From Harness
Classify planned features as autonomous or human-approval-required, then implement the current phase as parallel vertical slices — one subagent per feature. Use after dev-plan (and optionally prototype) has produced complete feature specs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/harness:implementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read everything. Subagents start with no conversation context but have full repo access — your job is to orient them with the right pointers, not to transcribe files into their prompts.
Read everything. Subagents start with no conversation context but have full repo access — your job is to orient them with the right pointers, not to transcribe files into their prompts.
Internal docs
.harness/engineering/architecture.md — stack, components, data flow, constraints.harness/engineering/implementation-plan.md — phases and task ordering.harness/engineering/features/ — all feature spec files (read every one).harness/adr/ — architectural decisions that constrain implementation.harness/product/CONTEXT.md — domain vocabulary (use these terms exactly in all code)Codebase
AGENTS.md — conventions, naming, patterns, do-not-edit filesREADME.md — public description, install/run instructionspackage.json / pyproject.toml / go.mod — dependencies and scriptsBuild a dependency map:
planned?planned features?If there is a conflict between implementation-plan.md and a feature spec, the feature spec takes precedence — it is the authoritative technical reference. Use implementation-plan.md only for phase ordering and task dependencies.
Before implementing anything, classify each planned feature in the current phase:
AFK (can be implemented autonomously) — ALL must be true:
architecture.mdHITL (needs human approval before proceeding) — ANY one is sufficient:
architecture.md or ADRsFor each HITL feature: state the specific question that needs answering before implementation can proceed. Do not implement HITL features — surface the question to the user and wait for resolution.
Present:
Example:
"Phase 1 — Foundation:
- AFK (parallel): user-authentication, project-creation
- HITL — blocked: database-schema → Question: the spec says 'soft delete', but the architecture doc says 'hard delete'. Which applies here?
I'll implement the AFK features in parallel. The database-schema feature needs your answer first. Proceed?"
Wait for confirmation. If HITL features have blocking questions, wait for answers before continuing.
Each agent implements ONE feature end-to-end through all layers — not one layer across all features.
A vertical slice means: from the user-facing entry point (UI interaction, CLI command, API endpoint) all the way through to storage, for this feature only. The agent implements exactly what this feature needs at each layer — not shared infrastructure, not future-proofing, not refactors.
This ensures each feature is independently demoable and verifiable the moment the agent finishes.
See REFERENCE.md for the prompt structure: the feature spec pasted in full, paths to the shared context docs, a short codebase orientation, and the implementation instructions.
Implement blocking features first (sequentially), then run the remaining independent features in parallel.
After all subagents finish:
done / blocked), files created or modifiedblocked features: the exact reason and what would unblock themdone features: one-line summary of what was builtRecommend next step:
npx claudepluginhub rubenglez/harness --plugin harnessGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.