Task Brief Creator Caveman

Task Brief Creator (Caveman)

Produce an executable implementation work plan under docs/briefs/ that one coding agent authors and another coding agent executes without reconstructing the route or re-interviewing the requester. The historical work-brief and handoff names remain activation aliases; the saved artifact's primary identity is a code-execution PLAN.

The plan is the execution artifact. Its job is to let a coding agent recover the first stage, intended order, stage deliverables and handoffs, replan boundaries, and whole-work completion criteria while routing to the right files and fixing the behavior envelope.

The plan is an executable work instruction — nothing else. It is not a scope-control memo, discussion summary, background briefing, or rationale document. Every section must answer "what does the coding agent do next?" — if a section reads like meeting minutes, negotiation history, or context prose, rewrite it until it routes to files, decisions, or verifiable outcomes. A plan that makes a coding agent reconstruct the execution sequence or re-interview the requester is a failed plan, regardless of polish.

"Executable, not discursive" is a prose style rule, not a content reduction rule. It tells you how each bullet should read — direct, action-routing, no rationale prose. It does not tell you to drop distinct concerns, merge unrelated bullets, or summarize the input down to its highlights. A brief that omits a concern from the input is also a failed brief, because the downstream agent will silently miss it. Tight prose, full enumeration: short bullets are fine and encouraged, but every distinct concern from the input and the codebase review must land somewhere in the brief. Caveman tightens prose further; it never tightens enumeration.

Modes

This skill operates in one of two output modes:

• Single-plan mode (default; historical single-brief name remains) — emits one executable work plan per invocation. The workflow below covers this case end to end.
• Briefset mode — emits a parent execution-management document plus N independently executable child briefs. Used when the input describes multiple execution contexts that need coordination (independent completion criteria, mixed work types, ordered dependencies, parallelizable waves, or shared conflict hotspots). It is selected by the criteria in references/briefset.md; long input, many files, or related edit points alone never trigger briefset mode.

Output-mode selection happens at Stage 1 alongside the ambiguity gate and is author-owned when the input and codebase make it evident. In briefset mode, follow the workflow below with the per-stage adaptations in references/briefset.md (parent template, naming, decomposition decision table, dual-validator save).

Stage 4 always runs an ownership pass. When user-owned decisions remain after codebase review, present only them in a Markdown table with 순번, 내용, 수정 추천안, and 근거. Codebase facts, output mode, evident work type, and reversible implementation choices are author- or worker-owned; product intent, scope, compatibility breaks, external ownership, and acceptance thresholds remain user-owned. The decision table is the ownership-pass output when rows exist, not a separate mode. See references/stage-4-interview.md for the full decision classification, codebase-precedence, and termination rules.

Code Agent Operating Path

Load references only when their decision point arrives:

1. Use this file for the stage order, output contract, save flow, caveman constraints, and guardrails.
2. Read references/caveman-style.md before composing or patching saved brief prose.
3. Read references/work-types.md during Stage 2 when the work type is not obvious or when the type changes downstream behavior.
4. Read references/briefset.md during Stage 1 when multiple execution contexts are plausible.
5. Read references/bloat-decomposition.md only after a candidate child brief is independently executable but still looks oversized or mixed.
6. Read references/stage-4-interview.md before the Stage 4 ownership pass, including requirements clarification and recommendations.
7. Read references/template.md while composing the saved Markdown.
8. Read references/cold-pickup.md when the Stage 5.7 gate fires or the user forces cold-pickup.

Do not re-open every reference by habit. The goal is to keep the live context focused on the next decision the coding agent must make. Caveman style applies to saved brief prose only, not to planning, validation, or chat.

