC10x ONLY when:**
- User EXPLICITLY says "don't use cc10x", "without cc10x", or "skip cc10x"
- No interpretation. No guessing. Only these exact opt-out phrases.

[CC10x]|entry: cc10x:cc10x-router

---

## Complementary Skills (Work Together with CC10x)

**Skills are additive, not exclusive.** CC10x provides orchestration. Domain skills provide expertise. Both work together.

**GATE:** Before writing code, check if task matches a skill below. If match, invoke it via `Skill(skill="...")`.

| When task involves... | Invoke |
|-----------------------|--------|
| *(Add user's installed skills here)* | |

Step 3: Update ~/.claude/settings.json

If file doesn't exist: CREATE with the template below. If file exists: MERGE these permissions into the existing permissions.allow array (don't overwrite!):

"Bash(mkdir -p .cc10x)",
"Bash(mkdir -p docs/plans)",
"Bash(mkdir -p docs/research)",
"Bash(mkdir -p docs/solutions)",
"Bash(git status)",
"Bash(git diff:*)",
"Bash(git log:*)",
"Bash(git branch:*)",
"Edit(.cc10x/*)",
"Write(.cc10x/*)"

Why the Edit/Write permissions? The live cc10x memory namespace is .cc10x/. The permission examples use the .cc10x/* scope so the namespace works without re-prompting on every memory write.

Step 4: Set User Standards (Optional)

Ask the user:

"Do you have coding standards or principles you want cc10x agents to always follow? (e.g. 'always use TypeScript strict mode', 'follow SOLID principles', 'never use any', 'prefer functional patterns')"

If user provides standards, write them to the project's memory:

Bash(command="mkdir -p .cc10x")
# Check if patterns.md already exists (Read returns error = doesn't exist)
Read(file_path=".cc10x/patterns.md")

# If it DOESN'T exist — create with standards already populated:
Write(file_path=".cc10x/patterns.md", content="# Project Patterns\n<!-- CC10X MEMORY CONTRACT: Do not rename headings. Used as Edit anchors. -->\n\n## User Standards\n- {standard 1}\n- {standard 2}\n\n## Architecture Patterns\n\n## Code Conventions\n\n## Common Gotchas\n\n## Last Updated\n{date}")

# If it DOES exist — append under User Standards:
Edit(file_path=".cc10x/patterns.md",
     old_string="## User Standards",
     new_string="## User Standards\n- {standard 1}\n- {standard 2}")

Read(file_path=".cc10x/patterns.md")  # Verify

If user skips: No action. The memory file will be created on first workflow run with an empty ## User Standards section for them to fill in later.

Step 5: Scan Installed Skills & Add to Table

Where to find installed skills:

1. ~/.claude/settings.json → check enabledPlugins object (plugins with value true)
2. ~/.claude/plugins/installed_plugins.json → detailed plugin info
3. ~/.claude/skills/ → personal skills (all projects)
4. .claude/skills/ → project-specific skills

Skill naming in table:

• Plugin skills: plugin-name:skill-name (e.g., mongodb-agent-skills:mongodb-schema-design)
• Personal/project skills: just the skill name (e.g., react-best-practices)

Example: If user has these:

# In enabledPlugins:
"mongodb-agent-skills@mongodb-agent-skills": true

# In ~/.claude/skills/:
react-best-practices/SKILL.md

Add to the Complementary Skills table:

| When task involves... | Invoke |
|-----------------------|--------|
| MongoDB, schema, queries | `mongodb-agent-skills:mongodb-schema-design` |
| React, Next.js, UI | `react-best-practices` |

Step 6: Confirm

"cc10x is set up! Please restart Claude Code to activate."

The 4 Workflows

Quick Start Examples

Build Something

"build a user authentication system"

→ Router detects BUILD intent
→ Stops to resolve missing requirements first
→ component-builder drives RED → GREEN → REFACTOR
→ code-reviewer + failure-hunter run in parallel
→ integration-verifier checks wiring, artifacts, and behavior
→ Workflow state and memory are updated

Fix a Bug

"debug the payment processing error"

→ Router detects DEBUG intent
→ Loads prior failures and project memory
→ bug-investigator starts from logs and observed behavior
→ code-reviewer checks the fix path
→ integration-verifier confirms the bug is actually closed
→ Useful findings go back into memory

Review Code

"review this PR for security issues"

→ Router detects REVIEW intent
→ code-reviewer uses repo and git context
→ Reports findings only when confidence clears the bar
→ Every finding includes file:line evidence

