Verify Multispec

verify-multispec workflow (v3)

Overview

2-phase sub-workflow mapping CLAUDE.md "Verify 阶段 — 关键发布 / 大重构 PR 升级 Agent Team Pattern C" onto harnessed runtime (Phase v3.0-3.4 W0.13e — D-04 Stage ④ Verify 7 sub + D-11 Agent Teams + Pattern A sub-workflow ship)。

| phase | id | upstream | model | capability | gate / on | | ----- | -- | -------- | ----- | ---------- | --------- | | 1 | 01-team-create | claude-platform | opus | {{ capabilities.agent-teams-create.cmd }} | parallelism: agent-teams-upgrade.fires; on: is_major_release OR is_large_refactor → invoke | | 2 | 02-team-cleanup | claude-platform | haiku | {{ capabilities.agent-teams-shutdown.cmd }} | mandatory 防呆清单 |

Per-phase config loads from workflows/verify/multispec/workflow.yaml; phase 01 creates 4 teammate (code-review + gstack-review + gstack-cso + gstack-qa) via TeamCreate, teammates 互相 SendMessage 质询 findings 是否真问题 (NOT fire-and-forget); phase 02 mandatory shutdown_request

• TeamDelete (bundled Agent Teams cleanup discipline)。

Capability refs

Sister workflows/capabilities.yaml entries:

• agent-teams-create — Bucket 5 Agent Teams (impl: claude-platform, cmd: TeamCreate)
• agent-teams-send-message — Bucket 5 Agent Teams (impl: claude-platform, cmd: SendMessage)
• agent-teams-shutdown — Bucket 5 Agent Teams (impl: claude-platform, cmd: TeamDelete)
• code-review — Bucket 1 mattpocock (teammate 1)
• gstack-review — Bucket 3 治理关卡 (teammate 2 Paranoid Staff Engineer)
• gstack-cso — Bucket 3 治理关卡 (teammate 3 安全审查)
• gstack-qa — Bucket 3 治理关卡 (teammate 4 端到端 QA)

Parallelism + on gate refs

Sister workflows/judgments/parallelism-gate.yaml:

• agent-teams-upgrade.fires — 5 OR-chain (teammatesendmessageneeded / subagentcontext_overflow /

sharedtasklist / opposinghypothesisdebate / fullstackthreeway)

Phase-level on clause (critical-release 升级触发):

• if: phase.is_major_release == true or phase.is_large_refactor == true → action: invoke
• else → action: skip

Routing rules (bundled Agent Teams routing — workflows/judgments/parallelism-gate.yaml)

• ✅ 触发: 关键发布 / 大重构 PR (≥3 specialist 需互相质询而非 fire-and-forget)
• ❌ 跳过: 常规 PR / 单点任务 (sister verify-code-review fan-out + verify-paranoid 已够用且省 token)
• Token 估算 prereq: team_cost 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-multispec — that is the CI/headless path (in-process SDK spawn that blocks the session inside Claude Code).

1. Bash: harnessed prompt verify-multispec --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-multispec --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
• D-11 Agent Teams 4-specialist Pattern C upgrade
• workflows/capabilities.yaml — agent-teams-{create,send-message,shutdown} + 4 specialist
• workflows/judgments/stage-routing.yaml — verify-multispec-critical-release trigger
• workflows/judgments/parallelism-gate.yaml — agent-teams-upgrade.fires (5 OR-chain)
• workflows/verify-work/workflow.yaml v2 SHIPPED phase 09-agent-team-multispecialist 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.