Agent skill

Crabbox Remote Test Runner

by openclaw in openclaw/agent-skills

Detects the Crabbox CLI or config in a repository and uses it to run tests and validation on remote runners, with checks before touching secrets or paid infrastructure.

MITAuto-check passedDevOps & Cloud

Install Crabbox Remote Test Runner

skills CLI
$ npx skills add openclaw/agent-skills --skill crabbox -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openclaw/agent-skills crabbox --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openclaw/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/crabbox .claude/skills/crabbox && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
crabbox
GitHub stars
1.1k
Token cost
~3.6k tokens
SKILL.md length
1,371 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Detects the Crabbox CLI or config in a repository and uses it to run tests and validation on remote runners, with checks before touching secrets or paid infrastructure.

  • Works in 5 steps: Reproduce entrypoint when feasible. → Patch. Narrow local test. → Remote… → …
  • A repository contains crabbox.yaml or .crabbox.yaml
  • SKILL.md covers Repository Contract, Authorization and Isolation, Route First and Preflight, plus 9 more sections
  • Calls jq; needs CRABBOX_TAILSCALE_AUTH_KEY

What it does

A repo-root `crabbox.yaml` or `.crabbox.yaml` signals that Crabbox is meant for validation work, as does an installed `crabbox` binary, which should pass `crabbox doctor` first. Detection is not permission: the agent inspects the config before running it, since it is executable project automation, and reviews the provider, actions, jobs, profiles, `env.allow`, artifacts and cleanup policy before remote runs.

Local targeted tests remain the choice for tight edit loops. Crabbox is for broad suites, package-heavy checks, Docker or end-to-end and live-provider proof, cross-OS and UI proof, fresh PR checkouts, reusable warmed boxes and runs that need durable logs. Brokered use needs a coordinator URL and token set up through `crabbox login`, and settings resolve in the order flags, environment, repo config, user config, defaults. `crabbox providers` and `crabbox config show` help inspect the setup.

When your agent uses it

  • A repository contains crabbox.yaml or .crabbox.yaml
  • Running a large test suite on a remote machine instead of your laptop
  • Proving a change works on another operating system or in a clean environment
  • Keeping auditable logs and artifacts of a validation run

Example prompts

  • “This repo has a crabbox.yaml, so run the full test suite on a remote runner and show me the results.”
  • “Check that Crabbox is set up correctly before we use it for the end-to-end tests.”
  • “Sync my dirty checkout to a fresh box and run the UI proof.”

Requirements

  • The `crabbox` CLI
  • A coordinator (broker) URL and token for brokered runs
  • A `crabbox.yaml` or `.crabbox.yaml` in the repository

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Reproduce entrypoint when feasible.
  2. Patch. Narrow local test.
  3. Remote install/update/onboard/CLI/service/API path.
  4. Record provider, id, command, environment shape, redacted secret source,
  5. Cleanup.

What it can do on your machine

Read from SKILL.md and the folder at commit 7e73306. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • CRABBOX_TAILSCALE_AUTH_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Crabbox Remote Test Runner loads about 3.6k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 1,371 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from openclaw/agent-skills at commit 7e73306, republished under its MIT licence (© openclaw). 1,371 words, ~3,586 tokens.

Download SKILL.mdSave it as .claude/skills/crabbox/SKILL.md (or your agent's skills folder).
name
crabbox
description
Crabbox/Testbox remote proof: portable provider routing, untrusted isolation, Linux/macOS/Windows/WSL2, live E2E, diagnostics, cleanup.

Crabbox

Remote and clean-machine proof. Packages. Docker. Live providers. Desktop. Cross-OS. The consumer repository owns when its validation needs a remote environment; Crabbox availability alone is not a reason to offload local work.

Backends:

  • blacksmith-testbox: trusted maintainer source. Prepared CI. tbx_....
  • aws: direct brokered Crabbox. Fresh PRs. Custom sync/env/capture. cbx_....
  • local-container: Docker fallback. Not remote proof.
  • ssh: existing operator host. macOS/Windows/WSL2.

