agentleFS
Sign inStart free
Google CloudKnown publisherGoogleCloudPlatform/devrel-demos/agents/charm-persona-quiz-for-agents/AGENTS.md

devrel-demos / charm-persona-quiz-for-agents

AGENTS.md404 starsChanged 13 days agoApache-2.0View on GitHub

  • Reads credentials

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    No try / catch fallback routing: Never catch a live API error or missing API key and substitute synthetic or heuristic scores in …

    line 7

≈ “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

CHARM Workspace Rules (AGENTS.md)

1. Strict Prohibition on Tier 2 / Heuristic Fallbacks (CRITICAL)

  • NEVER use Tier 2 (evaluateBrowserSystemOne, evaluateBrowserDecisions, evaluate_browser_decisions_via_jsc, or any keyword/lexical heuristic) as a runtime fallback when calling the decision model (gemini-decision-1 on POST https://generativelanguage.googleapis.com/v1beta/decisions).
  • Never fail silently. If the live gemini-decision-1 model is unavailable for any reason—including a missing GEMINI_API_KEY, network error, timeout, CORS block, or non-200 HTTP status—both the browser runtime (app.js) and the Python client (charm_gemini/client.py) MUST throw an explicit error and surface it visibly to the user (e.g., via #form-error-banner and #transport-status-pill in the UI, or RuntimeError in Python).
  • No try / catch fallback routing: Never catch a live API error or missing API key and substitute synthetic or heuristic scores in production runtime paths (runSystemOneEvaluation, callGeminiDecisionsApi, handleEvaluateSubmit, call_gemini_decisions_api).
  • Testing isolation only: evaluateBrowserSystemOne (in ocean-core.js) and evaluate_browser_decisions_via_jsc (in charm_gemini/client.py) may only be invoked explicitly inside automated test suites (tests/) to test schema normalization and UI rendering—never as a fallback in user-facing evaluation flows.

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