skills/sprites/SKILL.md
Run lane cards on Fly Sprites: remote, isolated, scale-to-zero sandboxes for heavy or parallel agent work. Golden-checkpoint provisioning so lanes start on a ready sprite with zero setup tokens. Use when: "run this on a sprite", "remote lane", "offload to a sandbox", "dispatch to sprites", "bake a sprite", "sprite fleet", heavy/long-running/parallel sub-agent work that should not run on this machine. Trigger: /sprites, /sprite-lane.
npx skillsauth add phrazzld/spellbook spritesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
One primitive: scripts/sprite-lane runs one lane card on one sprite and
writes a local receipt. No daemon, no fleet state. Both ad-hoc dispatch (an
orchestrator calling this skill) and event-driven intake (a webhook or cron
caller) use the same primitive.
| Lane shape | Run it |
|---|---|
| Quick exploration, repo Q&A, small review | Local native subagent |
| Massive parallel fan-out within one session (audits, migrations, cross-checked review) | The harness's own large-scale orchestration feature when it has one — sprites add network overhead for nothing there |
| Heavy build/test loops, big implementation tickets | Sprite |
| Long-running or detached work (hours, overnight) | Sprite, --detach |
| Parallel competing attempts on the same repo | One sprite per attempt |
| Anything needing isolation from this machine | Sprite |
Do not prescribe sprites for work a local subagent finishes faster; network and sync overhead make sprites worse for sub-minute lanes.
scripts/sprite-lane bake <sprite> # provision + golden checkpoint (idempotent)
scripts/sprite-lane run <sprite> --repo <owner/name|url> --card <file> \
[--branch <b>] [--harness codex|claude] [--detach] [--fresh]
scripts/sprite-lane status <sprite> # bake state + running lanes
scripts/sprite-lane fetch <sprite> <lane-id> # pull a detached lane's log
scripts/sprite-lane reset <sprite> # restore golden checkpoint
Receipts land in ~/.harness-kit/receipts/sprite-lane/<lane-id>.json with the
remote log path, exit code, and timing.
Sprites cannot fork from another sprite's checkpoint, so determinism comes
from: an idempotent bake (harness CLIs, auth, git identity) plus a per-sprite
golden checkpoint. run auto-bakes an unbaked sprite; --fresh restores
golden first so the lane starts clean. Bumping BAKE_VERSION in the script
invalidates stale bakes everywhere. Details, auth flows, and failure modes:
references/provisioning.md.
A lane card states: end state, success criteria, verification affordances,
boundaries, and expected output shape (template:
templates/lane-card.md). Big outcome-shaped tickets beat atomic tasks —
the agent on the sprite owns its own decomposition. Put the oracle in the
card; the sprite has no access to your local context.
--fresh wipes uncommitted work from previous lanes on that sprite. Fetch
anything you need first.~/.codex/auth.json; if lanes start failing with
refresh_token_reused or auth_error, re-run codex login locally and
re-bake.ANTHROPIC_API_KEY exported locally at run time.mount_failed health is unusable; re-bake and cut a new
golden.testing
Capture one compounding repo-technical learning while a solved problem is still fresh. Use when: after a bug fix, diagnosis, delivery, review, or incident reveals a reusable pattern worth adding to `docs/solutions/`. Trigger: /compound, /capture-learning, /learning.
testing
Route Misty Step factory application capabilities. Use when choosing, auditing, integrating, or operating Canary, Powder, Landmark, Aesthetic, or Bitterblossom: production observability, incidents, health checks, error logging, backlog/work-card state, release intelligence, UI/UX system adoption, or supervised/unsupervised agent dispatch. Trigger: /factory-apps, /factory-stack.
testing
Prove a skill beats no-skill with a falsifiable A/B eval, or retire it. Design, generate, run, and maintain a skill-specific eval: name the one claim the skill must earn, run it skill-on vs raw same-model, grade blind with objective checks first, return a keep/adapt/cut verdict. Use when: "eval this skill", "does this skill help", "prove the skill beats no skill", "write an eval for", "benchmark a skill", "is this skill worth it", "skill A/B", "skill regression test", "generate skill evals". Trigger: /skill-eval, /eval-skill, /prove-skill.
tools
> Template. Copy to `<target-repo>/.agents/skills/<repo>-<domain>/SKILL.md` > and fill every bracketed placeholder from the live target repo. Delete this > line and every other `> ` guidance line before committing. See > `../../references/repo-local-skill-generation.md` for the full process. --- name: <repo>-<domain> description: | [One paragraph: what this skill verifies/runs/operates for <repo>, stated in terms of the repo's real shape (service/CLI/library/etc.), not generic process. En