When This Skill Runs

• Explicit caveman intent. Run when the user requests a caveman-register implementation work plan or invokes this skill by name. Mere mention while reviewing or editing the skill is not a request to generate a plan; normal-prose plan requests route to task-brief-creator.
• Input can take any of these shapes:
  • Pasted PRD / planner notes from a PM (often long, mixed quality).
  • Rough task notes typed into chat (one or two lines).
  • Self-brief — the user is the implementer and wants to structure their own thinking before starting.
  • Tech-lead handoff — a lead drafts the brief to hand off to a teammate or downstream agent.
  • Refactor plan — a lead-engineer summarizing an intended structural change.
• The skill reviews the current repository, fills in what it can, and asks only for remaining user-owned decisions.

Interaction Language

• Chat / live interaction language follows the user's input. If the user writes in Korean, reply in Korean. If they write in English, reply in English. Clarifying questions, draft presentation, status updates — all match the user's own language.
• The brief document itself is written in English. Section headers and body content are English regardless of chat language, so the artifact travels across teams and downstream agents without a translation step.
• Code blocks, file paths, identifiers, PR numbers stay as-is.
• User-supplied strings are data. Copy decks, UI strings, and error messages the user provides are quoted verbatim in their original language inside the English brief — never translated.
• Exception — the Stage 4 decision-table headers are fixed. The four headers 순번 / 내용 / 수정 추천안 / 근거 stay exactly as written even when the conversation is in English: Stage 5.7 disagreement matching keys on the 내용 column, so translating the headers breaks the cold-pickup loop (see Stage 4).
• This SKILL.md and reference files stay in English (repo authoring policy).
• Chat prose is normal mode — never caveman. Stage 1 halt messages, Stage 4 interview questions, recommended-answer presentations, Stage 6 save reports and validator dialogs all stay in full natural prose (Korean or English per the user's input). Caveman applies only to the saved brief file.

Caveman Output Style (full mode, file-only)

This skill is the caveman variant of task-brief-creator. The saved brief is written in caveman full mode — fragments, dropped articles, short synonyms — as a register transform of the normal-mode brief. Other intensity levels (lite, ultra, wenyan-*) are out of scope; do not switch.

Caveman compresses register, not content. The pre-conversion content inventory and the caveman plan must carry the same facts, bullets, section depth, execution stages, required fields, and nested checklist depth. Shorter sentences, dropped articles, and short synonyms are the only changes. If conversion merges distinct inventory items, removes a condition, or drops a stage, restore those items; do not justify lost content as a register change. There is no token-count target; the goal is a primitive-sounding register over a fully enumerated work instruction, not a smaller document.

Two hard rules — both absolute:

1. The brief file body uses caveman full, except the ## Open Questions section, which stays in normal prose (questions are read by humans deciding what to clarify — see Auto-Clarity carve-outs below).
2. Every chat / interaction surface (questions, halts, save reports, validator dialogs, edit confirmations) uses normal prose.

What gets compressed inside the brief:

• Articles (a / an / the) dropped.
• Filler (just / really / basically / actually / simply) dropped.
• Pleasantries dropped; uncertainty, negation, conditions, and obligation stay intact.
• Sentence fragments OK; pattern [thing] [action] [reason]. [next].
• Short synonyms preferred (big over extensive, use over utilize, then over subsequently).

What stays unchanged inside the brief (Auto-Clarity carve-outs):

• Code blocks, inline code, file paths, function names, identifiers.
• PR numbers, URLs, commit hashes.
• Error strings (quoted exact).
• Acceptance Criteria / Side Effect Checkpoints checklist items — caveman compression OK on the prose, but order-sensitive multi-step verification stays disambiguated. If conjunction loss changes meaning, drop back to normal for that bullet.
• Reproduction steps where step order matters.
• Behavior Contract invariants and verification methods.
• Constraints legal / API-shape constraints.
• Section headers, the title # [<type>] <title>, and the ## Work Type value (feat, refactor, …).
• The escape-hatch token - N/A — <reason> for type-conditional sections.
• The entire ## Open Questions section body. Questions are read by humans deciding user-owned choices; caveman fragments lose nuance. Write each bullet in complete normal-prose - [non-blocking] ... — Default: ...; Reconfirm before: ... form.
• Execution Plan stage headers, field labels, field order, and Ends when indentation. Compress field values only; preserve stage count, handoff recipient, deliverable, and replan meaning.
• [confirmed] / [inferred], Evidence:, and Confirm by: tokens.

