agentleFS
Sign inStart free
ozkilimozkilim/runway/skill/AGENTS.md

runway / skill

AGENTS.md2 starsChanged 3 months agoMITView on GitHub

Claude Code users don't need this file — install.sh installs the skill automatically. For any other agent (Cursor, Codex, Windsurf, Aider, ...), paste the block below into your agent's instructions file (AGENTS.md, .cursorrules, CONVENTIONS.md, whatever your tool reads), replacing the two paths with the ones install.sh printed. When I ask about cloud spend, cloud costs, credits, burn, or runway, run: and show me the table it prints. Rules: - Always run it fresh — never answer spend questions from memory…

  • 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 31,774 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.

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    When I ask about cloud spend, cloud costs, credits, burn, or runway, run:

    line 13
  2. Distinctive:

    Always run it fresh — never answer spend questions from memory or from earlier numbers in the conversation.

    line 21
  3. Distinctive:

    Add at most one line underneath, only if something genuinely warrants it: real cash charged beyond credits, one month far outside the …

    line 24
  4. Very specific:

    Never invent a "months of runway left" figure unless I explicitly ask.

    line 27
  5. Very specific:

    Never shell out to aws, az, or gcloud for this — the script uses the SDKs deliberately.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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

runway — snippet for any coding agent

Claude Code users don't need this file — install.sh installs the skill automatically. For any other agent (Cursor, Codex, Windsurf, Aider, ...), paste the block below into your agent's instructions file (AGENTS.md, .cursorrules, CONVENTIONS.md, whatever your tool reads), replacing the two paths with the ones install.sh printed.

Cloud spend ("runway")

When I ask about cloud spend, cloud costs, credits, burn, or runway, run:

<REPO_PATH>/.venv/bin/python <REPO_PATH>/runway.py

and show me the table it prints. Rules:

  • Always run it fresh — never answer spend questions from memory or from earlier numbers in the conversation; they go stale.
  • Show the output and stop. No preamble, no restating figures, no summary.
  • Add at most one line underneath, only if something genuinely warrants it: real cash charged beyond credits, one month far outside the baseline (name the service responsible), or a data-quality warning in the output.
  • Never invent a "months of runway left" figure unless I explicitly ask; if I do, give a range and state the assumption.
  • --json gives the raw payload for follow-up computation. --check smoke-tests credentials. --provider aws|azure|gcp limits to one cloud.
  • Config lives at ~/.runway/config.yaml (mode 600). Setup guides: <REPO_PATH>/docs/setup/.
  • Never shell out to aws, az, or gcloud for this — the script uses the SDKs deliberately.

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