agentleFS
Sign inStart free
coreweavecoreweave/forge-agent-lens-for-claude-code/skills/forge-install/SKILL.md

forge-install

Skill9 starsChanged 24 days agoApache-2.0View on GitHub

This skill should be used when the user wants to "install the Forge plugin", "set up Forge", "install forge-agent-lens-for-claude-code", "configure Forge for the first time", "get started with Forge tracing", or needs to complete the initial setup of the Forge Agent Lens for Claude Code plugin including dependency installation and project configuration.

  • Reads credentials
  • Installs packages

We split this skill into the rules it gives an agent

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

  • 6

    Very specific

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

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

    If it fails with a permission error (EACCES on a system Node install), confirm with the user before retrying with sudo npm install -g …

    line 25
  2. Distinctive:

    Do not proceed until this prints a path.

    line 32
  3. Very specific:

    If --force is needed (e.g., rebuilding a corrupted settings.json), run forge-agent-lens-for-claude-code install --force.

    line 47
  4. Very specific:

    Check if project is already set:

    line 51
  5. Very specific:

    If it returns (not set), ask the user for their Forge project (entity/project) and set it:

    line 56
  6. Very specific:

    If wandb_api_key shows (not set) and no WANDB_API_KEY env var is active, ask the user for their key …

    line 68
  7. Very specific:

    All items should show ✓. If anything shows ✗, diagnose and fix before reporting success.

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Forge Agent Lens for Claude Code Plugin — Install

Complete the full installation and initial configuration of the Forge Agent Lens for Claude Code plugin.

Step 0 — Detect prior install state

which forge-agent-lens-for-claude-code
  • Not found → Fresh install. Continue with Step 1.
  • Found → Already installed or being upgraded. Skip Step 1 and continue with Step 2: re-running install both refreshes after an npm upgrade (drift detection fires automatically) and re-validates an existing install.

Step 1 — Install the CLI

npm install -g @coreweave/forge-agent-lens-for-claude-code

If it fails with a permission error (EACCES on a system Node install), confirm with the user before retrying with sudo npm install -g @coreweave/forge-agent-lens-for-claude-code.

Verify:

which forge-agent-lens-for-claude-code

Do not proceed until this prints a path.

Step 2 — Run install

forge-agent-lens-for-claude-code install

This creates ~/.forge-agent-lens-for-claude-code/settings.json, registers the marketplace in Claude Code, and installs the forge plugin at user scope.

The output will include one of:

  • ✓ Marketplace registered (vX.Y.Z) — first time on this machine.
  • ✓ Marketplace already registered (vX.Y.Z) — fully idempotent re-run.
  • ✓ Marketplace refreshed (vOLD → vNEW) followed by ✓ Plugin updated — restart Claude Code to apply — the binary was upgraded since last run; drift detection refreshed the pin and upgraded the loaded plugin.

If --force is needed (e.g., rebuilding a corrupted settings.json), run forge-agent-lens-for-claude-code install --force.

Step 3 — Configure the Forge project

Check if project is already set:

forge-agent-lens-for-claude-code config get project

If it returns (not set), ask the user for their Forge project (entity/project) and set it:

forge-agent-lens-for-claude-code config set project ENTITY/PROJECT

Step 4 — Configure API Key

Check current state:

forge-agent-lens-for-claude-code config show

If wandb_api_key shows (not set) and no WANDB_API_KEY env var is active, ask the user for their key (https://forge.coreweave.com/wandb/authorize) and set it:

forge-agent-lens-for-claude-code config set wandb_api_key API_KEY

Step 5 - (Optional) Custom Agent Name

Traces appear under the agent name claude-code in CoreWeave Forge AgentLens by default. If the user wants a custom name (e.g. to distinguish teams or projects), set it:

forge-agent-lens-for-claude-code config set agent_name CUSTOM_NAME

Skip this step unless the user asks; the default is fine for most users.

Step 6 - Verify

forge-agent-lens-for-claude-code status

All items should show ✓. If anything shows ✗, diagnose and fix before reporting success.

On success, tell the user Claude Code sessions will now be traced to their Forge project starting from the next session. If a Plugin updated or Marketplace refreshed line appeared in Step 2, remind them to run /reload-plugins (or restart Claude Code) so the running session picks up the new code.

Download now (ZIP)

  • Other versions3 projects use a version of this.

    Word for word · 3

    1. wandb/forge-agent-lens-for-claude-code★ 9100% same
    2. wandb/forge-claude-code★ 9100% same
    3. wandb/weave-claude-code★ 9100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

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