원클릭으로
cvg-work
Execute the plan slice by slice using TDD. Self-check completeness before declaring the implementation result.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Execute the plan slice by slice using TDD. Self-check completeness before declaring the implementation result.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | cvg-work |
| description | Execute the plan slice by slice using TDD. Self-check completeness before declaring the implementation result. |
Implement the plan. Work through slices in order, using TDD. Do not declare the implementation complete until the plan's "done when" criteria are all met.
The task context provides the plan path. Read the plan document and any linked behavior contract.
If the task context provides no coordination channel (standalone use), the coordination channel is the user: stop and ask directly.
Read project stage guidance from the task context before applying this skill.
For implementation, stage affects test breadth and resilience or migration work. TDD, error propagation, and plan completion remain mandatory. MVP guidance can avoid preemptive production hardening, but it cannot justify skipping a planned surface, weakening accepted behavior, or implementing before tests.
Understand:
If anything in the plan is unclear or seems wrong given the current code, capture the question and route it through the coordination channel provided by the task context. Do not silently reinterpret the plan.
Work in dependency order, one slice at a time: complete a slice — behavior, tests, and its atomic commit — before starting the next.
The acceptance surface per slice is an outcome contract, not a choreography. A slice is done when:
Do NOT write all tests first, then all implementation. That is horizontal slicing: it produces tests that verify imagined behavior rather than actual behavior. Within a slice, order tests and implementation however works — the parent-commit evidence rule is the contract, not a step sequence.
Test behavior, not implementation. If you rename an internal function and a test breaks even though behavior is unchanged, that test was bad.
Mock only at system boundaries. External APIs, databases when a test DB is not practical, time, and randomness are valid boundaries. Do not mock your own modules or internal collaborators.
Integration tests for cross-layer behavior. When a slice touches callbacks, middleware, or multi-module interactions, write at least one test that exercises the real chain without mocks.
After each slice passes its tests, ask:
Skip for leaf-node changes with no callbacks, no state persistence, and no parallel interfaces.
Maintain docs/impl-notes/<issue-id>.md during implementation. Record only
what the code reviewer needs to know:
Notes are fresh-reviewer evidence. Record decisions as standing statements without review provenance: no review round numbers, no finding IDs, no "reviewer found X" or "fixed in commit Y" status claims. Whether something is fixed is the diff's job to show; a provenance trail hands the next fresh reviewer the previous reviewer's search map. Adjudication history belongs in the per-run scratch directory, not here.
Do not narrate routine implementation. Commit the notes file alongside the implementation when it contains information a reviewer needs.
For brief/standard plans:
For full plans (cross-cutting):
Only after the self-check passes, declare the implementation ready for review.
Before editing code, run the cvg-code-review-feedback skill. The input is the
reviewer blocker findings appended to the prompt, plus the current plan,
contract, implementation notes, diff, and changed files.
Do not treat reviewer findings as a patch list. First produce the
cvg-code-review-feedback intake summary, then repair only implementation-owned
findings under the accepted plan and contract. If the feedback exposes a plan
gap, contract gap, systemic design gap, or reviewer clarification need, callback
through the coordination channel instead of patching around the missing decision.
When feedback exposes a plan gap, contract gap, or systemic design gap, stop. Workers do not edit plans, contracts, surface matrices, or scope, and must not continue implementation until the planner or coordination channel resolves the gap.
After repair, include the cvg-code-review-feedback result, fixed findings, verification
gates, and remaining blockers in the callback or final implementation result.
During implementation you may discover that:
Capture it as a worker-discovered contract gap and callback through the coordination channel. Include:
Do not implement through a contract gap, even when the missing behavior seems small or obvious. The planner or coordination channel must update the plan or contract before implementation continues.
A contract gap is a missing plan-level decision: an unlisted surface, a new invariant, or externally visible behavior the plan never decided. An implementation-level choice the plan leaves open (an internal error shape, a private helper's structure) is not a contract gap — make the call and record it under Uncertain assumptions in the implementation notes; the review gate adjudicates it.
Orchestrate the build loop with split engines - Codex CLI sessions implement and take every first-pass review round while a high-taste Claude design model holds the final exit gate. Use when the user asks for a hybrid, split-model, or cross-model build loop, such as codex implementing with fable as the closer or final reviewer. Claude Code only.
Orchestrate the plan loop with split engines - a high-taste Claude design model drafts and revises the plan while Codex CLI sessions gate it as fresh plan reviewers. Use when the user asks for a hybrid, split-model, or cross-model planning loop, such as fable planning with codex reviewing. Claude Code only.
Review implementation against the plan and contract. Distinguish code bugs from contract gaps. Bounded convergence.
Orchestrate a monitored implementation loop where a worker implements the plan and fresh code reviewers gate the exit. Use when the user asks to run a supervised implementation or build loop on Codex threads or Claude Code background agents.
Orchestrate a monitored planning loop where a planner drafts the plan and fresh plan reviewers gate the exit. Use when the user asks to create or revise a plan through supervised specialist sessions on Codex threads or Claude Code background agents.
Review a plan against the actual codebase. Verify slices are sufficient, surfaces are complete, and invariants are correct.