agentleFS
sagarchauhan005sagarchauhan005/agent-sage/.cursor/skills/sage-init/SKILL.md

sage-init

Skill0 starsChanged 5 months agoMITView on GitHub

Bootstrap a new repo for Sage SDLC — creates ./runs/, optional ./Agents.md, .sage-project.json. Use as the first command in a new project before /sage-plan or /sage-orchestrator.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 2 are distinctive, and 6 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.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If $HOME/.sage/install.json is missing, stop.

    line 13
  2. Distinctive:

    Use workspace root as the project directory.

    line 23
  3. Very specific:

    Create ./runs/ and ./runs/.gitkeep if missing.

    line 24
  4. Very specific:

    If ./Agents.md is missing, copy $HOME/.sage/Agents.md → ./Agents.md

    line 32
  5. Very specific:

    If ./Agents.md exists, compare SHA256 to $HOME/.sage/install.json → agents_md_sha256

    line 33
  6. Very specific:

    If different, refresh from $HOME/.sage/Agents.md (fixes stale copies after global updates)

    line 34
  7. Distinctive:

    If the user asked to keep local customizations, do not overwrite

    line 35
  8. Very specific:

    Do not create ./runs/<run-id>/ yet.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
SKILL.md

sage-init

You are Sage Init. Prepare the current workspace for Sage runs.

Prerequisites

If $HOME/.sage/install.json is missing, stop. Tell the user to run global install first:

npx agent-sage install --all
# or: cd /path/to/agent-sage && ./scripts/install.sh --all

Steps

  1. Read agents/sage-init.md.
  2. Use workspace root as the project directory.
  3. Create ./runs/ and ./runs/.gitkeep if missing.
  4. Write ./.sage-project.json with:
    • initialized_at (ISO 8601)
    • sage_home: $HOME/.sage
    • sage_version from $HOME/.sage/VERSION
    • local_agents_md: whether ./Agents.md exists in the project
    • next_command: sage-orchestrator (default)
  5. Agents.md — unless the user asked to skip local copy (--no-agents-md):
    • If ./Agents.md is missing, copy $HOME/.sage/Agents.md → ./Agents.md
    • If ./Agents.md exists, compare SHA256 to $HOME/.sage/install.json → agents_md_sha256
    • If different, refresh from $HOME/.sage/Agents.md (fixes stale copies after global updates)
    • If the user asked to keep local customizations, do not overwrite
    • Record agents_md_sha256 in ./.sage-project.json
  6. CLAUDE.md — if ./CLAUDE.md is missing and $HOME/.sage/CLAUDE.md exists, copy it to ./CLAUDE.md
  7. Do not create ./runs/<run-id>/ yet.

Report

Tell the user:

  • What was created or already present
  • Whether ./Agents.md is a fresh copy, pre-existing, or skipped
  • Whether ./CLAUDE.md was copied (if applicable)
  • Next: /sage-orchestrator (recommended) or /sage-plan

CLI alternative

npx agent-sage init
# or: /path/to/agent-sage/scripts/install.sh --project .

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.