agentleFS
Ju571nKJu571nK/lodeline/AGENTS.md

lodeline

AGENTS.md17 starsChanged yesterdayApache-2.0View on GitHub

For Lodeline Proxy work, read the specification entry point, agent roles and operating rules, and current execution status before starting.

  • 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 32,671 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 repository2 other files it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    Before implementing any issue tied to a generative AI product, verify that product's current behavior using official documentation, release …

    line 10
  2. Distinctive:

    Use a lower-cost model for broad changelog discovery and classification, then use a stronger model to validate security implications, …

    line 13
  3. Distinctive:

    Keep research scoped per product and date-stamped so later issue work can reuse it without repeating full discovery.

    line 14
  4. Very specific:

    Read apps/manager/AGENTS.md and apps/manager/README.md before assigning work on the fleet console.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Imported Claude Cowork project instructions

GitHub Issue Triage

  • Conserve tokens when inspecting GitHub issues: request only the fields and number of results needed for the task, then summarize rather than reproducing full issue bodies.
  • A lower-cost model may be used for routine issue discovery, classification, and status summaries. Use a stronger model when implementation planning, security analysis, or conflicting requirements require deeper reasoning.

Generative AI Compatibility Gate

  • Before implementing any issue tied to a generative AI product, verify that product's current behavior using official documentation, release notes, and the locally installed version when available.
  • Record changes to configuration paths and precedence, permission or approval modes, hook events and payloads, MCP/tool behavior, unattended modes, and platform-specific behavior before changing code.
  • Distinguish documented behavior from hardware-verified behavior. Do not remove compatibility gates or enable enforcement from documentation alone when the repository records conflicting measurements.
  • Use a lower-cost model for broad changelog discovery and classification, then use a stronger model to validate security implications, resolve contradictions, and define implementation scope.
  • Keep research scoped per product and date-stamped so later issue work can reuse it without repeating full discovery.

Lodeline Proxy Agent Workflow

For Lodeline Proxy work, read the specification entry point, agent roles and operating rules, and current execution status before starting.

  • The primary assistant is the orchestrator and the user's single reporting interface.
  • Delegate scoped research, coding, independent review, and verification as the authorized task requires.
  • Role definitions are not running agents; start workers only for concrete tasks and respect runtime limits.
  • Assign one writer per file; link assignments and results to requirement and acceptance IDs.
  • Preserve compatibility gates and distinguish implementation, review, and hardware verification.
  • Maintain execution status and report integrated results to the user.
  • Read apps/manager/AGENTS.md and apps/manager/README.md before assigning work on the fleet console.

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.