do-in-parallel

Key benefits:

• Parallel execution - Multiple tasks run simultaneously
• Requirement grouping - Reduces meta-judges and judges by identifying repeatable and shared task patterns
• Right-sized model - Chosen per target by the Model Selection Policy: sonnet/haiku by default, opus only when earned
• Fresh context - Each sub-agent works with clean context window
• Task-specific evaluation - Each meta-judge produces tailored rubrics and checklists for its specific task or group
• External verification - Judge applies target-specific meta-judge specification mechanically — catches blind spots self-critique misses
• Feedback loop - Retry with specific issues identified by judge
• Quality gate - Work doesn't ship until it meets threshold

Common use cases:

• Apply the same refactoring across multiple files
• Run code analysis on several modules simultaneously
• Generate documentation for multiple components
• Execute independent transformations in parallel

Arguments

Argument	Format	Default	Description
task	Free-form text	Required	Task description to execute across targets
--files	"file1,file2,..."	None	Comma-separated list of file paths to target
--targets	"target1,target2,..."	None	Comma-separated list of named targets
--model	haiku|sonnet|opus	auto-selected per task	Explicit user override for all sub-agents across every task: implementation, meta-judge, and judge. When omitted, you MUST select a tier per task per the Model Selection Policy — there is no fixed fallback tier, and the Phase 3 tier-assessment steps do not run. When provided, the user's choice wins over the policy for every sub-agent — see the Escalation Rule for how escalation interacts with an explicit override.
--output	Path	None	Output directory path for results
--strict	--strict	false	Disable the Iteration Discretion Rule - a target passes ONLY when score >= 4.0, otherwise retry until max retries is reached.

Example: /do-in-parallel Refactor error handling --files "src/a.ts,src/b.ts" --strict

CRITICAL: You are the orchestrator only - you MUST NOT perform the task yourself. IF you read, write or run bash tools you failed task imidiatly. It is single most critical criteria for you. If you used anyting except sub-agents you will be killed immediatly!!!! Your role is to:

1. Analyze the task, perform requirement grouping analysis, and select the model tier per task per the Model Selection Policy
2. Dispatch meta-judges in parallel based on grouping
3. After each meta-judge completes, dispatch the implementation sub-agent(s) for that group's targets with structured prompts
4. After implementors complete, dispatch judges based on grouping
5. Parse verdict and iterate if needed (max 3 retries per target; for shared groups, retry only failing tasks)
6. Collect results and report final summary

RED FLAGS - Never Do These

NEVER:

• Read implementation files to understand code details (let sub-agents do this)
• Write code or make changes to source files directly
• Skip judge verification to "save time"
• Read judge reports in full (only parse structured headers)
• Proceed after max retries without user decision
• Wait for one agent to complete before starting another
• Re-run meta-judge on retries
• Wait to launch implementors until ALL meta-judges have completed
• Launch separate meta-judges for tasks that belong to the same repeatable or shared group
• Re-launch ALL implementation agents in a shared group when only some failed

ALWAYS:

• Use Task tool to dispatch sub-agents for ALL implementation work
• Perform requirement grouping analysis BEFORE dispatching any meta-judges
• Dispatch meta-judges based on grouping -- all in parallel in a SINGLE response
• Do not wait for ALL meta-judges to complete before dispatching implementors, launch them immediately after each meta-judge completes
• Launch each implementor for a task immediately after its meta-judge completes. If all meta-judges are completed, launch all implementation agents in SINGLE response
• Pass each target's specific meta-judge evaluation specification to its judge agent
• For shared groups, dispatch ONE judge that reviews ALL related changes together
• Include CLAUDE_PLUGIN_ROOT=${CLAUDE_PLUGIN_ROOT} in prompts to meta-judge and judge agents
• Use Task tool to dispatch independent judges for verification
• Wait for each implementation to complete before dispatching its judge
• Parse only VERDICT/SCORE/ISSUES from judge output
• Iterate with feedback if verification fails (max 3 retries per target)
• Apply the Iteration Discretion Rule to every target verdict, unless --strict was provided
• For shared group retries, only re-launch the specific failing implementation agent(s), not the entire group
• Reuse same meta-judge specification for all retries (never re-run meta-judge)

Model Selection Policy

Picking the model is the single highest-leverage decision you make — more than any prompt wording, it decides whether a target comes back correct and how long the batch takes. You MUST NOT treat it as a formality: name the tier and give a one-line justification before dispatching each target. Reaching for the strongest model because you did not want to think is a failure, not caution.

