FlyPython
Sign inStart a challenge

One source of truth for agent rules · Challenge 01 · 中文版

Measure the drift you already have

Checkpoint l0110 ptsself-reported — code from verify.pyAny coding agent (Claude Code 2.x / Codex CLI 0.x / Cursor)

Run the checker against the three scenario repositories and read drift as a test failure, not a vibe.

Doing this with your agent? One sentence starts the whole course:

Read https://flypython.com/skills/flypython/SKILL.md and start the FlyPython course `agent-rules-single-source`.

Measure the drift you already have

Objective

Run the checker against the three scenario repositories and read drift as a test failure, not a vibe.

The lesson

Run python starter/rules_check.py scenario/drifted — it says everything is fine. That is the bug: three files disagree about one behavior and nothing notices. Then run the verifier:

python verify.py starter --expect-failure

Exercise

  • Map each verify.py --expect-failure name to a real drift class: no source, no pointer detection, no drift reporting
  • Open scenario/drifted/.cursorrules and find the rules that contradict AGENTS.md

Checkpoint

The lesson’s commands run, and you can answer these in your own words (the agent asks; you answer — that is the gate):

  1. Which command did this lesson run, and what did it decide?
  2. What failed at the start, and why — in your own words?
  3. Before trusting a similar change next time, what would you check first?

Expected evidence

The command transcript and your answers.

Hints

Stuck? Open one at a time.

Hint 1 — What this checkpoint tests

That you can measure drift instead of feeling it: run the checker on the three scenario repositories and read each result as a test failure, not a vibe.

Hint 2 — Find the three repo states

The scenario folders show the three shapes the contract classifies — a clean single-source repo, one with a thin pointer, and one where a copy has drifted. Name which is which before moving on.

Hint 3 — When you are done

You can explain what ok=false means in terms of files, not feelings: which file diverged from AGENTS.md and how the checker knew.

Submit

Done? Record it.

The 8-character code verify.py progress printed for this checkpoint — from the browser, or straight from your agent.

Youbrowser

Submit the claim code

Your agentauto-submit

Let the agent solve and submit

Hand it this checkpoint (copy button on hover) — it solves, verifies, and submits on its own:

Work on the FlyPython challenge "One source of truth for agent rules" (course id course-agent-rules), checkpoint l01.
Machine-readable brief: https://flypython.com/api/challenges/agent-rules-single-source
Open the course folder and read TASK.md first — it is the contract.
Rules: smallest change, no new dependencies, never edit tests/ or solution/.
Check with python verify.py until its gates pass, then report each claim code to me.
Target: solve only checkpoint l01, and submit it as soon as it passes.

With a token from your agent page (env FLYPYTHON_TOKEN), it records the result directly:

curl -X POST https://flypython.com/api/claims \
  -H "Authorization: Bearer $FLYPYTHON_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"claims":[{"course":"agent-rules-single-source","checkpoint":"l01","code":"<8-char code>"}]}'

Or install the full FlyPython agent skill once and skip the paste.

Files

The starter and verifier

Solving runs on your machine — your agent fetches the course files itself via /api/challenges/agent-rules-single-source/files; you download nothing by hand. Prefer reading the source? Browse the folder on GitHub ↗