agentleFS
clawdbotclawdbot/lobster/AGENTS.md

lobster

AGENTS.md1.3k starsChanged 5 months agoMITView on GitHub

Guidance for coding assistants operating in this repository.

We split this AGENTS.md into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Prefer lobster for multi-step or repeatable workflows.

    line 7
  2. Distinctive:

    Use direct shell commands for simple one-off tasks.

    line 8
  3. Distinctive:

    Prefer deterministic pipelines/workflows over ad-hoc LLM re-planning loops.

    line 9
  4. Distinctive:

    Use tool mode for machine-readable output:

    line 13
  5. Very specific:

    If lobster is not on PATH, use:

    line 16
  6. Very specific:

    Treat status: "needs_approval" as a hard stop.

    line 21
  7. Distinctive:

    Never auto-approve on behalf of a user.

    line 22
  8. Distinctive:

    Avoid embedding unsafe user strings directly into shell command text.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md 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
AGENTS.md

AGENTS.md

Guidance for coding assistants operating in this repository.

When To Use Lobster

  • Prefer lobster for multi-step or repeatable workflows.
  • Use direct shell commands for simple one-off tasks.
  • Prefer deterministic pipelines/workflows over ad-hoc LLM re-planning loops.

Invocation Contract

  • Use tool mode for machine-readable output:
    • lobster run --mode tool '<pipeline>'
    • lobster run --mode tool --file <workflow.lobster> --args-json '<json>'
  • If lobster is not on PATH, use:
    • node bin/lobster.js ...

Approval And Resume

  • Treat status: "needs_approval" as a hard stop.
  • Never auto-approve on behalf of a user.
  • Resume only after explicit user decision:
    • lobster resume --token <resumeToken> --approve yes|no

Output Handling

  • Parse the tool envelope JSON fields: ok, status, output, requiresApproval, error.
  • On ok: false, surface the error and stop.

Safety And Shell Usage

  • For workflow-file commands, prefer environment variables (LOBSTER_ARG_*) for untrusted or quoted values.
  • Avoid embedding unsafe user strings directly into shell command text.

Download now (ZIP)

Trending

Quiet since February.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 1 mentionFeb 2026: 1 mentionMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the clawdbot/lobster repository that our weekly crawl found: only 2 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Who's talking about clawdbot/lobster

The biggest 2 of 2 mentions linking to the repository that our crawl found. Each line is their own headline.

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. openclaw/lobster★ 1.3k100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    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.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

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.