e2b-dev/herdr-e2b-sandbox.

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

e2b-box

Drive the herdr-e2b plugin — e2b-box, e2b-fleet, e2b-bench, e2b-dash — from the CLI, the way an agent orchestrator (or a human without the keybindings) uses it. Two workflows it maps: (1) you already have a worktree and want its work mirrored into an E2B cloud sandbox (e2b-box open/sync/pull, one box per worktree), and (2) you want ONE task fanned out from the current checkout to several coding agents at once — claude, codex, opencode, amp, grok, droid, prime, muse — each in its own auto-created worktree + sandbox (e2b-fleet), then monitored, graded with a held-out check (e2b-bench), and the best result pulled back (best-of-n). Use whenever the user mentions e2b-box, e2b-fleet, e2b-bench, fleets, "run the same task on claude and codex", "fan this out to N agents", "send this worktree to a sandbox", "move my work to the cloud box", "grade the fleet", "best of n agents", "pull the winner", or presses/asks about prefix+shift+E / prefix+shift+F / prefix+shift+D in herdr. Also use when orchestrating these commands yourself as the agent instead of the human.

herdr-e2b-bench

Build and run a coding-agent shootout in this repo — one task, N agents (claude, codex, opencode, amp, grok, droid, prime, muse), each in its own E2B sandbox, graded by a held-out test and compared on tokens, cost, wall clock and diff size. Takes one argument. `create` authors a new benchmark task: the brief (bench/BENCH.md), the held-out grader (bench/grade.sh), and the reusable measurement scripts (bench/usage.sh, bench/judge.sh, bench/README.md), then calibrates the grader by measuring its floor and its ceiling. `execute` drives an existing benchmark: fan out with e2b-box fleet, grade with e2b-bench, table with usage.sh, blind-judge with judge.sh, tear down. `quick` is `execute` on the fast task pair (bench/BENCH-quick.md + bench/grade-quick.sh) — ~5 minutes of agent time and a ~1s grader, for when you are testing the harness rather than the agents. Use this skill whenever the user mentions a bench, benchmark, shootout, race, "which agent is better", harness-bench, bench/BENCH.md, bench/grade.sh, held-out test, grading a fleet, best-of-n, or wants to compare coding agents on the same task, or says quick bench, fast bench, short bench, smoke bench, quick lap, or asks for a bench that does not take an hour — and also whenever they ask to add, change, calibrate, or score a benchmark task in this repo, or to run one for a demo recording. Prefer this over improvising e2b-fleet and e2b-bench calls by hand, because the held-out mechanics and the grader calibration are easy to get subtly wrong.

resolving-merge-conflicts

Use when you need to resolve an in-progress git merge/rebase conflict.

to-questionnaire

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

to-spec

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

wait-what

Stop. That last message did not land — re-pitch it.

wayfinder

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

wizard

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.