When in doubt — if compression creates technical ambiguity — write that bullet in normal prose. Caveman never wins over correctness.

See references/caveman-style.md for the full conversion rules, section-by-section guidance, and good/bad examples.

Output Contract

Example filename: 2026-04-23-feat-global-hotkey-system.md

If docs/briefs/ does not exist, create it. If a file with the same name already exists, append -v2, -v3, … until the path is unique — do not overwrite.

For briefset mode, the parent uses YYYY-MM-DD-briefset-<set-slug>.md and children use YYYY-MM-DD-<type>-<set-slug>-NN-<child-slug>.md. See references/briefset.md for the parent template and naming rules.

The nine required H2 sections are: Work Type, Current State (As-Is), Desired Outcome (To-Be), Scope (with In Scope / Out of Scope H3s), Related Files / Entry Points, Execution Plan, Side Effect Checkpoints, Acceptance Criteria, Open Questions. Optional Constraints may appear between Scope and Related Files / Entry Points when task-specific constraints exist. Execution Plan appears immediately after Related Files / Entry Points and before Side Effect Checkpoints. Put stage-local completion under each stage's Ends when. Reserve Acceptance Criteria for whole-work completion after all required stages and side-effect checkpoints finish.

Three work types require an additional H2 section between Current State (As-Is) and Desired Outcome (To-Be):

• fix → ## Reproduction
• perf → ## Baseline Measurement
• refactor → ## Behavior Contract

These exist because the work type changes the downstream agent's behavior (reproduction-first, measurement-first, behavior-preservation), and the brief must carry the type-specific input that behavior depends on. The escape hatch when the section legitimately has nothing concrete to capture is a single bullet - N/A — <reason>. See references/template.md and references/work-types.md for the per-section guidance.

Bullet count is not capped. The rule is cohesion plus completeness, not brevity:

• Each bullet should describe one coherent unit of context, scope, risk, or verification.
• Enumerate every distinct concern. If the input or the Stage 3 codebase review surfaces N distinct concerns that map to a section, the section gets ≥ N bullets. Sections expand to fit the work; they are not capped. A section reduced to one bullet when the input contained multiple concerns for it is the failure mode this rule exists to prevent.
• Do not merge unrelated concerns into one bullet just to keep the document short. Caveman never merges bullets — it shortens each bullet's prose.
• Write as many bullets as the task needs; do not compress larger work into vague combined bullets. Short prose per bullet is fine and encouraged — short count is the failure.

Completeness does not mean every discovered issue enters scope. Triage findings into must fix, check while here, and defer / record. Keep must-fix plus tightly coupled checks in scope; put unrelated valid findings in [deferred] Out of Scope. Use Open Questions only for non-blocking user-owned decisions with safe default and reconfirm milestone. If more than five independent must-fix concerns remain after triage, reconsider briefset mode or ask user to choose first slice only when slicing is a user-owned scope decision.

Workflow

Stage 1 — Ambiguity Gate (HALT or CONTINUE)

Before full codebase review, check whether the input contains enough signal to ground the brief. Use the four-anchor heuristic:

Count how many anchors are derivable from the input. Derivable = a reasonable engineer could answer the anchor from the user's input without inventing intent.

• All 4 anchors present → CONTINUE to Stage 2.

• 3 anchors present, TARGET missing → run a narrow target probe before deciding. Use at most a few rg / glob queries to find likely files, directories, routes, commands, or modules. If a concrete entry point emerges, CONTINUE. If not, HALT and ask the user for the target area.

• 3 anchors present, PROBLEM or GOAL or SCOPE missing → CONTINUE only when the missing anchor can be stated in one concrete sentence derived from the input (write that sentence into the brief; vague fillers like "make it better / cleaner" do not count). Otherwise HALT and ask for that anchor. Detail that survives this check gets filled in Stage 3 via codebase review or Stage 4 via user questions.

