Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.
Skill Claude CodeCodex
Use when cutting an Orchard release (tagging a new version of the FastAPI inventory service) — walks the pre-tag checklist so migrations, verify, changelog, and the tag stay in sync.
Skill Claude CodeCodex
Use when adding or restyling a Facet UI component, or before merging a UI PR — walks the component against DESIGN.md (tokens, states, a11y, contrast, responsive) so the design system is matched, not just remembered. The judgment check verify.sh can't grep.
Skill Claude CodeCodex
Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker without pushing, merging, or writing to external systems.
Skill Claude CodeCodex
Template/example skill showing the minimal structure. Replace or delete it. Use as a starting point when you want to capture a repeatable workflow as a skill.
Skill Claude CodeCodex
Wrap up a work session for a clean restart — fires on "handoff", "wrap up", "let's stop here", when context is filling, or when a phase closed. Part of the Agentsmith harness; writes a durable handoff note plus a paste-ready kickoff block so a fresh session loses nothing.
Skill Claude CodeCodex
Check whether this project's Agentsmith harness is installed correctly and healthy — fires on "is my harness set up right?", "harness doctor", "check my harness". Part of the Agentsmith harness; checks each selected agent's managed rules, settings, skills, hooks, verification, and leanness with a one-line fix for each…
Skill Claude CodeCodex
Orient a non-coder to this project's Agentsmith harness — fires on "what is this harness?", "what are my rules?", "which profile am I on?", "what do I type next?". Part of the Agentsmith harness; reads the canonical instructions and selected agent's safety configuration, then reports the profile, rules, safety mode…
Skill Claude CodeCodex
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. Part of the Agentsmith harness; scaffolds a numbered docs/feedback/NNNN-.md with the five-stage template (R9 — numbers are…
Skill Claude CodeCodex
Start a durable research / source note that captures what you read and found — fires on "start a research note", "capture these sources", "log my research". Part of the Agentsmith harness; scaffolds docs/research/ .md so findings live in the repo, never in disposable memory (R9), and are never silently deleted.
Skill Claude CodeCodex
Answer "is this shippable / done?" with evidence before a commit or PR — fires on "verify", "is this done", "ready to ship?", pre-commit or pre-PR. Part of the Agentsmith harness; runs the project's verify phases and never claims "passing" without showing the output (R5).
Skill Claude CodeCodex
Wayfind a foggy, multi-session effort into an accepted repository spec and separate implementation-ticket drafts. Use when the destination is known but important decisions, dependencies, or scope are not yet clear enough to implement safely.
Skill Claude CodeCodex
Write or review anything an agent reads — a core rule, a profile gate, a SKILL.md description, an instruction-file line, a subagent prompt, a handoff note, a verify-phase label. Part of the Agentsmith harness; supplies the levers that decide whether a line changes behaviour or only costs tokens — the two loads…
Skill Claude CodeCodex
Fixture proving that skill identity comes from metadata rather than its installation path.