agentleFS
ardanlabsardanlabs/kronk/.agents/default/AGENTS.md

kronk / default

AGENTS.md868 starsChanged 13 days agoApache-2.0View on GitHub

Each line is non-negotiable. If the trigger applies, call skill({ name: "..." }) BEFORE writing code or running tools. Optional skills: building-skills (authoring a new skill), code-review (only when the user asks for a formal code review).

  • 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 repository5 other files it gives its agents.

The file

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

5 rules. About 0 are common, 1 is distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify APIs from the live toolchain / docs, not recall.

    line 15
  2. Very specific:

    Use the host's native edit tool first.

    line 17
  3. Very specific:

    Use Kronk MCP web_search for all web research.

    line 18
  4. Very specific:

    Never call http://localhost:9000/mcp directly (curl/wget/fetch).

    line 19
  5. Very specific:

    After editing Go, on each changed package by exact path (not ./...): gofmt -s -w <changed files>, go vet ./<pkg>, staticcheck ./<pkg> if …

    line 20

≈ “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

MANDATORY SKILLS — load BEFORE acting

Each line is non-negotiable. If the trigger applies, call skill({ name: "..." }) BEFORE writing code or running tools.

  • Any .go file (read, write, modify) → skill({ name: "use-modern-go" })
  • Web research, or fallback edit when the host's exact-match edit fails → skill({ name: "kronk-mcp" })

Optional skills: building-skills (authoring a new skill), code-review (only when the user asks for a formal code review).

Rules

  • Senior software engineer. Be concise.
  • Verify APIs from the live toolchain / docs, not recall.
  • Double-check tool call arguments before submitting.
  • Use the host's native edit tool first; fall back to Kronk MCP fuzzy_edit only on exact-match failure.
  • Use Kronk MCP web_search for all web research.
  • Never call http://localhost:9000/mcp directly (curl/wget/fetch). If kronk-mcp fails, stop and report.
  • After editing Go, on each changed package by exact path (not ./...): gofmt -s -w <changed files>, go vet ./<pkg>, staticcheck ./<pkg> if installed, then go test ./<pkg>. Fix the code; don't suppress diagnostics. The project's own AGENTS.md wins (env vars, forbidden test dirs).

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.