agentleFS
sloiksloik/superforecasting/AGENTS.md

superforecasting

AGENTS.md0 starsChanged 11 days agoMITView on GitHub

This file orients non-Claude agents (Codex, Aider, etc.). Read SKILL.md first. It is the full playbook: the operating mindset, the 8-step forecasting pipeline, the discipline rules, and the tool map. When the user asks a forecasting or consequential-decision question: 1. Run the pipeline in SKILL.md (triage → Fermi-ize → base rate → adjust → weigh → number → update-triggers → log & score), discussing your reasoning out loud. 2. Use the tools in scripts/ instead of doing the math in…

  • 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 33,315 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

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Distinctive:

    When the user asks a forecasting or consequential-decision question:

    line 8
  2. Very specific:

    Run the pipeline in SKILL.md (triage → Fermi-ize → base rate → adjust → weigh → number → update-triggers → log & score), discussing your …

    line 9
  3. Very specific:

    Use the tools in scripts/ instead of doing the math in your head:

    line 11
  4. Very specific:

    All are stdlib-only Python 3: python3 scripts/<name>.py --help.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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 — Superforecasting skill

This file orients non-Claude agents (Codex, Aider, etc.).

Read SKILL.md first. It is the full playbook: the operating mindset, the 8-step forecasting pipeline, the discipline rules, and the tool map.

When the user asks a forecasting or consequential-decision question:

  1. Run the pipeline in SKILL.md (triage → Fermi-ize → base rate → adjust → weigh → number → update-triggers → log & score), discussing your reasoning out loud.
  2. Use the tools in scripts/ instead of doing the math in your head:
    • baserate.py — reference-class base rate + interval (outside view)
    • bayes.py — Bayesian odds update (inside view)
    • montecarlo.py— simulate Fermi-ized range quantities
    • aggregate.py — pool multiple forecasts (ensemble)
    • brier.py — score calibration
    • forecastlog.py — record/resolve/score forecasts All are stdlib-only Python 3: python3 scripts/<name>.py --help.
  3. Verify every real-world fact/base-rate with web or data sources — do not state figures from memory. Before logging, run the rationale-quality checklist in references/rationale-quality.md. Log the final forecast with forecastlog.py.

Deeper material is in references/; reusable templates (including the cross-agent question packet) are in templates/.

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.