CC Three-Tier Orchestrator
This is the top-level routing skill for the bundled Codex and Claude Code workflow.
Use it when you want the local 3-tier orchestration behavior packaged as an installable skill set.
Tier Model
Classify each coding task into exactly one tier:
tinymediumhigh-risk
The classifier is risk-first. Highest-risk signal wins.
Routing
Tiny
- handle locally in Codex
- do not invoke Claude Code just for ceremony
Medium
- optionally run
cc-opus-first-passif scope is unclear - run
cc-main-implementwith-Tier medium - use
cc-opus-review-loopfor meaningful plan or checkpoint reviews when the task grows or crosses a boundary
- optionally run
High-Risk
- run
cc-opus-first-pass - run
cc-opus-review-loopinPlanmode with-Tier high-risk - run
cc-main-implementwith-Tier high-risk - run
cc-opus-review-loopinCheckpointmode at milestone boundaries, risk increases, direction changes, or layer crossings
- run
Checkpoint Triggers
Trigger a checkpoint review when any of these occur:
- risk increases from the initial classification
- a milestone or subtask finishes
- implementation direction changes
- work crosses a new module or architectural layer
- fallback cadence: every 2-4 touched files, roughly every 80-200 changed lines, or after about 3 small edit rounds
After 2 consecutive clean checkpoint reviews, relax to milestone-only checkpoints until the next risk increase, direction change, or layer crossing.
Failure Rule
If Claude Code fails twice consecutively during one task:
- note
degraded mode - continue locally in Codex for the rest of that task
- do not retry Claude Code again for that task
Bundled Skills
../cc-opus-first-pass/SKILL.md../cc-main-implement/SKILL.md../cc-opus-review-loop/SKILL.md
Global Routing
If you want this routing to happen automatically across sessions, install the bundled skills and merge the AGENTS snippet from:
../../templates/codex-agents-snippet.md