agentleFS
Sign inStart free
odinfreeodinfree/storm-ecdsa-harness/AGENTS.md

storm-ecdsa-harness

AGENTS.md4 starsChanged 20 days agoMITView on GitHub

This repository is the public home of the Storm skill collection: agent skills for long optimization campaigns on open benchmarks (ecdsa.fail quantum circuits, the Proximity Prize at better.codes, Kaggle packing contests). Each skill is a folder under skills/ with a SKILL.md; a few single-file skills live directly at skills/*.md.

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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Keep each frontmatter description accurate — that line is what makes agents load the skill.

    line 15
  2. Very specific:

    Run scripts/redaction-check.sh before committing.

    line 17

≈ “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

Agent instructions for this repository

This repository is the public home of the Storm skill collection: agent skills for long optimization campaigns on open benchmarks (ecdsa.fail quantum circuits, the Proximity Prize at better.codes, Kaggle packing contests). Each skill is a folder under skills/ with a SKILL.md; a few single-file skills live directly at skills/*.md.

Conventions

  • Skill format: YAML frontmatter (name, description, whenToUse) plus a Markdown body. Prefer the directory form (skills/<name>/SKILL.md); supporting files live beside the SKILL.md.
  • Attribution: when a skill builds on someone's public work, its README table row and CREDITS.md entry must name the source and licence. Never remove an attribution line.
  • install.sh symlinks every skill into ~/.claude/skills, ~/.codex/skills, and ~/.agents/skills when present. It must stay idempotent and never replace an existing skill.
  • Skills are prompt configuration that agents execute. Treat pull requests like code: review the instructions a skill adds, not just its prose.

Working rules for agents

  • Match the existing style: imperative, compact, no marketing language.
  • Keep each frontmatter description accurate — that line is what makes agents load the skill.
  • Benchmark or score claims in any skill or note must name the evaluator and the date.
  • Run scripts/redaction-check.sh before committing; it must pass. Never commit secrets, session logs, wire files, absolute home paths, or private hostnames.

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