• 2 or fewer anchors present → HALT. Respond in the user's chat language naming exactly which anchors are missing, and ask for more input. Do NOT proceed through Stages 2–6 on an underspecified input. The briefset-mode check below also waits — never split an underspecified input into multiple equally underspecified child briefs. Example halt messages:

  English:

  I can't ground the brief from this input alone. Missing — PROBLEM (what is being fixed or changed) and TARGET (which area / file / subsystem is touched). Can you paste the spec or add one or two lines?

  Korean:

  입력만으로는 브리핑 만들기 어려워. 다음이 아직 확인 안 돼 — PROBLEM(뭘 고치거나 바꾸는지)과 TARGET(어느 영역/파일/시스템을 건드리는지). 더 얹어줄래? 기획서 붙여넣거나 한두 줄 더 써주면 돼.

Why halt instead of guess: an underspecified brief is worse than no brief — the downstream agent commits to the wrong problem framing and the rework cost eats the whole savings. Pushing back early is cheaper than producing a confident-looking but wrong document.

Edge case — pasted spec that looks long but is content-light: word count is not a proxy for the four anchors. A 2,000-word product narrative without a concrete PROBLEM or TARGET still halts. Judge by anchor coverage, not length.

See examples/03-halt-ambiguous.md for a worked halt case.

Briefset signal check (after CONTINUE): once anchors clear, also evaluate whether the input describes multiple execution contexts. Do not use file count, line count, input length, or several related edit points as triggers by themselves. Those are supporting evidence only.

If briefset signals are strong, select briefset mode and state evidence before Stage 2. If candidate contexts are fully independent — no ordering, dependencies, or shared conflict hotspots — select separate single-plan invocations instead; empty coordination parent adds overhead. If evidence unclear, default to single-plan mode. Ask only when topology depends on user-owned delivery boundary, release unit, or scope choice; do not ask user to choose document shape when code and input settle it. Several stages inside one cohesive execution context do not justify briefset mode; consult references/bloat-decomposition.md before splitting oversized candidate.

Stage 2 — Work Type Selection

Determine the Conventional Commits type. Consult references/work-types.md for the full list and per-type behavior hints.

• If the input explicitly names a type (e.g., "this is a refactor"), use it when the input evidence agrees.
• If named type conflicts with described outcome, classify by outcome and record mismatch; ask only if resolution requires user-owned behavior or scope choice.
• If type is implicit but high-confidence, assign without confirmation round-trip.
• If type is low-confidence but technically resolvable, probe codebase or put distinction into first Execution Plan stage as investigation with Replan when boundary.
• Ask in Stage 4 only when type depends on product or scope choice user owns; derive type from answer.

See references/work-types.md for author-selection routing table.

Stage 3 — Codebase Review

The goal is enough context to fill Current State (As-Is) and Related Files / Entry Points, not exhaustive exploration. Use whatever code search / read / symbol tooling fits the host environment and repository guidance — default Grep / Read / Glob, allowed semantic tools, language servers, or a short-lived subagent (e.g. Explore) when parallel lookups or main-context isolation is worth it. Tool choice is the runtime's call; this stage only fixes the purpose and budget of the review.

Review budget (soft limits):

• At most ~15 file reads
• At most ~10 search queries
• Stop when you can confidently enumerate the primary entry points and major affected areas implied by the input — not just the first file or symbol that grounds the brief. If likely input-implied surfaces remain unverified within review budget, add bounded investigation stage with named deliverable and Replan when condition.

Strategy:

1. Start wide with keyword search on terms from the input — feature names, function names, error strings, routes, type names.
2. Narrow to a list of candidate files, then read the 2–4 most promising ones.
3. If the input mentions a subsystem (e.g., "auth middleware", "checkout flow"), look at likely directories first.
4. Capture an As-Is picture by coherent context units: how each relevant function, module, behavior, integration, or user surface is shaped today.
5. Capture concrete Related File / entry-point hints with one-line purposes. At least one entry point must be solid before saving the brief.

