agentleFS
Sign inStart free
albertandrejevalbertandrejev/hopchase/AGENTS.md

hopchase

AGENTS.md0 starsChanged 9 days agoMITView on GitHub

Claude plugin for crypto fund-tracing across Solana, EVM chains and TRON, ending in a case report. Python scripts in scripts/, plugin skills in skills/, manifest in .claude-plugin/.

  • 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 repository4 other files it gives its agents.

The file

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

6 rules. About 0 are common, 1 is distinctive, and 5 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.

  • 5

    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. Distinctive:

    Never push to main; work on a branch and open a PR.

    line 10
  2. Very specific:

    Read API keys only from environment variables via scripts/common.py.

    line 11
  3. Very specific:

    Run python3 tests/test_smoke.py before every PR.

    line 21
  4. Very specific:

    Keep tests/ offline; verify live API behavior by running the script by hand.

    line 22
  5. Very specific:

    Use only the standard library in scripts/.

    line 26
  6. Very specific:

    Write results to stdout and progress to stderr via common.log.

    line 27

≈ “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
<!-- bmad:context --><!-- Verified 2026-11-05 against fe299f0. Managed by bmad-project-context; edits inside this block are replaced on refresh. Keep anything you want preserved outside the markers. -->

hopchase

Claude plugin for crypto fund-tracing across Solana, EVM chains and TRON, ending in a case report. Python scripts in scripts/, plugin skills in skills/, manifest in .claude-plugin/.

Policy

  • Never push to main; work on a branch and open a PR. Commits must be signed and history linear, so no merge commits.
  • Read API keys only from environment variables via scripts/common.py; never write them to output, logs, reports or commits.

Where things are

  • Adding a bridge: follow "Adding a new bridge" in skills/trace-funds/references/bridges.md.
  • Adding a skill or script: add it to the lists in tests/test_smoke.py and to README.md; the test only covers what is listed.

Running and verifying

  • Requires Python 3.11+: the scripts use datetime.UTC.
  • Run python3 tests/test_smoke.py before every PR; there is no CI, so nothing else checks the change. It does not exercise the tracers against live APIs.
  • Keep tests/ offline; verify live API behavior by running the script by hand.

Conventions that differ from defaults

  • Use only the standard library in scripts/; the plugin has no install step. Make HTTP calls through common.http or common.sol_rpc, which handle backoff, not requests.
  • Write results to stdout and progress to stderr via common.log; the skills redirect stdout into trace files.
<!-- /bmad:context -->

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