audit
01Skill Claude CodeCodex
Drift audit for tracking files, specs, plans, or citations against live state. Produces one Reviews/ doc with mechanically-verified findings, two-pass (inventory then apply).
Skill Claude CodeCodex
Drift audit for tracking files, specs, plans, or citations against live state. Produces one Reviews/ doc with mechanically-verified findings, two-pass (inventory then apply).
Skill Claude CodeCodex
Re-explain your own previous answer in plain language, for when it didn't land. Use when the user types /bro, or says the last answer was too dense, too jargon-heavy, or asks for it simpler. Re-expresses what was already said; never answers something new.
Skill Claude CodeCodex
Periodic sweep of the workspace's curated narrative (session-note titles + git subjects + roadmap/DECISIONS) to surface repeated, formalizable work and propose turning it into skills or scripts. Writes one Reviews/ doc with a verdict per candidate. NOT correction triage (that's /review-corrections) and NOT drift…
Skill Claude CodeCodex
Shape a raw idea into a clear, INTENT-ready brief by interviewing the user one question at a time — reading any existing code/systems the idea touches as ground truth before asking — so it's ready to graduate via /new-project. Use when the user has a new idea to think through ("let's brainstorm X", "kick off an idea"…
Skill Claude CodeCodex
Run a structured planning session — interview the sources of truth, draft, adversarial review (up to 3 reviewers, scaled to the change), approve, update docs. Required for any change to the shipped engine, a skill/template, a hook, recall, security, or a public release, and for features spanning several files or…
Skill Claude CodeCodex
Graduate an idea from your lab into its own full-rig project workspace under /Projects/ (stamped from the lab template — recall engine, hooks, git drift-gate, vendored identity, seeded memory, genome skeletons). Use when the user says "graduate X", "spin up a project for X", or "/new-project".
Skill Claude CodeCodex
Triage pending correction candidates (captured by the recall Stop hook) into memory — promote the worthy, drop the noise, surface the contested. Closes the correction→memory loop.
Skill Claude CodeCodex
First-run personalization for a freshly cloned Lab — interview the user one question at a time and write their IDENTITY.md, so the agent knows who it's working with. Use on first run, when IDENTITY.md still has placeholders, or when the user says "/setup", "set up my lab", or "personalize this".
Skill Claude CodeCodex
Cleanly wrap a work session — ground state against git+filesystem, update and de-bloat the tracking files, ensure the next-session landing pad is grounded (not invented), scan staged changes for leaked secrets, then commit (and push if there's a remote). Invoke at session end, or whenever the user says "wrap".
Hook Claude Code
Runs before the agent uses a tool for Edit, Write and NotebookEdit tool calls, executing protect-files.sh via bash. From cyb213/Lab-Zero.
Hook Claude Code
Runs when a session starts, executing recall-session-start.sh via bash. From cyb213/Lab-Zero.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing recall-user-prompt.sh via bash. From cyb213/Lab-Zero.
Hook Claude Code
Runs when the agent finishes a response, executing recall-stop.sh via bash. From cyb213/Lab-Zero.
Settings file Claude Code
Agent settings declaring 4 hook events (PreToolUse, SessionStart, UserPromptSubmit, Stop).
Instructions file CodexOpenCode
AGENTS.md instructions for cyb213/Lab-Zero, covering agents.md — your lab, what this is, who you're working with, how to work here and working discipline + continuity.
Instructions file
Claude Code instructions for cyb213/Lab-Zero, covering claude.md — claude code entry point and claude code specifics.