# Cc Opus First Pass

> Use to classify a coding task into the 3-tier system (tiny/medium/high-risk) and get an analysis brief before implementation. Always uses Opus 4.6 first for deep reasoning. Skip for tasks that are obviously tiny.

- Skill: `xukai-ye/cc-opus-first-pass` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add xukai-ye/cc-opus-first-pass`
- Raw SKILL.md: https://api.skillmd.com/api/skills/xukai-ye/cc-opus-first-pass/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: Xukai-YE (https://skillmd.com/u/xukai-ye)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/xukai-ye/cc-opus-first-pass

---


# CC Opus First Pass

Use this skill to classify a task into the 3-tier system and produce an analysis brief.

Model order (always Opus-first for analysis):

- `claude-opus-4-6`
- `claude-sonnet-4-6`
- `opus`
- `sonnet`

## 3-Tier Classification

Classify into exactly one tier: **TINY**, **MEDIUM**, or **HIGH-RISK**.

The classifier is **risk-first**: the highest-risk signal present determines the tier.

### Risk Signals

| Signal | Low | Moderate | High |
|--------|-----|----------|------|
| Files / modules / layers | 1 file, local path | 2-4 files, 1 module boundary | Crosses modules or layers |
| Auth / security | None | Minor permission check | Trust boundary, secrets, auth flow |
| State / concurrency | None | Simple state update | Shared state, locks, async coordination |
| Schema / migration | None | Additive field | Breaking change or migration |
| Build / config / deps | None | Config value tweak | Build system, CI, or new dependency |
| Public API surface | None | Backward-compatible addition | Breaking change or redesign |
| Blast radius clarity | Obvious | Mostly clear | Hard to reason about |
| Design tradeoffs | None | Minor choice | Significant alternatives |

### Decision

- **TINY**: All signals low. <= 15 lines, 1 file, obvious blast radius. -> Skip this skill; Codex handles directly.
- **MEDIUM**: Any moderate signal and no high signals. -> `cc-main-implement -Tier medium` (Sonnet-first).
- **HIGH-RISK**: Any high signal. -> Full orchestration: plan review -> `cc-main-implement -Tier high-risk` (Opus-first) -> checkpoint reviews.

**Highest-risk signal wins.**

## Workflow

1. Classify the task.
2. If `TINY`, skip this skill and proceed in Codex.
3. If `MEDIUM` or `HIGH-RISK`, invoke the bundled script:

```powershell
powershell -NoProfile -ExecutionPolicy Bypass -File "scripts/invoke-cc-opus-first-pass.ps1" `
  -UserRequest "$ARGUMENTS" `
  -WorkingDirectory "$PWD"
```

4. If specific files are already known, include them as context paths:

```powershell
powershell -NoProfile -ExecutionPolicy Bypass -File "scripts/invoke-cc-opus-first-pass.ps1" `
  -UserRequest "$ARGUMENTS" `
  -WorkingDirectory "$PWD" `
  -ContextPaths "src/app.ts","src/auth.ts"
```

5. Read Claude Code output and use it as a first-pass brief, not as unquestioned truth.
6. Codex still owns:
- final implementation decisions
- actual edits
- verification
- final user-facing explanation

## Failure Handling

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

- note the failure briefly
- continue locally in Codex
- do not block the task solely because the external first pass is unavailable

## Expected Claude Output

The script asks Claude Code for:

1. Tier Verdict: TINY, MEDIUM, or HIGH-RISK
2. Risk Signal Assessment (which signals triggered and at what level)
3. Why (concise justification)
4. Likely Affected Files
5. Implementation Plan
6. Risks and Edge Cases
7. Suggested Tests
8. Patch Sketch

Use that output to guide the Codex implementation and review pass.