Tier default: sonnet and haiku are the default. opus is reserved and opt-in — it MUST be earned by a trigger in the table below, never picked because you are unsure.

Per task, not per run: a tier is chosen independently for every task, from that task's own scope, complexity and risk — the batch is no longer forced into one "same configuration for all parallel agents." Independent tasks are each tiered on their own merits. A repeatable group's shared meta-judge produces one reusable spec, but that does NOT force one tier: each task in the group keeps its own implementation and judge tier from the Selection Rules below, so a critical-domain target inside an otherwise-mechanical group can still land on opus while its siblings stay cheaper. A shared group's single judge reviews every task in the group together, so it runs at the HIGHEST current implementation tier among them (see Role Pairing). A tier reached by one task (including one reached by escalation) MUST NOT be carried into sibling tasks or the next batch.

Selection Rules

Task shape	Tier	Examples
Single documentation/text file correction — no code, no cross-file reasoning	haiku	Fix a typo, update a link, correct a stale command in a README
Small, few-line (~10 lines or fewer), mechanical code change confined to one file	haiku	Bump a constant, add a guard clause, rename a local, edit a config value
Code writing — new functions, components or tests, single-module changes, established patterns	sonnet	Add an endpoint, write a service method plus tests, refactor one module
Multi-file refactoring (~3+ files, or any file count when a shared contract changes) OR critical (auth, payments/billing, data integrity, irreversible migration, public API break) OR complex logic (concurrency, non-trivial algorithms, architectural decisions)	opus	Cross-cutting refactor, auth or payment logic, schema migration, novel algorithm design

Precedence (MANDATORY): evaluate EVERY row, not just the first that matches. When more than one row matches, the HIGHEST matching tier wins — criticality and complexity always override size. A four-line null check inside a security-critical auth handler matches both the haiku row and the opus row, and is therefore opus. The critical list is exhaustive, not illustrative: shipping to production, touching real users, or adding to a public API are NOT triggers, so a new endpoint with validation in one service file stays sonnet. Mechanical-breadth carve-out: breadth alone is not complexity. For a purely mechanical change — one identical, rule-driven edit repeated across targets, with no logic and no contract change — only the multi-file trigger does NOT apply; the critical and complex logic triggers still do. You MUST tier it on the content of a single occurrence, as if the task touched one file; mechanically renaming a symbol across 40 files is therefore haiku, but the same rename confined to src/auth/ is opus — the critical trigger fires on that single occurrence regardless of breadth. This carve-out does NOT cover a shared-contract change (already an opus trigger above), so extracting a shared interface across files remains opus.

Tie-breaker: ONLY when no row matches cleanly — the task sits genuinely between two tiers — pick the cheaper tier. You MUST NOT bias up to opus to hedge; the Escalation Rule makes a cheap first guess recoverable, and one recovered task costs far less than over-provisioning every task.

Role Pairing

Any model-assigned pipeline has up to three roles — producer (does the work), criteria-setter (defines what "correct" means), evaluator (checks the work against those criteria); in this skill they instantiate per parallel task as implementation / meta-judge / judge — a repeatable group shares one meta-judge across its tasks, and a shared group additionally shares one judge across its tasks. Default: the SAME tier for all three roles of that task.

Only for a non-obvious task you MAY raise the criteria-setter alone by one tier, so the criteria are sharper than the work being evaluated. Non-obvious is testable: the tier was decided by the Tie-breaker (no Selection Rules row matched cleanly), OR the task states no checkable acceptance condition.

Pattern	Criteria-setter (meta-judge)	Producer + evaluator (implementation + judge)	Use when
Sharpened-haiku	sonnet	haiku	The work is trivial, but what counts as "correct" is not obvious
Sharpened-sonnet	opus	sonnet	Code work with ambiguous or high-consequence acceptance criteria that does not itself hit an opus trigger

Producer and evaluator MUST always share a tier — for a repeatable or shared group's judge that serves more than one task, "share a tier" means the HIGHEST current implementation tier among the tasks it serves, so it is never asked to judge work above its own tier (see Model Escalation on Retry). You MUST NOT raise the evaluator alone, and MUST NOT set the criteria-setter below the producer tier. An explicit --model override supersedes this whole section: when the user passed --model, every role for every task runs at that tier, and Role Pairing MUST NOT raise the meta-judge above it.

Escalation Rule

Bump BOTH producer and evaluator (the failing task's implementation and judge) one tier for the next attempt when either trigger fires:

1. Low first-attempt quality — a low score, or issues showing the model misunderstood the task rather than merely missing details.
2. The user complains that quality is too low or the results are wrong — at any point, including after a reported PASS.

