e0ipso/strikethroo/st-refine-plan

st-refine-plan

Inputs

The user supplies the numeric plan ID conversationally, plus any optional refinement notes.

Operating Procedure

1. Locate the strikethroo root

Run scripts/find-strikethroo-root.cjs from the user's working directory. If it exits non-zero, stop and ask the user to run npx strikethroo init.

Treat the path it prints as <root> for every subsequent step.

2. Resolve the plan

Run scripts/validate-plan-blueprint.cjs <plan-id> planFile for the plan file's absolute path. Another field name prints that field instead.

If the script exits non-zero, stop and ask the user to confirm the plan ID. Do not guess a different ID.

3. Load project context

Read <root>/config/STRIKETHROO.md for this project's directory conventions. Read <root>/config/hooks/PRE_PLAN.md and execute its instructions before proceeding. Read <root>/config/templates/PLAN_TEMPLATE.md; the refined plan must still conform to it. Read <root>/config/shared/clarification-gate.md and apply it in the Clarification Loop.

4. Baseline Review

Read the entire plan end-to-end without modifying it. Record every contradiction and every gap you find under these lenses:

• Context gaps: missing background, assumptions, competing priorities.
• Technical gaps: underspecified architecture, unclear interfaces, missing diagrams.
• Risk gaps: untracked risks, missing mitigations, hand-wavy success metrics.
• Scope issues: gold-plating, ambiguous boundaries, requirements that

contradict YAGNI.

Document each one as {section, issue, severity, proposed fix}.

5. Clarification Loop

Default to Interactive Clarification. Switch to Autonomous Clarification only when one of these holds without interpretation:

• The user's request names the mode by intent, with a keyword such as "auto",

"autonomous", "non-interactive", "without asking me", or "don't ask".

• An upstream orchestrator (for example the st-full-workflow skill) declared

autonomous operation for this invocation in the prompt passed to this skill.

Otherwise use Interactive Clarification, even when the user's presence is uncertain. Do not infer autonomous mode from indirect signals such as terse prompts, scripted-looking input, or absence of recent user messages.

Either branch starts from the gaps documented in the Baseline Review. Think harder before raising one: only put forward an uncertainty you can cite. Append every resolution to the plan document's "Plan Clarifications" table in its existing question/answer format, marking each entry's source.

Interactive Clarification

Follow the clarification cadence in <root>/config/shared/clarification-gate.md.

1. Ask one question at a time per that cadence; never dump them as a batch.
2. Prefill each question with the most plausible answer, and always offer an

"Other / open-ended" option for the nuances you did not anticipate.

1. STOP AND ASK: Put each question to the user and halt execution to await

their input. Do not simulate the user's response. Do not proceed to step 6 until you have received explicit answers and confirmed the resolved scope.

1. Record a question the user cannot or will not answer as unresolved, with

mitigation notes so downstream assistants know the risk, then proceed with the available context.

1. Re-evaluate whether the answers opened new gaps. If so, repeat this loop.

Autonomous Clarification

1. Resolve each gap from the codebase, its configuration files, its

documentation, and the project's established patterns. Fall back to a reasonable assumption only where those do not answer it.

1. Mark each resolution's source as "auto-resolved" (confirmed in the

codebase) or "assumption" (best-effort guess, with its rationale).

1. Record a gap you can resolve neither way as unresolved, with mitigation

notes so downstream assistants know the risk.

6. Refinement Implementation

Refine the plan in place, at the path step 2 resolved.

1. Maintain Identity: Keep the existing id and directory. Never allocate

a new plan ID and never move the plan.

1. Structure Compliance: Keep the plan conformant to

<root>/config/templates/PLAN_TEMPLATE.md, adding any missing section.

1. Content Updates:

• Refresh the executive summary against the clarifications.
• Update the architectural sections, diagrams, and risk mitigations the

gaps named.

• Trim scope creep that is not explicitly required.
• Point each affected section back at the Q&A table.

1. Net-New Sections: Add a subsection the plan now needs (Decision Log,

Data Contracts) under Notes, clearly labeled.

1. Change Log: Append to Notes a bullet stating what this session

changed, such as - 2025-03-16: Clarified auth flow tokens and updated architecture diagram.

7. Run the post-plan hook

Execute <root>/config/hooks/POST_PLAN.md.

Before you write the final response, run scripts/check-for-updates.cjs "<root>" as a separate command using this skill's script path. Keep the user's working directory. Read the one JSON line on stdout. Never pause for permission and never run an update. When notice is present, append its exact text after the structured summary block, or after your final response when this skill emits no summary block. Nothing may follow the notice.

Failure Modes

• A helper script fails unexpectedly. Surface stderr to the user and

stop — do not fall back to manual path discovery.