claudecode-research-harness-workflow

HAR: Execute Plans.md tasks from single task to full parallel team run. Trigger: implement, execute, do everything, breezing, team run, parallel. Do NOT load for: planning, review, release, setup.

Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or Playwright when available. Do NOT load for: sharing URLs, embedding links, or editing screenshot files.

Explicit helper for authentication and payment implementation with Clerk, Supabase Auth, or Stripe. Do NOT load for: general UI work, database design, or non-auth features.

CI red? Call us. Pipeline fire brigade deploys. Use when user mentions CI failures, build errors, test failures, or pipeline issues. Do NOT load for: local builds, standard implementation work, reviews, or setup.

Explicit helper for CRUD scaffolding and API endpoint generation. Do NOT load for: UI components, form design, database schema discussion, or general implementation.

Deploy to Vercel/Netlify. One-way ticket to production arranged. Use when user mentions deployment, Vercel, Netlify, analytics, or health checks. Do NOT load for: implementation work, local development, reviews, or setup.

Generate an Acceptance Demo HTML for non-engineer vibecoders right before ship/wait/reject decision. Reads back the acceptance_criteria that were stored as personal-preference.v1 by harness-plan-brief (joined by user_request_hash), then renders a single-file HTML showing each criterion as verified or unverified along with a ship/wait/reject recommendation. Use when the user asks for an acceptance review, wants to decide whether to ship a delivered task, or says: acceptance demo, accept demo, acceptance decision, acceptance review, ship/wait/reject decision, acceptance inspection. Do NOT load for: implementation, code review, release work.

Long-running task loop using /loop (Claude Code dynamic mode) and ScheduleWakeup to re-enter with fresh context on each wake-up. Internally invokes harness-work through Agent. Trigger: long-running, loop, wake-up, autonomous. Do NOT load for: one-shot task execution, review, release, planning.

Generate a Plan Brief HTML for non-engineer vibecoders before implementation starts. Searches harness-mem (project-only) for relevant past decisions, patterns, and Plans archive entries, then renders a single-file HTML artifact summarizing understanding, options, risks, acceptance criteria, and confidence. Use when the user requests a planning preview, a non-engineer-friendly summary before approval, or says: plan brief, planning preview, planning overview, plan review. Do NOT load for: actual implementation, code review, release work.

HAR: Research-backed, team-validated task planning, Plans.md management, progress sync. Trigger: create a plan, add tasks, update Plans.md, mark complete, check progress. Do NOT load for: implementation, review, release.

Generate a Progress Tracker HTML for non-engineer vibecoders to glance at session progress (cc:WIP / cc:TODO / cc:done counts, percentage, elapsed/estimated minutes, cost so far/estimate, drift alerts). Uses Plans.md as source of truth, renders a single-file HTML with auto-regeneration support. Use when user asks for progress overview, session status snapshot, dashboard, or says: progress tracker, progress check, progress board, dashboard. Do NOT load for: actual implementation, code review, release work.

Generic release automation for projects using Keep a Changelog + GitHub. Single confirmation gate then end-to-end automation: bump detection, CHANGELOG promotion, PR/main merge, tag, GitHub Release. Trigger: release, version bump, publish. Do NOT load for: implementation, review, planning, setup.

HAR: Multi-angle code, plan, scope review. Security/quality check. Trigger: review, code review, plan review, scope analysis. Do NOT load for: implementation, new features, bugfix, setup, release.

HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.

HAR: Sync Plans.md with implementation. Drift detect, marker update, retrospective. Trigger: sync-status, where am I, check progress. --snapshot for snapshots. Do NOT load for: planning, implementation, review, release.

File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: /maintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.

Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.

Explicit helper for development principles, safety guidelines, and diff-aware editing rules. Do NOT load for: implementation, review, workflow coaching, or VibeCoder onboarding.

Controls session resume/fork(branch) for /work based on --resume/--fork flags. Updates session.json and session.events.jsonl. Internal workflow use only. Do NOT load for: user session management, login state, app state handling.

Internal sub-skill for session startup checks, Plans.md status, git state, and harness-mem resume pack. Invoked by session/startup workflows only. Do NOT load for: implementation, reviews, or mid-session tasks.

Internal sub-skill for cross-session handoff, durable learning, and memory persistence. Invoked by session/memory workflows only. Do NOT load for: implementation, review, ad-hoc notes, or SSOT editing.

Unified session management window. Handles initialization, memory, state all-in-one. Explicit /session invocation only — sub-skills handle auto-delegation. Use when managing Claude Code sessions, /session command. Do NOT load for: app user sessions, login state, authentication features.

Manages session state transitions per SESSION_ORCHESTRATION.md. Controls state updates at /work phase boundaries, escalated transitions on error, and initialized restoration on session resume. Internal workflow use only. Do NOT load for: user session management, login state, app state handling.

Explicit helper for UI components, hero sections, forms, feedback, and contact surfaces. Do NOT load for: authentication, backend implementation, database work, or business logic.

Explicit helper for Cursor PM ↔ Claude Code two-agent workflow guidance. Do NOT load for: solo implementation, workflow setup, handoff execution, or general process coaching.

RES: Read-only audit of raw data: variable inventory, missingness, IDs, units, merge keys, feasibility. Produces data_audit_report.md. Trigger: audit data, inspect data, data audit, check raw data. Do NOT load for: cleaning, analysis, review, release, setup.

RES: Generate and run reproducible data cleaning, harmonization, reshaping, and merging scripts. Preserves raw data. Produces cleaned datasets, cleaning report, and merge report. Trigger: clean data, merge data, process data, harmonize data. Do NOT load for: audit, analysis, review, release, setup.

RES: Generate an executable empirical analysis plan from study_spec.md, audit report, and cleaned data structure. Produces analysis_plan.md. Trigger: create analysis plan, plan analysis, generate analysis plan. Do NOT load for: cleaning, execution, review, release, setup.

RES: Build the replication/evidence package after a review APPROVE verdict. Assembles scripts, logs, cleaned-data docs, tables, figures, and reproducibility report. Requires human confirmation gate. Trigger: release research, build replication package, package evidence, finalize study. Do NOT load for: planning, execution, review, setup, audit, cleaning.

RES: Read-only review of research outputs. Checks identification, model spec, numerical accuracy, causal claims, reproducibility. Produces review_report.md with APPROVE/REQUEST_CHANGES/BLOCK verdict. Trigger: review research, check results, review analysis, verify outputs. Do NOT load for: cleaning, execution, release, setup, audit, planning.

RES: Initialize research project structure, create study_spec.md and analysis_plan.md, set up data protection rules and folder layout. Trigger: setup research project, initialize study, new research project. Do NOT load for: audit, cleaning, analysis, review, release.

RES: Execute approved analysis tasks from analysis_plan.md. Writes scripts, runs them, saves logs and outputs, updates task status. Trigger: run analysis, execute task, run regression, produce table, produce figure. Do NOT load for: planning, review, release, setup, audit, cleaning.