Active judgement:

• Let the user's goal drive any extra probing. If first code reads surface a nearby signal that could change work direction — dependency, style hook, comment, product doc, older brief, or unused surface clearly tied to the same feature — check just enough to decide how it affects the brief. Do not turn this into mandatory repo-wide audit.
• Prefer a reasoned recommendation over asking the user. If a nearby signal is relevant but not required for the requested slice, encode the judgment in Constraints, Out of Scope as [deferred], Side Effect Checkpoints, or Acceptance Criteria. Ask only when the choice changes product behavior, scope, ownership, or acceptance in a way the requester must own.
• Separate implementation completion from user / operator success when both exist. Code may already expose a pass condition, event, return value, validator status, or stored state that says "done"; user-facing or operator-facing success may be different. Capture both when they matter: put existing pass condition in Current State (As-Is) / Side Effect Checkpoints, and put intended observable outcome in Desired Outcome (To-Be) / Acceptance Criteria.
• If a nearby signal is weak, mention it in the Stage 6 save report instead of bloating the brief. Brief stays executable; report can carry useful "noticed while reviewing" context in normal prose.

Evidence discipline:

• Mark load-bearing findings as confirmed when codebase review directly verified them. A confirmed finding cites the file and a stable locator: section heading, function / class name, validator message, command output, or nearby quoted token. Line numbers are useful as secondary hints, but do not rely on line numbers alone because they drift after edits.
• Mark risk statements as inferred when they describe likely downstream behavior rather than a fact already present in a file. Name what confirms inference, such as validator fixture, execution-reconstruction check, or specific command.
• Do not write inferred risk as confirmed defect. Caveman output may sound terse, but it must still let downstream agent tell evidence from judgment.
• Prefix every load-bearing Current State (As-Is) bullet with [confirmed] or [inferred]. Caveman keeps evidence token and stable locator/probe explicit. Validator checks label shape only; Stage 5.6 and human review own truthfulness.

Contract discipline:

• Name existing contracts that must keep speaking old shape while change lands. Contracts can be public APIs, persisted ids, database rows, event names, config keys, file formats, CLI flags, i18n keys, analytics events, generated schemas, or cross-process payloads.
• Put contract-preservation facts in Constraints or Side Effect Checkpoints, not as vague Out of Scope filler. Good: - [ ] Existing saved sessions with status "pending" still deserialize. Bad: - [ ] Do not break compatibility.
• If requested outcome requires changing a contract, surface compatibility choice in Stage 4 unless user already explicitly approved the break.

Source-of-truth inputs. When the user provides a checklist, TODO file, review rubric, audit notes, or any document as the source of truth, do not turn it into a representative summary.

• Treat each listed item as required concern until mapped, explicitly deferred / out of scope, or represented as non-blocking user-owned Open Question with safe default.
• Preserve the source's own dimensions, such as named variants, files, examples, sections, or checklist groups. Do not collapse them unless the user asks for a summary rather than an executable brief.
• Use searches only for literal terms that come from the user's source document or the target files being reviewed. Do not invent generic banned-pattern searches unless the user, repository rules, or source document defines those patterns.
• The saved brief does not need to expose an internal ledger, but Stage 5.6 must be able to trace each source item to a concrete bullet or checklist item. Caveman wording must not merge two source items into one bullet just to sound shorter.

If source document is long, keep private coverage ledger. Every source item must end as in scope, out of scope/deferred, execution stage, acceptance criterion, side-effect checkpoint, related file, constraint, or structured non-blocking question.

Do not:

• Read entire large files when symbolic / targeted-range reads suffice.
• Chase tangential code just to pad the brief. If it does not tighten Current State (As-Is) or Related Files / Entry Points, skip it.
• Make architectural claims the code does not support. If uncertain, label it [inferred] and route confirmation into investigation stage or Replan when boundary.

Already-satisfied gate. Before Stage 4, compare full requested outcome and acceptance boundary against current code plus current verification signals.

