How do I install the Cc Main Implement skill?

Run npx skillmds@latest add xukai-ye/cc-main-implement in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Cc Main Implement safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Cc Main Implement?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Cc Main Implement free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Cc Main Implement?

Xukai-YE (@xukai-ye) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Cc Main Implement by xukai-ye — Agent Skill

Name: Cc Main Implement
Rating: 4.666666666666667 (3 reviews)
Author: Xukai-YE

Cc Main Implement

Use when a coding task is medium or high-risk and Claude Code should do the main implementation work. Pass -Tier to select model preference: medium uses Sonnet 4.6 first, high-risk uses Opus 4.6 first. Codex reviews, verifies, and applies only short follow-up patches.

Xukai-YE Updated Sep 22, 2026

File contents

CC Main Implement

This skill makes Claude Code the primary implementation worker for medium and high-risk tasks.

Codex remains the orchestrator and final reviewer.

When to Use

Use this skill when:

the task is classified as medium or high-risk by the 3-tier classifier
multiple files are likely involved
a meaningful implementation flow already exists
the user wants Claude Code to do the majority of coding

Do not use it for tiny tasks.

Tier-Aware Model Preference

Tier	Model Order
medium	`claude-sonnet-4-6` -> `claude-opus-4-6` -> `sonnet` -> `opus`
high-risk	`claude-opus-4-6` -> `claude-sonnet-4-6` -> `opus` -> `sonnet`

Pass -Tier medium or -Tier high-risk to the invocation script. Default is high-risk if omitted.

Responsibility Split

Claude Code:

performs the main implementation
edits the majority of files
runs focused checks when appropriate
performs a brief self-review before returning
returns output in the required structured format

Codex:

classifies the task tier
supplies the plan and scope
reviews Claude Code output and diffs
fixes issues Claude Code missed
keeps follow-up edits short and targeted when possible
runs final verification
explains final results to the user

Workflow

If the task is tiny, skip this skill.
If the task is high-risk, do plan review first with cc-opus-review-loop -Tier high-risk.
Then invoke the bundled script:

powershell -NoProfile -ExecutionPolicy Bypass -File "scripts/invoke-cc-main-implement.ps1" `
  -UserRequest "$ARGUMENTS" `
  -WorkingDirectory "$PWD" `
  -Tier "medium"

If specific files or plan files are already known, pass them:

powershell -NoProfile -ExecutionPolicy Bypass -File "scripts/invoke-cc-main-implement.ps1" `
  -UserRequest "$ARGUMENTS" `
  -WorkingDirectory "$PWD" `
  -Tier "high-risk" `
  -ContextPaths "task_plan.md","src/app.ts","src/auth.ts"

After Claude Code finishes, Codex must:

inspect the changed files and diff
run focused verification
optionally run cc-opus-review-loop at a checkpoint
make only necessary follow-up patches

Failure Handling

If Claude Code is unavailable, not authenticated, or fails:

note it briefly
if Claude fails twice consecutively during the same task, note "degraded mode" and continue locally in Codex for the rest of that task; do not retry Claude Code again for that task
do not block the task solely because Claude Code could not run

Required Claude Output Format

Claude Code must return exactly these sections:

Decision - what was implemented and why this approach
Changed Files - list of modified or created files
Patch Summary - concise description of each change
Why This Way - rationale for key design choices
Tests - tests added, modified, or suggested
Known Risks - remaining risks or limitations
Rollback Point - how to revert if needed

Treat that output as an implementation report. The real source of truth is still the repo diff and test results.

---name: cc-main-implementdescription: Use when a coding task is medium or high-risk and Claude Code should do the main implementation work. Pass -Tier to select model preference: medium uses Sonnet 4.6 first, high-risk uses Opus 4.6 first. Codex reviews, verifies, and applies only short follow-up patches.---# CC Main ImplementThis skill makes Claude Code the primary implementation worker for medium and high-risk tasks.Codex remains the orchestrator and final reviewer.## When to UseUse this skill when:- the task is classified as **medium** or **high-risk** by the 3-tier classifier- multiple files are likely involved- a meaningful implementation flow already exists- the user wants Claude Code to do the majority of codingDo not use it for tiny tasks.## Tier-Aware Model Preference| Tier | Model Order ||------|-------------|| **medium** | `claude-sonnet-4-6` -> `claude-opus-4-6` -> `sonnet` -> `opus` || **high-risk** | `claude-opus-4-6` -> `claude-sonnet-4-6` -> `opus` -> `sonnet` |Pass `-Tier medium` or `-Tier high-risk` to the invocation script. Default is `high-risk` if omitted.## Responsibility SplitClaude Code:- performs the main implementation- edits the majority of files- runs focused checks when appropriate- performs a brief self-review before returning- returns output in the required structured formatCodex:- classifies the task tier- supplies the plan and scope- reviews Claude Code output and diffs- fixes issues Claude Code missed- keeps follow-up edits short and targeted when possible- runs final verification- explains final results to the user## Workflow1. If the task is tiny, skip this skill.2. If the task is high-risk, do plan review first with `cc-opus-review-loop -Tier high-risk`.3. Then invoke the bundled script:```powershellpowershell -NoProfile -ExecutionPolicy Bypass -File "scripts/invoke-cc-main-implement.ps1" ` -UserRequest "$ARGUMENTS" ` -WorkingDirectory "$PWD" ` -Tier "medium"```4. If specific files or plan files are already known, pass them:```powershellpowershell -NoProfile -ExecutionPolicy Bypass -File "scripts/invoke-cc-main-implement.ps1" ` -UserRequest "$ARGUMENTS" ` -WorkingDirectory "$PWD" ` -Tier "high-risk" ` -ContextPaths "task_plan.md","src/app.ts","src/auth.ts"```5. After Claude Code finishes, Codex must:- inspect the changed files and diff- run focused verification- optionally run `cc-opus-review-loop` at a checkpoint- make only necessary follow-up patches## Failure HandlingIf Claude Code is unavailable, not authenticated, or fails:- note it briefly- if Claude fails **twice consecutively** during the same task, note "degraded mode" and continue locally in Codex for the rest of that task; do not retry Claude Code again for that task- do not block the task solely because Claude Code could not run## Required Claude Output FormatClaude Code must return exactly these sections:1. **Decision** - what was implemented and why this approach2. **Changed Files** - list of modified or created files3. **Patch Summary** - concise description of each change4. **Why This Way** - rationale for key design choices5. **Tests** - tests added, modified, or suggested6. **Known Risks** - remaining risks or limitations7. **Rollback Point** - how to revert if neededTreat that output as an implementation report. The real source of truth is still the repo diff and test results.

Frequently asked questions