Always report provider, id, run URL, command, result. Never call Testbox “AWS Crabbox.”

Repository Contract

This canonical skill owns portable Crabbox policy and CLI operations only. Consumer-specific setup belongs in that repository's AGENTS.md, package scripts, hydration workflow, or another file outside the synchronized skill.

Resolve these placeholders from trusted repository instructions before running an example:

  • <check-command>: the repository's focused or broad validation command.
  • <install-and-check-command>: its clean-container install plus validation.
  • <trusted-bootstrap-script>: a maintainer-reviewed untrusted-PR bootstrap stored outside the untrusted checkout.
  • <container-image> and <owner/repo#number>: the consumer's runtime and PR.

Never invent a missing command or copy a command from another consumer.

Authorization and Isolation

Routine use of the configured Crabbox/Testbox environment is part of completing the requested task; do not ask for separate approval. This includes creating, reusing and stopping task-owned leases, temporary state, and clean checkouts or worktrees needed for proof or a task-required Crabbox repair.

A dirty, missing or occupied checkout is a reason to use a clean task-owned checkout or worktree, not a permission blocker. Preserve existing checkouts, branches and unrelated edits. Keep source-trust, credential, production-access, budget and publication boundaries; routine-use approval does not waive them.

Route First

Source trust determines which providers are allowed. It does not select one.

  • Trusted development tests/checks/builds: follow the consumer's local-first policy; use remote when its environment is needed or explicitly requested.
  • Trusted + remote proof: inspect and preserve the resolved provider.
  • Blacksmith Testbox: use when already resolved or explicitly requested.
  • Direct AWS: use when AWS semantics are required or explicitly requested.
  • Untrusted contributor/fork: secretless fork CI or sanitized direct AWS.
  • Never untrusted code on credential-hydrated Testbox.
  • Never run untrusted repo wrapper/config locally.
  • No speculative warmup. Acquire when first heavy command ready. Reuse id. Stop.

Test size, expected duration, and hydration failure do not authorize a provider override. Omit --provider for normal work. Add it only when the user requests that backend or the proof specifically tests its semantics.

Preflight

Run from repo root.

sh
command -v crabbox
crabbox --version
crabbox config show --json | jq '{provider, profile, target}'
crabbox run --help | sed -n '1,100p'
command -v blacksmith
blacksmith --version

Set the checked installed binary once. A consumer may document a different trusted wrapper, but the shared skill never assumes a sibling checkout or repository-specific script.

sh
export CRABBOX="$(command -v crabbox)"
test -n "$CRABBOX"
"$CRABBOX" --version
"$CRABBOX" config show --json | jq '{provider, profile, target}'

Read .crabbox.yaml and config show; the resolved provider can also come from user or environment configuration. If the binary is missing, follow the consumer's trusted install instructions. For a source build or repair, verify the canonical upstream and use a clean task-owned checkout or worktree. Never assume a sibling checkout is trusted or overwrite its unrelated work. Keep task-specific builds separate from the operator's installed binary.

Trusted Testbox

Use this section only when config show resolves blacksmith-testbox or the user explicitly requested Testbox. These provider-neutral commands preserve the resolved configuration; add --provider blacksmith-testbox only for that explicit override.

One-shot heavy gate:

sh
"$CRABBOX" run --timing-json -- CI=1 <check-command>

Several commands: warm once, save id, reuse, stop.

sh
"$CRABBOX" warmup --keep --timing-json
"$CRABBOX" run --id <tbx_id> --timing-json -- <check-command>
"$CRABBOX" stop <tbx_id>

Rules:

  • One lease, one active command. No sync/reclaim during run.
  • Native Testbox runs own sync, including reused --id runs. Never rely on --no-sync to preserve a remote baseline: Blacksmith has no native bypass, and released Crabbox versions can silently ignore the flag. An unchanged intentional rerun is not a Testbox exception.
  • --reclaim only deliberate checkout-path ownership transfer.
  • Base/head change: stop. Rewarm. No stale-lease override.
  • Raw SHA unreliable for warmup --ref; use branch/tag.
  • blacksmith testbox list hides states. Use list --all or status --id <tbx_id>.
  • Testbox status/stop: --id. No status --json.
  • Delegated provider rejects --fresh-pr, --full-resync, --script*, --env-helper, capture/download flags.
Verify Synced Inputs

Before interpreting a missing-module or missing-fixture failure, compare required inputs with the frozen source. A successful sync can omit tracked files matched by its exclusions. Inspect the installed sync rules, including Git-ignore negations, rather than assuming Git and rsync select identical files.

Record each required missing path and its exact frozen Git blob. Restore only those reviewed inputs in the task-owned remote checkout, then verify their bytes. Do not regenerate a baseline, copy unrelated local state, disable exclusions, or treat every missing file as acceptable. Account for changed and untracked inputs separately from committed blobs. Recheck required inputs after each native sync before running the affected proof.

A timeout during sync is not a test result. Establish whether payload dispatch occurred before retrying or reporting a command failure. If dispatch is unknown, inspect the same lease and invocation first. Preserve completed proof against its source identity, and continue only the missing verification.

Untrusted AWS

Clean trusted default-branch checkout. Installed trusted Crabbox binary. Fresh lease per reviewed full head SHA. No instance role. No Tailscale. No hydration. Only CI forwarded. Trusted bootstrap uploaded beside --fresh-pr.

sh
cd <clean-trusted-default-branch-checkout>
env -u CRABBOX_AWS_INSTANCE_PROFILE \
  "$CRABBOX" config show --json | \
  jq -e '.aws.instanceProfile == ""' >/dev/null

env -u CRABBOX_AWS_INSTANCE_PROFILE \
  -u CRABBOX_TAILSCALE \
  -u CRABBOX_TAILSCALE_AUTH_KEY \
  -u CRABBOX_TAILSCALE_AUTH_KEY_ENV \
  -u CRABBOX_TAILSCALE_EXIT_NODE \
  -u CRABBOX_TAILSCALE_EXIT_NODE_ALLOW_LAN_ACCESS \
  -u CRABBOX_TAILSCALE_HOSTNAME_TEMPLATE \
  -u CRABBOX_TAILSCALE_TAGS \
  "$CRABBOX" warmup \
  --provider aws --network public --tailscale=false \
  --tailscale-exit-node= \
  --tailscale-exit-node-allow-lan-access=false \
  --keep --timing-json

"$CRABBOX" inspect --provider aws --id <cbx_id> --json | \
  jq -e '.network == "public" and .tailscale == null' >/dev/null

env -u CRABBOX_AWS_INSTANCE_PROFILE \
  CRABBOX_ENV_ALLOW=CI \
  "$CRABBOX" run \
  --provider aws --id <cbx_id> \
  --fresh-pr <owner/repo#number> \
  --no-hydrate --timing-json \
  --script <trusted-bootstrap-script> -- \
  <expected_full_head_sha> <check-command>

env -u CRABBOX_AWS_INSTANCE_PROFILE \
  "$CRABBOX" stop --provider aws <cbx_id>

The consumer-owned bootstrap proves the IMDSv2 IAM credential endpoint returns 404, verifies the full SHA, removes inherited runtime injection variables, pins the repository toolchain, isolates HOME, installs, and tests.

Head moved? Stop. Rewarm. No reuse across revisions. No remote PR or no-role proof unavailable? Secretless fork CI. No exceptions.

Show full SKILL.md (520 more words)Show less

Direct AWS

Trusted direct run:

sh
"$CRABBOX" run \
  --provider aws \
  --idle-timeout 90m --ttl 240m --timing-json \
  --shell -- \
  "<check-command>"

Focused:

sh
"$CRABBOX" run \
  --provider aws --timing-json --shell -- \
  "<check-command>"

Stale sync: retry --full-resync once. Still bad: fresh lease. One-shot should stop itself; after failure/interruption verify "$CRABBOX" list --provider aws.

Broker auth, not cloud keys:

sh
"$CRABBOX" config show
"$CRABBOX" doctor
"$CRABBOX" whoami
"$CRABBOX" login --url <broker-url> --provider aws

Normal validation asking for AWS keys usually means wrong path.

Fresh PR / Container

--fresh-pr <owner/repo#123>: clean remote checkout. Add --apply-local-patch only for intentional local fixup. Direct providers only.

Use local Docker only when the resolved configuration selects it or the user explicitly requests a local-container lane:

sh
"$CRABBOX" run \
  --provider local-container \
  --local-container-image <container-image> \
  --no-hydrate --fresh-pr <owner/repo#number> \
  --timing-json --shell -- \
  "<install-and-check-command>"

Report local-container; not AWS/Testbox. Keep --no-hydrate and use a repository-local dependency cache when host-mounted caches cannot cross filesystems.

Observability

Prefer built-ins:

  • --preflight: target/workspace/tool probes.
  • --debug --timing-json: sync, command, total timing.
  • --script <file> / --script-stdin: safe multiline direct-provider command.
  • --allow-env NAME + --env-from-profile <file>: exact direct-provider env.
  • CRABBOX_ENV_ALLOW=NAME,...: exact ambient env allowlist.
  • --capture-stdout, --capture-stderr: direct-provider local capture.
  • --capture-on-fail: test artifacts. Treat as secret-bearing until reviewed.
  • --keep-on-failure: retain failed lease for debugging.
  • --results-auto / --junit <path>: structured failure digest.
  • CRABBOX_PHASE:<name> lines: phase timing.

Secrets: exact key only. One command. Never print. Never repo file. Never shell history. No safe injection path? Report live auth blocked. No fake-key upgrade to “live proof.”

Real E2E

“Test in Crabbox” means user path, not merely remote unit tests.

  1. Reproduce entrypoint when feasible.
  2. Patch. Narrow local test.
  3. Remote install/update/onboard/CLI/service/API path.
  4. Record provider, id, command, environment shape, redacted secret source, observed result.
  5. Cleanup.

Route:

  • Install/package: pack tarball; install like user; matching Docker/package lane.
  • Provider/auth: real provider. Scrub unrelated provider vars.
  • Integration: setup, config, send/receive, and inspect redacted logs.
  • Service/session/tool: real CLI or API; inspect persisted state and result.
  • Parser/config: focused tests enough only when OS/package/service cannot matter.

Before/after: same Testbox when practical. Detached temp worktrees under /tmp. Never checkout refs in synced root. For native Testbox, prepare and compare both revisions within one synced invocation; later runs sync the local checkout again. Full-screen CLI: real PTY. Interactive Clack: exact arrows/Enter; raw search typing can lie.

Use the consumer's documented temporary state/config directory so proof cannot mutate the operator's normal installation.

Desktop / Cross-OS

Static hosts:

sh
"$CRABBOX" run --provider ssh --target macos \
  --static-host <macos-host> -- <check-command>
"$CRABBOX" run --provider ssh --target windows --windows-mode normal \
  --static-host <windows-host> -- pwsh -NoProfile -Command '<check-command>'
"$CRABBOX" run --provider ssh --target windows --windows-mode wsl2 \
  --static-host <windows-host> -- <check-command>

Windows/WSL2: prefer Azure when advertised/configured. Native Windows uses OpenSSH + PowerShell + Git + tar. Actions hydration Linux-only.

Brokered macOS: paid EC2 Mac. First quota/no-spend preflight. No silent substitution for Linux proof.

sh
"$CRABBOX" admin hosts quota --provider aws --target macos \
  --region eu-west-1 --type mac2.metal --json
"$CRABBOX" admin hosts allocate --provider aws --target macos \
  --region eu-west-1 --type mac2.metal --dry-run --json

Human desktop: WebVNC preferred when the resolved provider supports it. Do not change providers only to gain desktop support.

sh
"$CRABBOX" warmup --desktop --browser --keep
"$CRABBOX" desktop launch --id <id> \
  --browser --url https://example.com --webvnc --open --take-control
"$CRABBOX" desktop doctor --id <id>
"$CRABBOX" webvnc status --id <id>
"$CRABBOX" artifacts collect --id <id> --all --output artifacts/<slug>

Before handoff, prove CLI/app from neutral ~:

sh
"$CRABBOX" run --id <id> --shell -- \
  "cd ~ && command -v <command> && <command> --version"

Visible desktop alone proves nothing. Keep browser windowed unless capture task. Never commit proof assets to product repo.

Failure Triage

Identify layer: wrapper, provider, hydration, sync, SSH, command.

sh
"$CRABBOX" doctor
"$CRABBOX" status --id <id> --wait
"$CRABBOX" inspect --id <id> --json
"$CRABBOX" history --limit 20
"$CRABBOX" logs <run_id>
"$CRABBOX" results <run_id>
blacksmith testbox list --all
blacksmith testbox status --id <tbx_id>
  • Provider/CLI old: follow the consumer's trusted Crabbox update path.
  • Config/auth: config show, doctor, whoami.
  • Sync quiet/stale: --debug --timing-json, then --full-resync once.
  • Testbox capacity: no retry storm. Report the blocker; change providers only with explicit user approval.
  • Command failure: read phase, failed test, JUnit, skipped shell segment. Focused rerun first.
  • Cleanup unclear: list exact provider. Stop only owned ids.
  • Consumer wrapper broken: use the installed Crabbox CLI only to isolate the wrapper, preserving the same resolved provider.

Crabbox stop does not accept --timing-json.

Boundary

Crabbox stays generic: lease, sync, command, logs, results, timing, cleanup. Consumer setup belongs in that repository's hydration workflow and scripts.

© openclaw, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/crabbox of openclaw/agent-skills.

Open the folder on GitHubat commit 7e73306

Compare with similar skills

Crabbox Remote Test Runner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Crabbox Remote Test Runner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Crabbox Remote Test Runner this skillopenclaw/agent-skills1.1k—~3.6kAutomated safety check: PassMIT
CI Triageandymai/brepjs114—~3.7kAutomated safety check: PassApache-2.0
Dx Code Analyzer Configureforcedotcom/sf-skills1.1k—~5.6kAutomated safety check: PassApache-2.0
Nw Cicd And DeploymentnWave-ai/nWave617—~2.8kAutomated safety check: PassMIT
Knowledge Engineering Quality And DeliveryechoVic/blade-code180—~1.4kAutomated safety check: PassMIT
CI Failure Triage and RepairChachamaru127/claude-code-harness3.2k1 repos~1.1kAutomated safety check: NotesMIT

Similar skills

  • CI Triage

    andymai/brepjs

    This skill should be used when a brepjs GitHub Actions job is red or behaving oddly on github.com (a remote CI run, not a local pre-commit/pre-push hook) — "CI failed", "ci-pass is failing", "npm ci…

    114 GitHub stars~3.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Dx Code Analyzer Configure

    forcedotcom/sf-skills

    Set up, configure, and troubleshoot Salesforce Code Analyzer for any project.

    1.1k GitHub stars~5.6k tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed
  • CI/CD pipeline design methodology, deployment strategies, GitHub Actions patterns, and branch/release strategies.

    617 GitHub stars~2.8k tokensUpdated 21 days ago
    DevOps & CloudAuto-check passed
  • 覆盖 Blade Code 跨测试、构建、资格验证、发布与双语文档的工程质量闭环. An agent skill from echoVic/blade-code.

    180 GitHub stars~1.4k tokensUpdated 10 days ago
    Testing & QAAuto-check passed
  • CI Failure Triage and Repair

    Chachamaru127/claude-code-harness

    Diagnoses failing CI pipelines and tests, deciding first whether the test or the implementation is at fault, and hands hard cases to a dedicated fixer subagent.

    3.2k GitHub starsUsed in 1 repo~1.1k tokens
    DevOps & CloudAuto-check: notes
  • CI Watchdog

    latitude-dev/latitude-llm

    Continuously monitor GitHub PR CI checks and automatically fix failures until all checks pass.

    4.7k GitHub stars~1.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from openclaw/agent-skills

  • Beam

    openclaw/agent-skills

    Publish a redacted local coding session to an authenticated read-only Beam catalog.

    1.1k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Session Viewer

    openclaw/agent-skills

    Render Codex, Claude Code, OpenClaw, or Pi session JSONL transcripts as a searchable, shareable single-file HTML viewer.

    1.1k GitHub stars~918 tokensUpdated today
    Auto-check passed
  • Team Handoff

    openclaw/agent-skills

    Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.

    1.1k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Behavior Validator

    openclaw/agent-skills

    Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.

    1.1k GitHub stars~940 tokensUpdated today
    Auto-check passed
  • Handoff

    openclaw/agent-skills

    Clipboard-ready handoff prompt for another agent to investigate or continue a task.

    1.1k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Readme Standard

    openclaw/agent-skills

    House README standard: structure, badge row, tone, per-archetype templates, and verification gates for steipete/openclaw repos.

    1.1k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Works with

Questions about Crabbox Remote Test Runner

What does Crabbox Remote Test Runner do?

Detects the Crabbox CLI or config in a repository and uses it to run tests and validation on remote runners, with checks before touching secrets or paid infrastructure. yaml` signals that Crabbox is meant for validation work, as does an installed `crabbox` binary, which should pass `crabbox doctor` first.allow`, artifacts and cleanup policy before remote runs.

When should I use Crabbox Remote Test Runner?

Crabbox Remote Test Runner fits situations like: A repository contains crabbox.yaml or .crabbox.yaml; running a large test suite on a remote machine instead of your laptop; proving a change works on another operating system or in a clean environment; keeping auditable logs and artifacts of a validation run.

How do I install Crabbox Remote Test Runner in Claude Code?

Run `npx skills add openclaw/agent-skills --skill crabbox -a claude-code`. Or copy the skill folder (skills/crabbox in openclaw/agent-skills) into .claude/skills/crabbox in your project. Claude Code loads it when a task matches its description.

How do I install Crabbox Remote Test Runner in Codex?

Run `npx skills add openclaw/agent-skills --skill crabbox -a codex`. Or copy the skill folder (skills/crabbox in openclaw/agent-skills) into .agents/skills/crabbox in your project. Codex loads it when a task matches its description.

Can I use Crabbox Remote Test Runner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openclaw/agent-skills --skill crabbox -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/crabbox, .gemini/skills/crabbox, .github/skills/crabbox and .opencode/skills/crabbox in your project.

What does Crabbox Remote Test Runner need to run?

Going by SKILL.md and its folder, Crabbox Remote Test Runner needs the command-line tools its instructions call (jq) and credentials named CRABBOX_TAILSCALE_AUTH_KEY. Our summary lists: The `crabbox` CLI; A coordinator (broker) URL and token for brokered runs; A `crabbox.yaml` or `.crabbox.yaml` in the repository.

Does Crabbox Remote Test Runner access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Crabbox Remote Test Runner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Crabbox Remote Test Runner use?

Crabbox Remote Test Runner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Crabbox Remote Test Runner use?

About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Crabbox Remote Test Runner?

Skills that share tags, products or a category with Crabbox Remote Test Runner: CI Triage (andymai/brepjs, 114 stars), Dx Code Analyzer Configure (forcedotcom/sf-skills, 1.1k stars), Nw Cicd And Deployment (nWave-ai/nWave, 617 stars) and Knowledge Engineering Quality And Delivery (echoVic/blade-code, 180 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Crabbox Remote Test Runner?

openclaw (a GitHub organization) maintains it in openclaw/agent-skills, which has 1,102 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: openclaw/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.