Ladder: haiku → sonnet → opus. opus is the ceiling — there is no further tier. If opus-tier work still fails, escalate to the user, never loop.

• Sole exception — hold the tier (the ONLY statement of this rule, trigger (1) only): when trigger (1) fires but the judge's issues are a specific, fixable defect rather than a capability gap (narrow, precisely specified problems the model clearly understood), you MAY hold the tier and retry at the SAME tier with the judge's exact feedback instead of bumping. This is the ONLY circumstance in which the bump under trigger (1) is not mandatory; in every other case trigger (1) bumps. Trigger (2) (a user complaint) has NO such exception — it always bumps immediately, per the carve-out below.
• Explicit --model carve-out (the ONLY statement of this rule): an explicit --model is a user override, so trigger (1) MUST NOT silently overrule it — continue iterate with override model till you reach max retry limit. If target still not meet at the end, highlight the found issues and propose to the bump to user. Trigger (2) IS that approval, so it bumps immediately.
• Scoped to the failing task only. Escalation re-tiers the retries of THAT task's implementation and judge. It does NOT re-tier the batch: sibling tasks running concurrently, and every task in a later batch, are assessed on their own merits per the Selection Rules, starting again from the sonnet/haiku default.
• Escalation moves implementation and judge only. The task's meta-judge (or the group's, for repeatable/shared groups) is NOT re-run and NOT re-tiered — its specification is reused across the task's retries, and changing the criteria mid-task invalidates the comparison across attempts.
• Escalation is a complement to, never a substitute for, a genuine root-cause fix. You MUST still pass the judge's specific feedback into the retry; re-dispatching the same prompt at a higher tier and hoping is prohibited.
• Escalation is orthogonal to the score thresholds, the Iteration Discretion Rule and the per-target max-3-retries budget — it changes which model runs the next attempt, never whether an attempt is warranted.
• Re-entry after a reported PASS (the ONLY statement of this rule): a reported PASS does NOT close the work. If the user later says a target's result is wrong or its quality too low, re-enter that target's retry path under trigger (2), and that target's retry budget resets — the complaint opens a fresh cycle of up to 3 retries even if the earlier cycle was exhausted.

Cross-Provider Equivalence

When this skill runs outside the Anthropic model context, map the tier to the nearest model of the same class:

Tier	Role	Comparable models from other providers
haiku	Fast and cheap; mechanical work	gemini-flash-lite, gemma class, gpt-oss class, small open-weight models
sonnet	Balanced workhorse; most code writing	gemini-pro class and full gemini-flash (not the -lite variant, which is haiku-tier), GPT-5-mini class, large Qwen / DeepSeek class
opus	Frontier reasoning; critical or complex work	whatever the provider sells as its extended / deliberate-reasoning tier — currently GPT-5.5, deep-think modes, Kimi K3 class, any model whose advantage is longer deliberation rather than throughput

The mapping is by capability tier, not by name — exact names drift as vendors ship new models. Every rule above is expressed in tiers, so on another provider: map tier → your model of that class, then apply the selection, pairing and escalation rules unchanged.

Process

Phase 1: Parse Input and Identify Targets

Extract targets from the command arguments:

Input patterns:
1. --files "src/a.ts,src/b.ts,src/c.ts"    --> File-based targets
2. --targets "UserService,OrderService"    --> Named targets
3. Infer from task description             --> Parse file paths from task

Parsing rules:

• If --files provided: Split by comma, validate each path exists
• If --targets provided: Split by comma, use as-is
• If neither: Attempt to extract file paths or target names from task description
• STRICT_MODE = --strict present || false - disables the Iteration Discretion Rule; a target then passes ONLY when score >= 4.0, otherwise it is retried until max retries
• Strip ALL flags from the task text before building sub-agent prompts — never pass them into a sub-agent prompt

Example: /do-in-parallel Simplify error handling --files "src/a.ts,src/b.ts" --strict

Phase 2: Task Analysis with Zero-shot CoT

Before dispatching, analyze the task systematically:

Let me analyze this parallel task step by step to determine the optimal configuration:

1. **Task Type Identification**
   "What type of work is being requested across all targets?"
   - Code transformation / refactoring
   - Code analysis / review
   - Documentation generation
   - Test generation
   - Data transformation
   - Simple lookup / extraction