• If all requested outcomes are confirmed, all acceptance checks already hold, and no edit, integration, migration, or evidence-producing work remains, create no plan. Report no-work-needed in normal chat prose with inspected paths, verification action, and observed signal, then stop.
• If user explicitly asked for saved verification record despite already-satisfied state, create verification-only plan that expects no edits and records no-change evidence route. First stage must also say failure route: stop dependent work, return to owning plan, activate bounded correction plus re-verification work, then recalculate briefset topology and handoffs before continue.
• If only part of outcome is already satisfied, keep remaining work and make no-change branch explicit instead of directing unconditional edit.
• In briefset mode, re-run topology after this gate: zero active children means no-work-needed, one means single-plan mode, and two or more retain briefset mode. Follow references/briefset.md for child and handoff rules.

This outcome is called no-work-needed; do not confuse it with Stage 5.7 No-op pass, which describes review-loop termination.

Stage 4 — User Decision Table

After Stage 3 has enough context, run ownership pass and collect only remaining user-owned decisions into Markdown decision table. Stage 4 is not a pre-review guessing interview: ask only after the codebase has been checked enough to state the uncertainty, the recommended change, and the evidence behind it.

Use this exact table shape for user-decision questions:

| 순번 | 내용 | 수정 추천안 | 근거 |
|---|---|---|---|
| 1 | <decision the user must make> | <recommended change to apply to the brief> | <codebase/input evidence and risk> |

Keep these four headers exactly as written, even when the surrounding conversation is not Korean. They are the stable decision-table contract: number, decision content, recommended change, and rationale.

Intent before enumeration. Preserve each requirement's meaning, not an unresolved interpretation of its words. If input and bounded review leave multiple plausible goals, behaviors, scope boundaries, or completion criteria, ask the user before treating one interpretation as the task. Use the existing decision table to show the ambiguity, concrete alternatives, recommended interpretation, and supporting evidence. Distinguish a missing condition needed for the stated goal from an optional enhancement; label recommendations as proposals, not existing requirements. Offer only task-relevant additions. An unanswered optional enhancement stays excluded; do not enlarge the plan to make it look more complete. Ask first and allow an opportunity to answer. If no answer arrives and a safe fallback exists, save it with its reconfirmation milestone in Open Questions; never label it approved. If no safe fallback exists, halt without saving. A task cancellation stops authoring; it is not permission to use fallbacks and continue.

User-owned gaps to close before drafting:

• Desired Outcome (To-Be) — confirm when absent, ambiguous, or when the codebase review suggests more than one plausible interpretation.
• Out of Scope — the most valuable guardrail for the downstream agent. Put unclear or high-risk scope boundaries in the decision table with a recommended exclusion/inclusion.
• Acceptance Criteria — what makes the task verifiably done. If code has a separate internal completion condition and user has a separate success condition, carry both instead of collapsing them into one vague criterion.
• Compatibility and ownership — ask before breaking contract or crossing externally owned boundary.
• Open Questions — keep only non-blocking user-owned decisions with safe fallback and reconfirm milestone.

Author determines output mode, work type, entry points, side-effect checks, and technical sequencing when input and codebase make them evident. Technical unknowns become investigation stages, bounded Worker decision fields, Replan when conditions, constraints, or author-selected defaults. Ask the user for relevant observations or access details only when they hold information unavailable from the reviewed artifacts; do not ask them to perform the technical investigation.

Decision-table rule. Each row must request a real decision or a specific unavailable user-held observation, not a vague status note. 내용 states what the user must decide. 수정 추천안 states the concrete brief change you recommend. 근거 cites the input, codebase finding, existing pattern, or risk. After the user answers, patch the draft plan in memory before composing the brief. An unanswered or skipped question is not approval: non-blocking rows use their declared safe fallback, remain in structured Open Questions form, and proceed; any blocking row halts without writing. Full decision classification, table rules, and termination rules live in references/stage-4-interview.md.

