By name: harness-work description: "Executes plans.json tasks — solo, parallel, or breezing team mode. Use when implementing tasks or running the work loop." when_to_use: "implement task, run task, execute plans, work on task, run all tasks, parallel workers, breezing" allowed-tools: ["Read", "Write", "Edit", "Grep", "Glob", "Bash", "Task"] argument-hint: "[all|task-number|range|--codex|--opencode|--parallel N|--commit|--resume id|--breezing|--auto-mode]" effort: high model: sonnet
Harness Work
Unified execution skill for Harness. Consolidates the following legacy skills:
work— plans.json task implementation (auto scope detection)impl— Feature implementation (task-based)breezing— Full team auto-executionparallel-workflows— Parallel workflow optimizationci— CI failure recovery
Quick Reference
| User Input | Subcommand | Behavior |
|---|---|---|
harness-work |
auto | Auto-selects based on task count (see below) |
harness-work all |
auto | Executes all incomplete tasks in auto mode |
harness-work 3 |
solo | Immediately executes task 3 only |
harness-work --parallel 5 |
parallel | Forces parallel execution with 5 workers |
harness-work --codex |
codex | Delegates to Codex CLI (explicit only) |
harness-work --opencode |
opencode | Delegates to OpenCode CLI (explicit only) |
harness-work --breezing |
breezing | Forces team execution |
Execution Mode Auto Selection (auto-selection when no flag is specified)
When no explicit mode flag (--parallel, --breezing, --codex, --opencode) is provided,
the optimal mode is automatically selected based on the number of target tasks:
| Target Task Count | Auto-Selected Mode | Reason |
|---|---|---|
| 1 task | Solo | Minimal overhead. Direct implementation is fastest |
| 2-3 tasks | Parallel (Task tool) | Threshold where Worker isolation benefits emerge |
| 4+ tasks | Breezing | Lead coordination + Worker parallelism + Reviewer independence is effective |
Rules
- Explicit flags always override auto mode
--parallel N→ Parallel mode (regardless of task count)--breezing→ Breezing mode (regardless of task count)--codex→ Codex mode (regardless of task count)--opencode→ OpenCode mode (regardless of task count)
--codexactivates only when explicitly specified. Not auto-selected because Codex CLI may not be installed in some environments--codexcan be combined with other modes:--codex --breezing→ Codex + Breezing--opencodeactivates only when explicitly specified. Not auto-selected because opencode-plugin-cc may not be installed in some environments
Options
| Option | Description | Default |
|---|---|---|
all |
Target all incomplete tasks | - |
N or N-M |
Task number/range specification | - |
--parallel N |
Number of parallel workers | auto |
--sequential |
Force sequential execution | - |
--codex |
Delegate implementation to Codex CLI (explicit only, not auto-selected) | false |
--opencode |
Delegate implementation to OpenCode via opencode-plugin-cc (explicit only, not auto-selected) | false |
--commit |
Commit after each task is done (default: off) | false |
--resume <id|latest> |
Resume previous session | - |
--breezing |
Lead/Worker/Reviewer team execution | false |
--no-tdd |
Skip TDD phase | false |
--no-simplify |
Skip Auto-Refinement | false |
--auto-mode |
Explicitly enable Auto Mode rollout. Only considered when the parent session's permission mode is compatible | false |
Token Optimization (v2.1.69+): For lightweight tasks that don't involve git operations, enable
includeGitInstructions: falsein plugin settings to reduce prompt token usage.
1-Hour Prompt Cache (breezing sessions > 30 min):
source "${CLAUDE_PLUGIN_ROOT}/scripts/enable-1h-cache.sh"before starting. ExportsANTHROPIC_CACHE_CONTROL=max-age=3600so all spawned Workers, Reviewers, and hooks share a cached system prompt — reduces token cost and latency across long sessions.