Architecture

USER REQUEST
     │
     ▼
┌─────────────────────────────────────────────────────────────────┐
│                    cc10x-router (ONLY ENTRY POINT)              │
│              Detects intent → Routes to workflow                │
└─────────────────────────────────────────────────────────────────┘
     │
     ├── BUILD ──► component-builder ──► [code-reviewer ∥ failure-hunter] ──► integration-verifier
     │
     ├── DEBUG ──► bug-investigator ──► code-reviewer ──► integration-verifier
     │
     ├── REVIEW ─► code-reviewer
     │
     └── PLAN ───► planner

MEMORY (.cc10x/)
├── activeContext.md  ◄── Current focus, decisions, learnings
├── patterns.md       ◄── Project conventions, common gotchas
└── progress.md       ◄── Completed work, remaining tasks

WORKFLOW STATE (.cc10x/workflows/)
├── {wf}.json         ◄── Durable workflow artifact
└── {wf}.events.jsonl ◄── Append-only workflow event log

The 11 Agents

The 19 Skills

Skills are loaded automatically by agents. You never invoke them directly.

cc10x-router is the entry-point skill that routes every workflow; it ships alongside these 19.

Memory Persistence

cc10x survives context compaction. This is critical for long sessions.

.cc10x/
├── activeContext.md   # What you're working on NOW
│   - Current task
│   - Active decisions (and WHY)
│   - Learnings this session
│
├── patterns.md        # Project conventions
│   - Code patterns
│   - Common gotchas (bugs → fixes)
│   - Architectural decisions
│
└── progress.md        # What's done, what's left
    - Completed items (with evidence)
    - Remaining tasks
    - Blockers

The live namespace is .cc10x/ (memory .cc10x/*.md, workflow state .cc10x/workflows/*). Two legacy residue locations are ignored by current router hydration if present: .claude/cc10x/ (pre-10.1.20, before the workflow state moved out of .claude/ to escape the harness sensitive-file gate) and the version-segmented .cc10x/v10/ layout (v10.x, before the namespace was de-versioned in v11). cc10x does not migrate either; a fresh .cc10x/ is created on first use.

Iron Law: Every workflow loads memory at START and updates at END.

Task-Based Orchestration

cc10x uses Claude Code's Tasks system for workflow coordination:

┌─────────────────────────────────────────────────────────────────┐
│  BUILD: User Authentication                                     │
│  ├── component-builder (pending)                                │
│  ├── code-reviewer (blocked by: builder)                        │
│  ├── failure-hunter (blocked by: builder)                │
│  └── integration-verifier (blocked by: reviewer, hunter)        │
└─────────────────────────────────────────────────────────────────┘

• Dependency chains: Agents wait for blockers to complete
• Parallel execution: reviewer + hunter run simultaneously
• Resume capability: TaskList() checks for active workflows
• Automatic handoff: Each agent updates status when done
• Router-owned advancement: only the router decides whether a workflow can continue

Hooks

The plugin currently ships these Claude Code-native hooks:

These hooks are intentionally minimal. They improve reliability without turning the plugin into a second runtime.

Plan → Build Automation

Plans don't get lost. They flow automatically to the build phase.

Day 1: "plan a task tracker"
  → Planner creates docs/plans/2025-01-29-task-tracker-plan.md
  → Memory updated with plan reference

Day 2: "build it"
  → Router detects BUILD
  → component-builder finds plan in memory
  → Follows plan phases with TDD

Expected Behavior

When You Say "Build a Task Tracker"

cc10x Response:

Detected BUILD intent. Executing BUILD workflow.

Loading memory...
✓ Memory loaded

Clarifying requirements (REQUIRED):
1. What framework/language? (Node.js, Python, etc.)
2. Should tasks have priorities, due dates, categories?
3. CLI app or web app?
4. Any features beyond basic CRUD?

Waiting for your answers before proceeding.

Without cc10x:

I'll help you build a task tracker! Let me start...
[Writes code without asking]
[Skips tests]
[Claims "it should work"]

