agentleFS
Sign inStart free
hcsolakogluhcsolakoglu/sidekick/skills/hermes/SKILL.md

sidekick

Skill1 starsChanged 4 months agoMITView on GitHub

Orchestrate persistent local agent workers with Sidekick

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. sksareen/sidekick★ 1same name
    2. specscore/specstudio-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run sidekick spawn ENGINE NAME --dir PATH -- "PROMPT" with a bounded scope and verification.

    line 18
  2. Very specific:

    Start one background sidekick wait NAME...

    line 19
  3. Very specific:

    Use adopt for an existing session, tail for live output, and cancel for a resumable full-tree stop.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sidekick

Procedure

  1. Run sidekick doctor ENGINE.
  2. Inspect sidekick capabilities ENGINE --model MODEL --json before choosing a model-dependent control.
  3. Run sidekick spawn ENGINE NAME --dir PATH -- "PROMPT" with a bounded scope and verification. Use separate control flags only when native evidence marks them supported.
  4. Start one background sidekick wait NAME... --all --json for the batch; continue independent work.
  5. Harvest sidekick result NAME --json and check terminal status plus exitCode.
  6. Continue with sidekick send NAME -- "FOLLOW-UP"; persisted controls are immutable and send accepts no control overrides.

Use adopt for an existing session, tail for live output, and cancel for a resumable full-tree stop. Avoid overlapping file ownership and busy polling.

Sidekick records separate requested, applied, and effective observations. An argv flag alone is not effective-provider evidence. Unsupported, malformed, model-dependent-unverified, or runtime-version-mismatched explicit values fail closed with exit 2. Devin family slug glm-5.2 and variant UID glm-5-2 are not silently aliased; --mode high is not an effort setting.

Hermes oneshot currently has no public per-run --effort flag. Global Hermes agent.reasoning_effort config is outside Sidekick's per-run control plane and is not rewritten by Sidekick. Explicit Hermes non-auto --effort fails closed until a native per-run surface exists. For high-effort reviews prefer Codex/Claude with native effort flags.

Do not concurrently spawn workers with the same --dir: harness session discovery and workspace state can be directory-scoped, causing contention, serialization, or overlapping edits. Use a separate git worktree and --dir for each parallel worker. Otherwise serialize the work and continue the existing run with sidekick send.

Hermes prompts near 32 KB are unsafe on native Windows because Hermes oneshot accepts argv only; use WSL or another engine.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free