Before writing Open Questions:

• Make one active judgement pass. Ask: would a downstream coding agent still need to ask the requester what to do, or can the brief make a reasonable call?
• Do not use Open Questions to avoid making an implementation recommendation. If answer is reasonable bounded choice, put it into Worker decision, Constraints, or relevant execution stage.
• Keep Open Questions for user-owned decisions only. Product direction, scope expansion, compatibility breaks, acceptance thresholds, and external ownership can require question.
• Save question only when non-blocking; use exact normal-prose form - [non-blocking] <question> — Default: <safe fallback>; Reconfirm before: <stage or milestone>.
• If user has not answered blocking decision and no safe fallback exists, HALT and create no file.
• Open Questions: None is acceptable only after this pass. It means "downstream agent can proceed without re-interviewing requester," not "nothing interesting was found."

Stage 5 — Save + Validate

Once Stage 4 closes, compose the final Markdown internally and write it straight to disk — do not paste the full brief into chat first. The user reviews the file in their editor in Stage 6, where real markdown rendering and diff tooling are available.

1. Compute the filename per the Output Contract above.

2. Ensure docs/briefs/ exists; create it if not.

3. Resolve filename collisions by appending -v2, -v3, ….

4. Render the complete template from references/template.md and write the file (English section headers, English body in caveman full mode — see references/caveman-style.md for conversion rules and the Auto-Clarity carve-outs that stay in normal prose).

5. Run the structural validator — a fast smoke test for the template contract:

   python3 <skill-dir>/scripts/validate_brief.py docs/briefs/<filename>.md
   

   If brief is stored in isolated artifact tree while entry-point paths belong to another checkout, add --repo-root <repository-root> before brief path.

   <skill-dir> is the installed skill package directory — the directory containing this SKILL.md (resolve it from wherever this skill was loaded, e.g. ~/.claude/skills/task-brief-creator-caveman or a plugin cache). Never assume the user's repository contains the script: the brief lives in the user's repo, the validator lives with the skill.

   • Exit 0 → continue to Stage 5.5; the validator result is reported in the Stage 6 banner.
   • Exit 1 (structural failure) → fix file and rerun validator without asking user. If same structural cause still fails after two repair attempts, leave file in place and carry residual failure into Stage 6.
   • Exit 2 (file I/O error) → inspect the actual error: invalid arguments, invalid --repo-root, missing artifact, or unreadable file. Correct the cause; do not infer that a saved file disappeared or recreate it unnecessarily.

   The validator only checks structural conformity (section presence, checklist format, filename pattern, type coherence). It does not judge content quality — Stage 5.5 execution reconstruction, Stage 5.6 self-check, Stage 5.7 cold-pickup, and human review do that. Passing validator ≠ good brief; failing validator = malformed brief.

Shared Validation Budget and Artifact State

A validation run covers the single plan or the entire parent-and-children set. It has at most five rounds, including the initial round. A round starts from one saved artifact state, runs structural validation, Stage 5.5, Stage 5.6, and gated Stage 5.7 in that order. Keep the existing two-repair limit for the same structural cause; structural repairs before Stage 5.5 remain inside that round. Any content edit after Stage 5.5 starts the next round from structural validation; do not restart a stage-local unlimited loop or reset the counter for a child. Collect briefset reports against the same artifact state before applying related patches together. Unchanged children need not be rewritten, but each round still covers every required document. At each round start, snapshot all authored files to a unique scratch directory outside the repository and record the round, file membership, content hashes, findings, decisions, and checks actually completed. Do not apply a content patch unless a round remains to validate it. At round five, retain the latest well-formed artifact or restore a previously checked snapshot when a demonstrated regression requires it; stop automatic repairs and report remaining gaps. Restoration is set-wide: restore parent and affected children from the same recorded state, remove only files created by this run that are absent from that snapshot, and rerun structural validation. Reuse an earlier semantic result only for exactly the restored content hashes and unchanged input/decisions; otherwise report it unverified. Restoration does not open a sixth repair round. A new user answer or requested edit starts a new validation run. An internal retry, unavailable agent, or renamed file does not reset the budget. Delete scratch snapshots after the final state and residuals have been reported. The Stage 5.7 reference uses this shared bookkeeping and adds no per-child retry budget.

