Verify Code Review

verify-code-review workflow (v3)

Overview

1-phase sub-workflow mapping CLAUDE.md "Verify 阶段 — code-review 多 agent 并行" 章节 onto harnessed runtime (Phase v3.0-3.4 W0.11 — D-04 Stage ④ Verify 7 sub + 子任务并行 机制 subagent default routing 机器化 + Pattern A sub-workflow ship)。

| phase | id | upstream | model | capability | parallelism | | ----- | -- | -------- | ----- | ---------- | ----------- | | 1 | 01-code-review | mattpocock-skills | sonnet | {{ capabilities.code-review.cmd }} | judgments.parallelism-gate.subagent-default.fires |

Per-phase config loads from workflows/verify/code-review/workflow.yaml; engine spawns multiple subagent in parallel fan-out (bundled subagent-default rule — Task / Agent 工具 spawn 多任务并发, context 隔离, summary 折叠回主 context)。

Capability refs

Sister workflows/capabilities.yaml entries:

• code-review — Bucket 1 mattpocock 高频招式 (impl: mattpocock-skills, cmd: /code-review)

Parallelism gate ref

Sister workflows/judgments/parallelism-gate.yaml:

• subagent-default.fires — subtask.parallel_count The banner above (when present) means this invocation is REGISTERED with the engine (an intent marker) — not yet compliant: the steps below (prompt → spawn → checkpoint complete) resolve it, and a per-turn ` reminder persists until they run.

The numbered sequence below is the state machine — execute it with Bash. Do NOT improvise an equivalent flow from the Overview above: freelancing bypasses the engine (no ledger, no evidence guard). harnessed gives you the spawn-ready prompt; YOU spawn the subagent with a CC-native Task / Agent tool (keeps the session responsive + lets clarification round-trips reach the user).

Do NOT pipe to harnessed run verify-code-review — that is the CI/headless path (in-process SDK spawn that blocks the session inside Claude Code).

1. Bash: harnessed prompt verify-code-review --task "$ARGUMENTS" --json → parse {prompt, max_iterations, model}.
2. Spawn a CC-native subagent (Task / Agent tool) with that prompt + model, wrapped in the ralph-loop plugin: /ralph-loop "" --max-iterations --completion-promise "COMPLETE". If the plugin is absent, use the native goal gate instead (Claude Code 2.1.139+ / Codex): /goal "this subtask is delivered: the subagent's final output contains verbatim COMPLETE; or stop after turns" then spawn the subagent and let the goal evaluator drive re-spawns until it clears. If /goal is unavailable too, self-loop: spawn → check output for COMPLETE → re-spawn with prior output appended (up to max_iterations). Set the goal only at the leaf subtask level — /goal is single-slot per session and a nested goal overwrites the outer one.
3. If the output contains STATUS: NEEDS_CLARIFICATION + a question list: STOP, relay them verbatim via AskUserQuestion, append the answers to the spec, then re-spawn the same sub.
4. On COMPLETE: Bash harnessed checkpoint complete verify-code-review --summary "". The evidence guard runs here (fail-CLOSED): if a declared artifacts_expected file is missing it exits non-zero — re-spawn to produce it before treating the sub as done.

References

• D-04 Stage ④ Verify 7 sub 分解
• workflows/capabilities.yaml — code-review
• workflows/judgments/parallelism-gate.yaml — subagent-default.fires
• workflows/defaults.yaml — ralphmaxiterations.verify-code-review.* values (W2.2 backfill)
• workflows/verify-work/workflow.yaml v2 SHIPPED phase 03-code-review-parallel sister verbatim

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: easyinplay
• Source: easyinplay/harnessed
• License: Apache-2.0
• Homepage: https://harnessed.cc/

Install and usage instructions live in the source repository linked above.