AlexanderMattTurner/agent-glovebox
Agent Claude Code
Read-only reviewer that inspects the current diff or branch for correctness bugs and reuse/simplification opportunities, with no power to edit. Invoke it for an unbiased second opinion before shipping: after finishing a feature/fix, before opening a PR, or whenever the user asks for a code review of pending changes.…
AlexanderMattTurner/agent-glovebox
Command Claude Code
Write the end-of-session handoff — what this session could not fix, pasted in chat.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs when a session starts, executing safe-launch.sh and session-setup.sh with --advisory (4 commands). From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs after instructions files are loaded, executing safe-launch.sh with --advisory. From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs before the agent uses a tool for WebFetch, Bash, Bash, Edit, Write, MultiEdit and NotebookEdit tool calls, executing safe-launch.sh with --advisory (6 commands). From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs on the PermissionDenied event, executing safe-launch.sh with --event. From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs after a tool call finishes, executing safe-launch.sh with --event and --advisory (3 commands). From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing safe-launch.sh with --event and --advisory (3 commands). From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs when the agent sends a notification, executing safe-launch.sh with --advisory. From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs when a session ends, executing safe-launch.sh with --advisory and --session-summary (3 commands). From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Hook Claude Code
Runs when the agent finishes a response, executing safe-launch.sh with --advisory (2 commands). From AlexanderMattTurner/agent-glovebox.
AlexanderMattTurner/agent-glovebox
Settings file Claude Code
Agent settings declaring 9 hook events (SessionStart, InstructionsLoaded, PreToolUse, PermissionDenied) and 185 allowed tools.
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
How to sit on a set of already-open PRs and drive them to landed — building the watch set, reading GitHub's mergeability and queue state correctly, re-arming auto-merge, dispatching fixes for reds, and deciding which wake-ups deserve a reply. Activate when asked to "babysit", "watch", "monitor", "sit on", "keep an eye…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
How to respond when a CI check goes red, a PR check fails, a test is flaky, a job times out, or a webhook reports a failing status — plus how to read GitHub check state at all (gh locally vs mcpgithub on the web, and why one page of getcheckruns never proves "all green"). Activate whenever a check is red or cancelled…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
Turn a defect class into a well-designed guard PROPOSAL (and, once a human promotes it, a well-built guard). Activate when writing a ## Proposed guards entry after fixing a bug, and when a human has explicitly approved implementing a lint, pre-commit hook, CI check, assertion, or ratchet — never to ship a guard inside…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
Drives the Explore -> Plan -> Critique -> Review -> Verify discipline for a written plan. Activate on entry to plan mode, before writing the plan — including the plan-mode requests "plan this", "scope this out", "figure out how to do X", "explore the codebase first" — in auto mode at the start of any non-trivial task…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
The mechanics of committing, pushing, and resolving merge conflicts in this repo. Activate before you commit or push, when a PR reports a merge conflict or a dirty mergeablestate, when a merge-conflict label or an auto-resolve bot comment arrives, when you must audit a bot's merge resolution or answer a merge-delta…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
How to write the end-of-session handoff — the residue of what this session could not fix. Activate when the user asks for a handoff, when a session is ending with a known failure still standing, or when you are about to call something "pre-existing", "unrelated" or "not mine". The load-bearing rule is that a handoff…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
Outputs content inside a copyable fenced markdown code block so the user can copy the raw markdown verbatim. Activate whenever the user asks for "copyable markdown", "raw markdown", "the markdown source", "give me the markdown", "as a code block I can copy", or any variation of requesting markdown they can paste…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
Runs a broad, multi-dimension codebase audit by fanning out parallel read-only subagents (one per dimension x file-area), independently confirms their findings, then groups the survivors into one fix plan with partitioned commits, on as few PRs as the footprint bound allows, and self-critiques it before delivery.…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
Runs a fresh, unbiased review of pending changes by delegating to the read-only code-reviewer subagent, then triages and fixes the findings. Activate when the user asks to "review this", "peer review", "get a second opinion", "review my changes/diff/branch", or wants a review pass before opening a PR. Distinct from…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
Creates high-quality pull requests with an iterative compress-critique-fix loop before submission. Activate this skill whenever you are asked to create, open, submit, or push a pull request, OR whenever a new feature, fix, or refactor is complete and ready to ship. Also activate when the user says "make a PR", "open a…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
How to run the external Control Tower / LinuxArena eval (glovebox's marginal-defense benchmark) — dispatching the live sbx-microVM e2e, building the cells JSON, picking the agent model + budget, and pulling the .eval transcripts back. Activate whenever the user asks to "run CT", "run the Control Tower eval", "smoke…
AlexanderMattTurner/agent-glovebox
Skill Claude CodeCodex
How to run and report the live-fire breakout CTF — glovebox's containment test, where a real autonomous agent attacks the production sandbox stack and a judge grades whether it was contained. Covers the dispatch inputs, the four postures (guarded, automode, control, stock sbx), the verdict vocabulary and what each…