Version History

Files Structure

plugins/cc10x/
├── .claude-plugin/
│   └── plugin.json
├── hooks/
│   └── hooks.json
├── config/
│   └── hook-mode.json
├── scripts/
│   ├── cc10x_event_logger.py
│   ├── cc10x_git_guard.py
│   ├── cc10x_hooklib.py
│   ├── cc10x_posttooluse_artifact_guard.py
│   ├── cc10x_pretooluse_guard.py
│   ├── cc10x_sessionstart_context.py
│   ├── cc10x_state_persist.py
│   └── cc10x_task_completed_guard.py
├── tools/
│   ├── review_package.py
│   ├── phase_brief.py
│   └── live_harness_runner.py
├── tests/
│   └── fixtures/
├── agents/
│   ├── component-builder.md
│   ├── bug-investigator.md
│   ├── code-reviewer.md
│   ├── integration-verifier.md
│   ├── doc-syncer.md
│   ├── planner.md
│   ├── plan-gap-reviewer.md
│   ├── researcher.md
│   ├── triage-agent.md
│   ├── architecture-scanner.md
│   └── references/silent-failure-red-flags.md
│
└── skills/
    ├── cc10x-router/
    │   ├── SKILL.md
    │   └── references/
    │       ├── workflow-artifact-and-hook-policy.md
    │       ├── workflow-artifact.skeleton.json
    │       ├── build-workflow.md
    │       ├── debug-workflow.md
    │       ├── review-workflow.md
    │       ├── plan-workflow.md
    │       ├── triage-workflow.md
    │       ├── codebase-health-workflow.md
    │       └── remediation-and-research.md
    ├── agent-common/SKILL.md
    ├── memory-and-handoff/SKILL.md
    ├── building/SKILL.md
    ├── debugging/SKILL.md
    ├── code-review/SKILL.md
    ├── planning/SKILL.md
    ├── plan-review-gate/SKILL.md
    ├── architecture/SKILL.md
    ├── frontend/SKILL.md
    │   └── references/{ui-state-and-feedback,accessibility-and-forms,performance-and-layout,design-md-authoring,design-md-inspiration-index}.md
    ├── exploration/SKILL.md
    ├── diff-driven-docs/SKILL.md
    ├── research/SKILL.md
    ├── verification/SKILL.md
    ├── codebase-hygiene/SKILL.md
    ├── codebase-design/SKILL.md
    │   └── references/{DEEPENING,DESIGN-IT-TWICE}.md
    ├── domain-modeling/SKILL.md
    │   └── references/{CONTEXT-FORMAT,ADR-FORMAT}.md
    ├── mcp-cli/SKILL.md
    ├── resolving-merge-conflicts/SKILL.md
    └── update/SKILL.md

Additional developer docs live under:

docs/cc10x-orchestration-bible.md
docs/cc10x-orchestration-logic-analysis.md
docs/cc10x-orchestration-safety.md
docs/router-invariants.md

If you need to understand or evolve the harness, start there after reading cc10x-router.

Optional MCP Integrations

cc10x works out of the box with no MCPs required. These are optional — they unlock specific features when installed in your own Claude Code MCP settings.

Important: CC10X no longer ships MCP server config inside the plugin. This avoids startup warnings for users who do not have Bright Data or Octocode credentials configured.

Without these MCPs: cc10x still works fully. The research agents degrade to built-in Claude Code tools and note the lower-confidence path in their outputs.

With octocode installed: When the router detects new/unfamiliar tech, 3+ failed debug attempts, or explicit research requests, it automatically calls octocode tools to search GitHub before invoking the planner or bug-investigator.

Troubleshooting

Claude Code keeps asking for permission to edit memory files

Add these two lines to ~/.claude/settings.json under permissions.allow:

"Edit(.cc10x/*)",
"Write(.cc10x/*)"

These permission examples cover the live .cc10x/ namespace.

Or run "Set up cc10x for me" again — the setup wizard adds them automatically.

cc10x not activating in a specific project

The global ~/.claude/CLAUDE.md activates cc10x in every project — you only need one install. If it's not activating in a specific project:

1. Check if that project has its own .claude/CLAUDE.md — open it and verify the cc10x section is present. If the project-level file exists but doesn't have the cc10x entry, add it there.
2. Verify the entry format — use [CC10x]|entry: cc10x:cc10x-router (plugin reference). A relative path like ./plugins/cc10x/... only works in the cc10x repo itself, not in your projects.
3. Restart Claude Code — the plugin system requires a restart after any CLAUDE.md change.

Ubuntu / Linux install error: EXDEV cross-device link

If you see:

Error: Failed to install: EXDEV: cross-device link not permitted

This is a Linux filesystem issue — /tmp and your home directory are on different filesystems, so the installer can't rename() across them. Fix:

# Set TMPDIR to a directory on the same filesystem as your home:
mkdir -p ~/.claude/tmp
TMPDIR=~/.claude/tmp claude
# Then install normally: /plugin install cc10x@cc10x

If that doesn't work, install manually:

# Clone directly into the plugins directory
git clone https://github.com/romiluz13/cc10x.git ~/.claude/plugins/cc10x

Then follow Step 2 in the setup guide above to add the cc10x entry to ~/.claude/CLAUDE.md.

"Unknown skill cc10x:cc10x-router"

The cc10x plugin is disabled. Run:

/plugins enable cc10x

Then retry your command.

Contributing

• Star the repository
• Report issues
• Suggest improvements

License

MIT License

cc10x v12.7.0
The Intelligent Orchestrator for Claude Code