agentleFS
Sign inStart free
juwonyeejuwonyee/election-risk/AGENTS.md

election-risk

AGENTS.md2 starsChanged 17 days agoMITView on GitHub

Guidelines for agents working on this repository. Installing it instead? See the README. - skills/ is the product: four Agent Skills (profit-structure, candidate-positions, prediction-markets, election-risk), each with SKILL.md, references/, agents/openai.yaml, LICENSE, and scripts/ with a copy of the engine so each works when installed alone. election-risk calls the others by name ($profit-structure); they hand off through files in election-risk-out/. - engine/ is the source of truth for the Python engine (erisk.py + erisk_engine/). Never edit any skills/*/scripts/ directly: edit engine/,…

  • 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 31,542 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 repository5 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, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Keep SKILL.md short (it loads on every use).

    line 33
  2. Distinctive:

    Never add buy/sell language, position sizing, or anything that helps get around a venue's geo-restrictions.

    line 37

≈ “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

Guidelines for agents working on this repository. Installing it instead? See the README.

What lives where

  • skills/ is the product: four Agent Skills (profit-structure, candidate-positions, prediction-markets, election-risk), each with SKILL.md, references/, agents/openai.yaml, LICENSE, and scripts/ with a copy of the engine so each works when installed alone. election-risk calls the others by name ($profit-structure); they hand off through files in election-risk-out/.
  • engine/ is the source of truth for the Python engine (erisk.py + erisk_engine/). Never edit any skills/*/scripts/ directly: edit engine/, then run python3 scripts/sync_engine.py.
  • The policy book (candidate positions) is never committed. Users build it, or download the maintainers' copy from a release with erisk book download --accept-risk.
  • examples/ holds worked company folders (the same layout the engine writes to election-risk-out/).
  • research/ is development material (company notes, market catalogs). It is not installed.
  • .claude-plugin/, .codex-plugin/, .cursor-plugin/, .agents/plugins/, gemini-extension.json make the repo installable as one plugin.

Checks before a change ships

python3 scripts/sync_engine.py --check     # the skill's engine copy matches engine/
python3 scripts/validate_skills.py         # spec: name = folder, description <= 1024 chars, links resolve
python3 -m unittest discover tests         # offline engine tests

Rules for skill content

  • Frontmatter uses only spec fields (name, description, license, compatibility, metadata, allowed-tools) so skills also load on claude.ai and the API.
  • Descriptions: third person, what it does + when to use it.
  • Keep SKILL.md short (it loads on every use); detail goes in references/, linked one level deep with a note on when to read it. Time-sensitive context lives only in skills/election-risk/references/policy.md. The probability table (skills/candidate-positions/references/probability-table.md) changes only with new research in research/probability-table/.
  • Never add buy/sell language, position sizing, or anything that helps get around a venue's geo-restrictions.

Versioning

VERSION, both plugin manifests and the marketplace files share one x.y.z: x = restructure, y = new skill, z = changes to existing skills. Bump metadata.version in any SKILL.md you change.

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