sefaertuncsefaertunc/Worclaude/AGENTS.md

Worclaude

AGENTS.md4 starsChanged 7 months agoMITView on GitHub

worclaude — CLI tool that scaffolds a comprehensive Claude Code workflow into any project.

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 repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-routingSkill
- backend-conventionsSkill
- claude-md-maintenanceSkill
- coding-principlesSkill
- context-managementSkill
- coordinator-modeSkill
- frontend-design-systemSkill
- git-conventionsSkill
- memory-architectureSkill
- planning-with-filesSkill
- project-patternsSkill
- prompt-engineeringSkill
- review-and-handoffSkill
- security-checklistSkill
- subagent-usageSkill
- testingSkill
- verificationSkill

The file

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

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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

Very specific:
Use display.* helpers for user output — never console.log.
line 30
Distinctive:
Read source files before modifying them.
line 33
Very specific:
Every merge to main gets at least a patch version bump (even docs/CI/test-only).
line 49
Distinctive:
Never add Co-Authored-By trailers or AI attribution to commits/PRs.
line 51

≈ “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

worclaude — CLI tool that scaffolds a comprehensive Claude Code workflow into any project.

Tech Stack

Node.js 20+ (pure ESM, no build step)
Commander.js, Inquirer.js, Chalk, Ora, fs-extra
Vitest (1011 tests, 71 files)
ESLint flat config + Prettier
VitePress for docs

Build & Test Commands

npm test                        # Run tests
npm run lint                    # Lint
npm run format                  # Format
npm run docs:build              # Build VitePress docs
node src/index.js <command>     # Test a CLI command locally

Code Conventions

Named exports only (no default exports).
Use display.* helpers for user output — never console.log.
Operate on parsed JSON objects; never text-substitute on stringified JSON.
Cross-platform: path.join, os.platform(), never hardcode separators.
Read source files before modifying them. Ask if ambiguous, do not guess.

Project Structure

src/commands/ — CLI command handlers (init, upgrade, status, doctor, backup, restore, diff, delete, doc-lint, observability, regenerate-routing, scan, setup-state, worktrees)
src/core/ — config, merger, scaffolder, workflow-meta
src/data/ — agent catalogs, stack definitions, routing metadata
src/generators/ — dynamic file generators (agent-routing.md, etc.)
src/utils/ — display, npm helpers, hashing
templates/ — user-facing scaffold content (agents, commands, skills, hooks, settings)
docs/spec/ — SPEC.md (source of truth) and PROGRESS.md (read first every session)

Key Principles

Source of truth: docs/spec/SPEC.md. Features must match the spec exactly.
One feature at a time. Test after each. Commit working increments.
Every merge to main gets at least a patch version bump (even docs/CI/test-only).
Feature branches never modify shared-state files — those are updated on develop via /sync after merging PRs.
Never add Co-Authored-By trailers or AI attribution to commits/PRs.

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