ClydeShen

context-handover

End-of-context-window session transition that saves memory, writes a handoff doc, posts a GitHub progress comment, and instructs the user to /compact for a clean next session. Use when context usage approaches 80%, when remaining tokens are insufficient for the current phase's remaining work, or when user says "handover", "context is full", "save progress", "end session". Distinct from /handoff (lightweight subagent briefing — no GitHub, no /compact).

setup-harness-skills

Creates CLAUDE.md/AGENTS.md from the harness template (if absent) and configures docs/agents/ so harness skills know the issue tracker, triage labels, domain docs, GitHub Project board, and session state location. Run before first use of triage, to-prd, to-issues, context-handover, or session-start — or if those skills appear to be missing context. Typically consumes <30% of a context window.

Code & Development Listed

harness-audit

Scans a project for agent-harness gaps and outputs a prioritised list with paste-ready config snippets to close them. Covers hooks, CI, pre-commit, instruction file quality, init.sh, and session discipline. Use when starting a new project, auditing an existing harness, writing or reviewing CLAUDE.md/AGENTS.md, setting up CI gates, beginning multi-day autonomous work, or when user says "set up harness", "health check", "agent discipline", "project setup", "pre-commit hooks", "stop hook", "verification gap".

Code & Development Listed

harness-guide

Review the current project state and continuously guide the project toward better Harness and Compound Engineering practices. Identify: - behaviors that align with best practices - anti-patterns or weak workflows - missing operational discipline, evals, harnesses, or feedback loops Then recommend the next highest-leverage step, including: - what to do next - why it matters now - what commands, tools, or workflows to use Ask questions one at a time. For each question, provide your recommended answer. If information can be discovered from the codebase, inspect the codebase instead of asking the user.

Data & Documents Listed

harness-issues

Break a plan, spec, or PRD into independently-grabbable issues using tracer-bullet vertical slices with enforced AC templates, creation gates, and dual output to GitHub Issues + PLAN.md. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

harness-prd

Turn the current conversation context into a GSD-compatible PRD with WHAT/HOW constraints, optionally writing to .harness/phases/01-discuss/CONTEXT.md. Use when user wants to create a PRD from the current context.

harness-triage

Harness-aware issue triage with effort calibration and agent brief generation. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Web & Frontend Listed

harness-verify-before-move

Comprehensive pre-phase-transition sweep. Verifies phase exit criteria, syncs code status (git/lint/build/tests), audits and cleans design docs, cleans implementation-notes, prunes stale documents and memory, syncs GitHub project state (milestones, issues, status labels, board), updates README, writes a fresh memory snapshot, then outputs a clean project snapshot. Use when completing a phase, before advancing to next phase, or when user says "verify before move", "clean up before moving", "sync everything", "project snapshot", "clean slate", "phase transition". Typically consumes ~8K–15K tokens / <10% of a context window.

session-start

Briefs the current session by reading session state, handoff doc, and memory to determine the active phase, task, and context budget. Outputs a structured briefing and detects whether the phase should be skipped or reverted based on observable artifacts. Use at the start of every long-running agent session, or when user says "start session", "what are we working on", "resume", "pick up where we left off", "what's the active task".

skill-cleanup

Audit and remove stale, renamed, or duplicate skills across all installed agent platforms (Claude Code, Kiro, Codex, Windsurf, Gemini, Pi, and more). Handles symlink and copy installs, detects artifacts, and generates OS-correct removal commands. Use when skills list feels cluttered, after renaming a skill, after uninstalling a plugin, or when user says "clean up skills", "remove old skill", "prune skills", "stale skill", "duplicate skill".

write-harness-skill

Create new harness-compatible agent skills with proper structure, progressive disclosure, and bundled resources — includes harness-specific checklist (token budget, setup-harness-skills reference, AI footer, creation gates). Use when user wants to create, write, or build a new skill.