2. **Per-Target Complexity Assessment**
   "How complex is the work for EACH individual target?"
   - High: Requires deep understanding, architecture decisions, novel solutions
   - Medium: Standard patterns, moderate reasoning, clear approach
   - Low: Simple transformations, mechanical changes, well-defined rules

3. **Per-Target Output Size**
   "How extensive is each target's expected output?"
   - Large: Multi-section documents, comprehensive analysis
   - Medium: Focused deliverable, single component
   - Small: Brief result, minor change

4. **Independence Check**
   "Are the targets truly independent?"
   - Yes: No shared state, no cross-dependencies, order doesn't matter
   - Partial: Some shared context needed, but can run in parallel
   - No: Dependencies exist --> Use sequential execution instead

Independence Validation (REQUIRED before parallel dispatch)

Verify tasks are truly independent before proceeding:

Check	Question	If NO
File Independence	Do targets share files?	Cannot parallelize - files conflict
State Independence	Do tasks modify shared state?	Cannot parallelize - race conditions
Order Independence	Does execution order matter?	Cannot parallelize - sequencing required
Output Independence	Does any target read another's output?	Cannot parallelize - data dependency

Independence Checklist:

• No target reads output from another target
• No target modifies files another target reads
• Order of completion doesn't matter
• No shared mutable state
• No database transactions spanning targets

If ANY check fails: STOP and inform user why parallelization is unsafe. Recommend /launch-sub-agent for sequential execution.

Requirement Grouping Analysis (REQUIRED before Meta-Judge dispatch)

After identifying individual tasks and validating independence, analyze whether tasks can share meta-judges and/or judges. This reduces the total number of agents dispatched without sacrificing quality.

Three grouping types (can be combined within a single user prompt):

Grouping Type	When to Apply	Meta-Judges	Implementation Agents	Judges
Repeatable	Same task pattern applied across multiple files/modules (e.g., "add tests to all 3 modules")	ONE shared meta-judge for the group	One per task (always isolated)	One per task, each receiving the SAME shared spec
Shared	Tasks that should be reviewed/verified together because they are interdependent (e.g., "implement S3 adapter AND integrate it into analytics")	ONE combined meta-judge for the group	One per task (always isolated)	ONE judge for the entire group, reviewing all changes together
Independent	Tasks that are fully independent with no grouping benefit	One per task	One per task (always isolated)	One per task

Decision process:

For each pair of tasks, ask:

1. "Is this the SAME task applied to different targets?"
   +-- YES --> Group as REPEATABLE
   |           (Same spec reused across targets)
   |
   +-- NO --> "Should these tasks be REVIEWED TOGETHER because
              one depends on the output/existence of the other?"
              |
              +-- YES --> Group as SHARED
              |           (Combined spec, single judge reviews all)
              |
              +-- NO --> Mark as INDEPENDENT
                         (Separate meta-judge and judge per task)

CRITICAL:

• When in doubt, default to INDEPENDENT.** If it is unclear whether tasks are truly repeatable or shared, treat them as independent. Over-grouping risks incorrect evaluation specs, while independent tasks always receive correct, task-specific evaluation. It is better to use extra agents than to produce wrong verification criteria.
• Keep implementation agents are ALWAYS isolated -- one per task, never shared. Only meta-judges and judges can be shared/grouped. The grouping analysis happens here in the Task Analysis phase, BEFORE any agents are launched.

Meta-judge instructions:

• Repeatable group: When dispatching a meta-judge for a repeatable group, include explicit instructions to produce a reusable verification spec.
• Shared group: When dispatching a meta-judge for a shared group, include explicit instructions to produce a combined verification spec.

Shared group retry logic:

If the shared judge finds issues, analyze which specific implementation agent(s) produced the failing changes. Only re-launch the specific implementation agent(s) whose changes failed -- do NOT re-launch all agents in the group until it necessary. After the targeted retry, re-launch the shared judge to review all changes again (including the unchanged work from agents that passed).

Phase 3: Model and Agent Selection

Select the model tier and specialized agent per task, based on the analysis in Phase 2, per the Model Selection Policy — sonnet/haiku by default, opus only when earned. If --model was passed, skip straight to 3.2: every sub-agent for every task runs at the user's tier, per the Role Pairing override clause.

3.1 Model Tier Selection Per Task

Assess every task on the three axes below, then read its tier straight off the Selection Rules table — tiers are chosen per task, never once for the whole batch:

• Scope — one file, one component, or multiple files?
• Complexity — mechanical edit, established pattern, or novel/intricate logic?
• Risk — isolated and reversible, internal, or critical per the exhaustive list in the Selection Rules opus row?

Per grouping type: