Create Repo Agent
langfuse/langfuse
Design, implement, review, or harden Langfuse repo-owned autonomous agents.
Run and debug Preloop local CI — GitHub Actions-compatible workflows executed in one isolated microVM per job (smolvm/libkrun).
$ npx skills add preloopdev/preloop --skill preloop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install preloopdev/preloop preloop --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/preloopdev/preloop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/preloop .claude/skills/preloop && rm -rf skills-srcUse ~/.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/
Install the "preloop" agent skill from https://github.com/preloopdev/preloop/tree/main/skills/preloop into .claude/skills/preloop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "preloop", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/preloopdev/preloop/tree/main/skills/preloopType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add preloopdev/preloop --skill preloop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install preloopdev/preloop preloop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/preloopdev/preloop.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/preloop .agents/skills/preloop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "preloop" agent skill from https://github.com/preloopdev/preloop/tree/main/skills/preloop into .agents/skills/preloop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "preloop", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add preloopdev/preloop --skill preloop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install preloopdev/preloop preloop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/preloopdev/preloop.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/preloop .cursor/skills/preloop && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "preloop" agent skill from https://github.com/preloopdev/preloop/tree/main/skills/preloop into .cursor/skills/preloop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "preloop", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/preloopdev/preloop.git --path skills/preloop--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add preloopdev/preloop --skill preloop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install preloopdev/preloop preloop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/preloopdev/preloop.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/preloop .gemini/skills/preloop && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "preloop" agent skill from https://github.com/preloopdev/preloop/tree/main/skills/preloop into .gemini/skills/preloop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "preloop", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install preloopdev/preloop preloopInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add preloopdev/preloop --skill preloop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/preloopdev/preloop.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/preloop .github/skills/preloop && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "preloop" agent skill from https://github.com/preloopdev/preloop/tree/main/skills/preloop into .github/skills/preloop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "preloop", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add preloopdev/preloop --skill preloop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install preloopdev/preloop preloop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/preloopdev/preloop.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/preloop .opencode/skills/preloop && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "preloop" agent skill from https://github.com/preloopdev/preloop/tree/main/skills/preloop into .opencode/skills/preloop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "preloop", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
preloopRun and debug Preloop local CI — GitHub Actions-compatible workflows executed in one isolated microVM per job (smolvm/libkrun).
Preloop is an agent skill from preloopdev/preloop. Run and debug Preloop local CI — GitHub Actions-compatible workflows executed in one isolated microVM per job (smolvm/libkrun). Use when the user asks to run or plan a workflow locally, submit CI, debug a failed job, retry a failed step in its live VM, open a shell in a preserved VM, manage the local runner pool or GitHub credentials, or work with the preloop CLI, preloopd, or the aksh control plane. Triggers: "preloop run", "run CI locally", "run this workflow", "CI failed", "debug the failure", "retry the…
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering Autonomous loops and CI/CD. It works with GitHub Actions and GitHub. The repository describes itself as: agent-native, drop-in Github Actions that run locally or self-hosted in microvms, with debug/pause-on-failure and step-level retries. The licence is MIT.
Read from SKILL.md and the folder at commit 992e3b8. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
justFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
AKSH_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Preloop loads about 2.2k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 691 words of instructions outside code blocks.
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.
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.
The full file from preloopdev/preloop at commit 992e3b8, republished under its MIT licence (© preloopdev). 691 words, ~2,186 tokens.
.claude/skills/preloop/SKILL.md (or your agent's skills folder).Preloop is a macOS-first local/self-hosted/managed CI platform. It reimplements the
GitHub Actions control plane (aksh) and a faithful Rust runner, and executes each
job in an isolated Linux microVM via smolvm (libkrun) on Apple Silicon, with
Firecracker as the scale-tier executor. Workflows are drop-in GitHub Actions YAML;
the unmodified official runner also works against aksh.
Source of truth for this skill: the CLI at crates/preloop-cli/src/main.rs (current
subcommands only — docs under preloop/docs/ are partly aspirational; verify a
command exists before using it).
preloop secret list returns names only, never values.preloop run -f <workflow> # run; on failure a TTY run pauses the VM
preloop debug --json # read the paused session as JSON (agents/scripts)
<edit source on the host>
preloop debug --verdict retry --sync --from <step>
# sync host edits into the VM, re-run from that step
preloop debug --verdict continue # keep going from the paused step
preloop debug --verdict abort # tear down, mark failedInteractive preloop run pauses at a failed step and holds the microVM open so
you can fix and retry from that step. Non-interactive runs (--detach, piped
stdout, CI) never pause; pass --preserve-on-failure to keep the failed VM alive
for a later preloop shell.
preloop run [-f <path>] [--job <id>] [--event <trigger>] [--payload <file.json>]
[--base <ref>] [--secret NAME=VALUE] [-d|--detach] [--no-debug]
[--preserve-on-failure]-f — workflow file. A bare filename like ci.yml resolves inside
.github/workflows/; a path is used as-is. When omitted, discovers workflows
whose triggers match the current repo state/event.--job — single job by its YAML key; includes the needs: dependency closure.--event — simulate a trigger (push, pull_request, merge_group, …);
--payload supplies a webhook body JSON; --base sets the base ref for
pull_request/merge_group.--detach — submit and return without streaming events.--no-debug — tear down on failure instead of pausing (default when detached).preloop plan # expanded job DAG + matrix, no execution
preloop status # active and recent runs
preloop logs # run logs
preloop cancel # cancel current runpreloop shell [session-id|run-id|job-name] # PTY into the preserved VM
preloop debug [session] --json # session as JSON, exit (agents)
preloop debug [session] --verdict retry [--sync] [--force]
[--from <step>|--from-start] [--revert none|untracked|all]
preloop debug [session] --verdict continue|abort
preloop debug [session] --export [--patch-only] # pull VM-side edits back to host--sync — copy host source changes into the VM before retrying. A file changed
on both sides aborts unless --force.--from <step> — re-run from a 1-based step number or display name (must be at
or before the failed step); --from-start re-runs from the first user step.--revert — undo the failed attempt's workspace debris: none (default),
untracked, or all.--export — bring edits made inside the VM back to the host workspace.preloop secret set <NAME> [--value V | stdin] [--repo owner/repo]
preloop secret list [--repo owner/repo] # names only, never values
preloop secret rm <NAME> [--repo owner/repo]
preloop setup github # GitHub App or fine-grained PAT
preloop doctor # verify credential configpreloop serve [--listen ADDR] [--public-url URL] [--github-app-id ID]
[--github-app-key PATH] [--github-app-installation-id ID]
[--webhook-secret SECRET] [--save]
preloop update # poll GitHub Releases, atomically install matching binaryserve is the self-hosting entry point: control plane + microVM runner pool in the
foreground, serving the GitHub webhook and Checks endpoints. --public-url must be
the URL GitHub and remote runners can actually reach. Hidden alias: engine.
| Variable | Meaning |
|---|---|
AKSH_URL | server base URL; default http://127.0.0.1:9090 |
AKSH_TOKEN | API token for the server |
PRELOOP_HOME | state dir; default ~/.preloop |
PRELOOP_LISTEN / PRELOOP_PUBLIC_URL | override serve --listen / --public-url |
PRELOOP_RUNNER_LABELS | comma-separated extra runs-on labels (e.g. declare X64 on an ARM host) |
PRELOOP_RUNNER_POOL_SIZE | override warm runner pool size (memory-bounded, cap 8) |
PRELOOP_RUNNER_STORAGE_GB | persistent guest storage per runner; use 80 or more for full hosted-image OCI snapshots |
PRELOOP_RUNNER_PACK_PROXY / PRELOOP_RUNNER_PACK_NO_PROXY | proxy and bypass list for smolvm's registry export VM during golden packing |
PRELOOP_RUNNER_BASE_IMAGE / PRELOOP_RUNNER_BUNDLE / PRELOOP_RUNNER_DNS / PRELOOP_RUNNER_OVERLAY_GB / PRELOOP_RUNNER_NAME_PREFIX / PRELOOP_RUNNER_POOL_ENABLED / PRELOOP_USE_FORK / PRELOOP_USE_PACKED_GOLDEN / PRELOOP_WORKSPACE | runner pool / VM tuning knobs (full semantics in crates/preloop-cli/src/main.rs) |
Runner execution defaults: packed goldens enabled, warm pool disabled, one
single-use VM provisioned per queued job, and concurrency capped by host CPU.
Each VM receives 4 vCPUs and a 4096 MiB ballooned memory ceiling. Set
PRELOOP_RUNNER_POOL_ENABLED=true to keep warm runners (size is memory-bounded,
cap 8), or PRELOOP_USE_PACKED_GOLDEN=false to force cold OCI provisioning.
preloop/docs/09_agent_loop_retry_and_fork.md)Classify failures before retrying — do not burn loops on the wrong fix:
| Classification | Suggested action |
|---|---|
test_failure / compile_failure | edit source, retry step |
missing_secret | request/update policy, don't hack around it |
network_blocked | inspect the egress allowlist/policy |
cache_miss | continue, or warm the cache |
resource_oom / disk_quota | raise resources or fix the test |
timeout | optimize or raise the timeout |
infra_failure | retry job or report a bug |
fidelity_unsupported | unsupported workflow feature — record the gap, don't fake it |
just build-preloop # macOS CLI + ARM64 Linux runner (zigbuild)
just preloop-run WF=fixtures/workflows/failing.yml # run, pause on failure
just preloop-run-detached WF=... # submit, keep VM preserved
just preloop-shell # shell into the most recent preserved VM
just serve / serve-dev # aksh control plane on 127.0.0.1:9090
just test-ci # fmt-check + clippy + tests (the full gate)
just dogfood # E2E with the real official runner
just conform / conform-server-deep # protocol conformance gatesKey paths: crates/preloop-cli/src/main.rs (CLI), crates/preloop-orchestrator/,
crates/preloop-vm/ (smolvm provider), preloop/docs/00_index.md (design docs),
fixtures/workflows/ (sample workflows), goals/ (agent CI benchmarks).
Never report "fixed" on a dirty retry alone. The final verdict must come from a
clean run: fresh VM, clean overlay, strict network/secrets/cache policy. The repo
gate is just test-ci plus just conform for protocol fidelity.
© preloopdev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/preloop of preloopdev/preloop.
Open the folder on GitHubat commit 992e3b8
Preloop 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Preloop this skillpreloopdev/preloop | 175 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Create Repo Agentlangfuse/langfuse | 35k | — | ~730 | Automated safety check: Pass | Custom licence | |
| Nushellccusage/ccusage | 19k | — | ~938 | Automated safety check: Pass | Custom licence | |
| AI News RadarLearnPrompt/ai-news-radar | 1.8k | — | ~2.5k | Automated safety check: Notes | MIT | |
| Make GitHub Actions Workflowdotnet/efcore | 15k | — | ~1.7k | Automated safety check: Pass | MIT | |
| ONNX Runtime CI Managementmicrosoft/onnxruntime | 22k | — | ~4.1k | Automated safety check: Pass | MIT |
langfuse/langfuse
Design, implement, review, or harden Langfuse repo-owned autonomous agents.
ccusage/ccusage
Guides ccusage Nushell scripts. An agent skill from ccusage/ccusage.
LearnPrompt/ai-news-radar
A skill your agent uses when working on AI News Radar, 24 小时 AI 更新雷达, AI 更新雷达, 伯乐Skill, or Scout Skill: finding high-signal AI/tech sources, adding RSS/OPML/GitHub feeds, checking source health…
dotnet/efcore
Create GitHub Actions workflows for CI, automation, or PR management.
microsoft/onnxruntime
Triggers, re-runs and unblocks the CI checks on an ONNX Runtime pull request, after diagnosing whether a failure is transient or needs a code change.
latitude-dev/latitude-llm
Continuously monitor GitHub PR CI checks and automatically fix failures until all checks pass.
Works with
Categories
Run and debug Preloop local CI — GitHub Actions-compatible workflows executed in one isolated microVM per job (smolvm/libkrun). Preloop is an agent skill from preloopdev/preloop. Run and debug Preloop local CI — GitHub Actions-compatible workflows executed in one isolated microVM per job (smolvm/libkrun).
Preloop fits situations like: the user asks to run; plan a workflow locally; debug a failed job; retry a failed step in its live VM.
Run `npx skills add preloopdev/preloop --skill preloop -a claude-code`. Or copy the skill folder (skills/preloop in preloopdev/preloop) into .claude/skills/preloop in your project. Claude Code loads it when a task matches its description.
Run `npx skills add preloopdev/preloop --skill preloop -a codex`. Or copy the skill folder (skills/preloop in preloopdev/preloop) into .agents/skills/preloop in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add preloopdev/preloop --skill preloop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/preloop, .gemini/skills/preloop, .github/skills/preloop and .opencode/skills/preloop in your project.
Going by SKILL.md and its folder, Preloop needs the command-line tools its instructions call (just) and credentials named AKSH_TOKEN. Our summary lists: Docker; A credential in AKSH_TOKEN.
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.
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.
Preloop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Preloop: Create Repo Agent (langfuse/langfuse, 35k stars), Nushell (ccusage/ccusage, 19k stars), AI News Radar (LearnPrompt/ai-news-radar, 1.8k stars) and Make GitHub Actions Workflow (dotnet/efcore, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
preloopdev (a GitHub organization) maintains it in preloopdev/preloop, which has 175 GitHub stars. The repository was last updated on October 7, 2026.
Source: preloopdev/preloop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.