Help us improve
Share bugs, ideas, or general feedback.
From ralphharness
This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "execution modes", "ralph loop", "coordinator behavior", "delegate to subagent", or needs guidance on Ralph plugin arguments, state management, delegation patterns, or execution loop behavior. Core behavioral skill for all RalphHarness operations.
npx claudepluginhub informatico-madrid/ralph-harness --plugin ralphharnessHow this skill is triggered — by the user, by Claude, or both
Slash command
/ralphharness:ralphharnessThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Core skill for all Ralph plugins. Defines common arguments, execution modes, shared behaviors, and coordinator delegation rules.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Core skill for all Ralph plugins. Defines common arguments, execution modes, shared behaviors, and coordinator delegation rules.
All Ralph commands support these standard arguments:
| Argument | Short | Description | Default |
|---|---|---|---|
--quick | -q | Skip interactive phases, auto-generate artifacts, start execution immediately | false |
--commit | -c | Commit and push spec/feature files after generation | true (normal), false (quick) |
--no-commit | Explicitly disable committing files | - | |
--max-task-iterations | -m | Max retries per failed task before stopping | 5 |
--fresh | -f | Force new spec/feature, overwrite if exists | false |
Argument precedence: --no-commit > --commit > mode default.
awaitingApproval: true--quick)--commit to override)All Ralph plugins use .ralph-state.json for execution state. See references/state-file-schema.md for full schema.
Key fields: phase, taskIndex, totalTasks, taskIteration, maxTaskIterations, awaitingApproval.
When commitSpec is true:
chore(<plugin>): commit spec files before implementationWhen commitSpec is false:
RalphHarness v3.0.0+ has a self-contained execution loop via the stop-hook. No external dependencies required.
Key signals:
TASK_COMPLETE - executor finished taskALL_TASKS_COMPLETE - coordinator ends loopWhen taskIteration > maxTaskIterations: block task, suggest manual intervention.
If state file missing/invalid: output error, suggest re-running implement command.
All Ralph plugins follow consistent branch strategy:
The main agent is a coordinator, not an implementer. Delegate all work to subagents.
| Work Type | Delegate To |
|---|---|
| Research | Research Team (parallel teammates) |
| Requirements | product-manager subagent |
| Design | architect-reviewer subagent |
| Task planning | task-planner subagent |
| Task execution | spec-executor subagent |
Every delegation prompt to spec-executor or qa-engineer for VE tasks, [VERIFY] tasks, or Phase 3 (Testing) tasks MUST include a Delegation Contract with:
See references/coordinator-pattern.md → Task Delegation → Sequential Execution for the full contract template.
Why: Subagents execute in fresh context with no memory of prior decisions. Without the contract, they repeat diagnosed anti-patterns (e.g., using page.goto() for internal routes, hardcoding selectors, reusing consumed OAuth tokens). The contract is the mechanism to transfer accumulated knowledge from the coordinator to the executor.
Quick mode still requires delegation.