agentleFS
Sign inStart free
terry2010terry2010/surfbird/AGENTS.md

surfbird

AGENTS.md1 starsChanged yesterdayApache-2.0View on GitHub

Unofficial self-hosted Docker distribution of Cloudflare Kitesurf. See README.md.

  • 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 31,439 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 repository2 other files it gives its agents.

The file

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

2 rules. About 0 are common, 0 are distinctive, and 2 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.

  • 2

    Very specific

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

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

    Keep KITESURF_REF pinned to a commit/tag.

    line 22
  2. Very specific:

    No auth bypasses: auth mode must fail closed when SURFBIRD_TOKEN is empty.

    line 24

≈ “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

AGENTS.md — repo guide for coding agents

Unofficial self-hosted Docker distribution of Cloudflare Kitesurf. See README.md.

Layout

  • Dockerfile — full multi-stage build (raw/auth targets); Dockerfile.prebuilt for prebuilt engine trees
  • proxy/index.mjs — auth + REST proxy (all endpoint logic lives here)
  • entrypoint.sh — container process supervision (raw=engine only, auth=engine+proxy)
  • mcp/server.mjs — thin MCP stdio server wrapping the REST actions; mcp/server.json — MCP Registry metadata (version must match package.json before mcp-publisher publish)
  • skills/surfbird/SKILL.md — agent-facing REST usage doc
  • examples/ — python + bash clients
  • scripts/ci-smoke.sh — container smoke test (used by CI); scripts/smoke-test.sh — local prebuilt image test
  • upstream-tag.txt — last released upstream kitesurf tag (CI-managed)
  • scripts/metrics.mjs — daily npm/Docker Hub stats → metrics/data.jsonl + dashboard.md (both CI-managed)
  • bazel-downloader.cfg — optional China-mirror URL rewrites (--build-arg MIRRORS=1)
  • docs/ is gitignored — local notes only, never commit it

Rules

  • Never cut a release/tag/npm-publish without the user's explicit confirmation of version + changelog.
  • Keep KITESURF_REF pinned to a commit/tag; never default to main.
  • Patches in patches/ must apply cleanly (git apply --check); a failed patch fails the build. patches/*.patch is gitignored — patches are a local-only escape hatch, not for committing.
  • No auth bypasses: auth mode must fail closed when SURFBIRD_TOKEN is empty.
  • Probe /json/version for liveness (upstream added /health in 2026.11.9, but /json/version also verifies CDP discovery).
  • Turndown runs in the proxy (Node), NOT in-page — Boa's DOM shim breaks it.
  • Container ports must never bind 0.0.0.0 in examples/docs unless explicitly requested — use 127.0.0.1 bindings.

Verify

  • bash -n all shell scripts; node --check JS.
  • Full check: bash scripts/ci-smoke.sh <image> against a locally built image.
  • CI: .github/workflows/release.yml — daily upstream-tag watch → build → smoke → push; metrics.yml — daily stats → commits dashboard.md.

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