Scope Dialog (when no arguments provided)
Note: A lightweight drift check (
bash "${CLAUDE_PLUGIN_ROOT}/scripts/plans-drift-check.sh") runs before the scope dialog regardless of which option the user chooses. If stale markers are detected, the dialog is preceded by a drift summary and a confirmation prompt.
harness-work
How far do you want to go?
1) Next task: The next incomplete task from plans.json → Execute in Solo mode
2) All (recommended): Complete all remaining tasks → Auto-select mode based on task count
3) Specify numbers: Enter task numbers (e.g., 3, 5-7) → Auto-select mode based on count
If arguments are provided, execute immediately (skip dialog):
harness-work all→ All tasks, auto mode selectionharness-work 3-6→ 4 tasks, so Breezing is auto-selected
Effort Level Control (v2.1.68+, simplified in v2.1.72)
Claude Code v2.1.68 sets medium effort (◐) as default for Opus 4.6.
v2.1.72 removed the max level, simplifying to 3 levels: low(○)/medium(◐)/high(●).
/effort auto resets to default.
For complex tasks, use the ultrathink keyword to enable high effort (●).
Multi-Factor Scoring
At task start, the following scores are summed, and ultrathink is injected when the threshold reaches 3 or above:
| Factor | Condition | Score |
|---|---|---|
| File count | 4+ files to be changed | +1 |
| Directory | Includes core/, guardrails/, security/ | +1 |
| Keywords | Contains architecture, security, design, migration | +1 |
| Failure history | Agent memory contains failure records for the same task | +2 |
| Explicit specification | PM template includes ultrathink notation | +3 (auto-adopted) |
Injection Method
When score >= 3, prepend ultrathink to the Worker spawn prompt.
The same logic applies in breezing mode (managed centrally by harness-work).
Execution Modes
| Mode | Reference | When |
|---|---|---|
| Solo | references/solo-mode.md |
1 task (auto) or any task number |
| Parallel | references/parallel-mode.md |
2-3 tasks (auto) or --parallel N |
| Breezing | references/breezing-mode.md |
4+ tasks (auto) or --breezing |
| Codex | references/codex-work.md |
--codex explicit only |
| OpenCode | references/opencode-work.md |
--opencode explicit only |
| Ralph | harness-ralph-loop skill |
Task has [ralph] marker — pre-dispatch, any mode |
[ralph]marker pre-dispatch rule: Before any standard worker dispatch (solo or breezing), harness-work checks the task description for the[ralph]marker. If present, it delegates toharness-ralph-loopinstead of the standard worker flow. Ralph tasks serialize within a session (only one Ralph loop runs at a time). Seereferences/solo-mode.mdandreferences/breezing-mode.mdfor dispatch details.
Worker Contracts
| Topic | Reference |
|---|---|
| NG rules (plans.json ownership via harness plan-cli, no embedded git, no nested spawn) | references/worker-ng-rules.md |
| Self-review gate (worker-report.v1 schema + Lead validation) | references/worker-self-review.md |
| Universal violations session injection | references/universal-violations.md |
| Testing anti-patterns (mocks, test-only methods, incomplete stubs) | references/testing-anti-patterns.md |
Failure & Review
| Topic | Reference |
|---|---|
| Review loop (Codex exec / Reviewer fallback, verdict criteria, fix cycle) | references/review-loop.md |
| CI failure handling (3-strike auto-fix loop) | references/ci-failure.md |
| Automatic re-ticketing of failed tasks | references/re-ticketing.md |
Templates
| Template | Description |
|---|---|
templates/worker-report.v1.json |
Worker self-review JSON schema (SR-1 through SR-5) |
templates/completion-report.md |
Rich Completion Report skeleton (solo + breezing formats) |
Task Status SSOT
.claude/harness/plans.json is the sole source of truth for task status. All reads via harness plan-cli list/get, all writes via harness plan-cli update. See harness/references/cli-reference.md. The native Claude Code task list is not mirrored.
Related Skills
harness-plan— Plan the tasks to executeharness-sync— Sync implementation with plans.jsonharness-review— Review implementationsharness-release— Version bump and release