plan-phase workflow (v3)
Overview
2-phase sub-workflow mapping CLAUDE.md "Plan 阶段 — GSD + planning-with-files" onto harnessed runtime (Phase v3.0-3.4 W0.5 — D-04 Stage ② Plan 二层 + D-15 planning-with-files claude-code-plugin /plan + Pattern A sub-workflow ship)。
| phase | id | upstream | model | capability / invokes | artifacts |
|---|---|---|---|---|---|
| 1 | 01-gsd-plan |
gsd | sonnet | {{ capabilities.gsd-plan-phase.cmd }} |
(Wave A research + Wave B planner + Wave C plan-checker) |
| 2 | 02-persist |
planning-with-files | haiku | {{ capabilities.planning-with-files.cmd }} + invokes: /plan |
artifacts_expected: [task_plan.md, progress.md] |
Capability refs
Sister workflows/capabilities.yaml entries:
gsd-plan-phase— Bucket 2 (impl: gsd, cmd: /gsd-plan-phase)planning-with-files— Bucket 4 (impl: claude-code-plugin, cmd: /plan; requires theplanning-with-filesClaude Code plugin to be installed via the Claude Code plugin marketplace; outputs: task_plan.md + progress.md + findings.md)
Stage ② 铁律 — dual capability
GSD /gsd-plan-phase orchestrate (Wave A research → Wave B planner → Wave C
plan-checker) → planning-with-files /plan 持久化 (plugin 真生成 task_plan.md +
progress.md, NOT fs.writeFile self-impl per D-15 Q-AUDIT-5a claude-code-plugin
reframe)。
Invocation
- Slash command:
/plan-phase <num>(afterharnessed setup)
Output artifacts
task_plan.md— 主任务清单 + 文件路径 + 依赖 + 验收标准progress.md— phase 进度跟踪 + cross-session 恢复- (
findings.md由 discuss-* sub-workflow 产出, 此处不重复)
How to invoke
!harnessed checkpoint intent plan-phase
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
<workflow-intent>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 plan-phase — that is the CI/headless path (in-process SDK spawn
that blocks the session inside Claude Code).
- Bash:
harnessed prompt plan-phase --task "$ARGUMENTS" --json→ parse{prompt, max_iterations, model}. - Spawn a CC-native subagent (Task / Agent tool) with that
promptandmodel, then drive delivery with harnessed's own completion gate:- on return, write the subagent's final output to a file and run
harnessed checkpoint complete plan-phase --result-file <path>— it is fail-closed on the declared artifacts, the TDD boundary, and the verbatim<promise>COMPLETE</promise>. - if it blocks, run
harnessed checkpoint fail plan-phase --failing-tests <n>to record the attempt; it prints BUDGET-EXHAUSTED / NO-PROGRESS / BREAK-LOOP when a stop condition is reached. - respawn ONLY while none of those three has fired. Any one of them means stop: re-scope the subtask, fix the blocker, or escalate to the user. Never respawn past a stop directive.
- on return, write the subagent's final output to a file and run
- 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. - On
<promise>COMPLETE</promise>: write the subagent’s final output to a file, then Bashharnessed checkpoint complete plan-phase --result-file <path> --summary "<one-line>". Fail-CLOSED — it blocks unless every declaredartifacts_expectedfile exists, the TDD boundary passes (non-empty evidence / both the red and green sides present / the test file was not deleted), and the result carries a verbatim<promise>COMPLETE</promise>(or a structured COMPLETE status).--result <text>is the inline variant;--result-filewins and is quoting-safe on Windows.--forcerecords an audited override (evidence_status=overridden) — it does not silently pass. - If the complete gate blocked: Bash
harnessed checkpoint fail plan-phase --failing-tests <n>to record the attempt. It printsBUDGET-EXHAUSTED/NO-PROGRESS/BREAK-LOOPonce a stop condition is reached. Respawn ONLY while none of those three has fired; any one of them means STOP — re-scope the subtask, fix the blocker, or escalate to the user.
References
- D-04 Stage ② Plan 二层 (架构 / 计划)
- D-15 Q-AUDIT-5a planning-with-files claude-code-plugin reframe (NOT npm-sdk)
- workflows/capabilities.yaml — gsd-plan-phase / planning-with-files (Bucket 4)
- workflows/defaults.yaml — ralph_max_iterations.plan-phase.* values (W2.2 backfill)