Stage 5.5 — Downstream Execution-Reconstruction Check

After structural validator passes, run blind downstream execution-reconstruction check before cold-pickup. This is not a review prompt and not a rubric-driven validation prompt. Purpose: observe how fresh coding agent naturally reconstructs saved plan as work to start. Explanation must recover first stage, intended order, each stage deliverable and addressable handoff, verification input and expected signal when present, any no-change branch, replan boundaries, and whole-work completion basis after side-effect checks. This checks direction and executability, not full input coverage; Stage 5.6 remains coverage check.

Use a new sub-agent with no inherited conversation, prior findings, or reused reviewer context, and enforce a read-only task boundary. Send only a natural work-start request in the user's ordinary style, containing the saved brief path. The agent explains intended work; it must not execute the plan, edit files, or run its implementation commands. If independent context or read-only operation cannot be provided, or the agent fails without a usable result, record Stage 5.5 as unavailable with the reason. Do not claim an aligned reconstruction or substitute an informed self-review. For briefset mode, include only the briefset parent path. Do not include the original user request, Stage 3 findings, Stage 4 decisions, suspected gaps, validation criteria, expected answer format, or any hint about what might be wrong. Do not ask the sub-agent to "verify", "review", "audit", "compare", or "find missing items". Chat stays normal prose; the work-start request is not caveman.

Example shape only — do not hard-code this sentence:

<brief path> 작업 진행할꺼야. 우선 이 브리프 파일을 확인하고 어떻게 작업할껀지 의도 설명해줘.

Compare natural reconstruction against original request, saved Execution Plan, and user-locked Stage 4 decisions. Treat only material drift as a failure:

• The work purpose is different.
• The understood scope is materially wider or narrower.
• The first work direction points away from the intended entry points or workflow.
• First stage, intended order, stage deliverable, handoff, or replan boundary cannot be recovered.
• Stage-local Ends when checks are confused with whole-work Acceptance Criteria.
• A user constraint, exclusion, or acceptance threshold is missing from reconstruction.
• The sub-agent assumes work that the brief did not intend.
• Caveman compression made execution reconstruction ambiguous or wrong.

If material drift appears, patch only within the shared round budget, restart from structural validation, and run a fresh execution-reconstruction check with the same information boundary. Do not fix drift by changing the sub-agent prompt. Fix the brief.

This check is mandatory whenever the host can spawn a sub-agent. Do not downgrade it to a self-check because the plan looks obvious or because Stage 5.6 is clean.

If host cannot spawn sub-agent, report execution-reconstruction check unavailable in Stage 6. Do not block the workflow waiting for sub-agent support; continue to Stage 5.6 and mark Stage 5.5 as unavailable in the save report. Do not replace it with a self-check; the point is the downstream agent's natural read.

Stage 5.6 — Content-Level Self-Check

The structural validator confirms the file has the required sections. It does not confirm the file is a complete work instruction. Before handing off in Stage 6, re-read the saved brief from disk and run a content-coverage self-check against the original input plus Stage 3 / Stage 4 findings. This checks whether input and codebase concerns survived into the plan; do not treat a clean Stage 5.5 reconstruction as proof that nothing is missing.

The brief is a work instruction, not a summary. Caveman compresses how the brief reads, never what it contains — so this self-check is identical to the normal-mode skill's check, plus one caveman-only parity item. Run this checklist:

• Input coverage: every distinct concern named in input maps to at least one bullet or stage (In Scope, Out of Scope, Related Files, Execution Plan, Constraints, Side Effect Checkpoints, Acceptance Criteria, or structured non-blocking Open Questions). If spec section is not implemented now, it appears in Out of Scope as [hard] / [deferred],

…(truncated)