agentleFS
kimgoetzkekimgoetzke/coding-agent-configs/skills/update-agents/SKILL.md

update-agents

Skill2 starsChanged 7 months agoMITView on GitHub

Check for and apply updates to locally installed agents from the kimgoetzke/coding-agent-configs GitHub repo. Use when user asks to update agents, sync agents, check for agent updates, or mentions updating their agents.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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
  1. Very specific:

    Check for updates to locally installed agents by fetching the latest from kimgoetzke/coding-agent-configs on GitHub and comparing against …

    line 9
  2. Distinctive:

    If you cannot determine which tool you are, ask the user.

    line 24
  3. Distinctive:

    If you are Claude Code, set:

    line 32
  4. Distinctive:

    If you are Copilot, set:

    line 35
  5. Distinctive:

    If you are Pi, set:

    line 38
  6. Distinctive:

    If you cannot determine which tool you are, ask the user before proceeding.

    line 42
  7. Distinctive:

    Only use the directory for the currently running tool.

    line 44
  8. Distinctive:

    Run the check script using the current tool's skill directory:

    line 48
  9. Very specific:

    If ALL_UP_TO_DATE: tell the user all agents are up to date and stop

    line 69
  10. Distinctive:

    Ask the user if they want to apply this update

    line 73
  11. Distinctive:

    After processing all agents, print a summary:

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Update Agents

Check for updates to locally installed agents by fetching the latest from kimgoetzke/coding-agent-configs on GitHub and comparing against the local agents directory for the current coding agent product.

Configuration

  • Remote repo: https://github.com/kimgoetzke/coding-agent-configs.git
  • Scripts location: Bundled in this skill's scripts/ directory

Target directory by tool

ToolDefault target directory
Claude Code~/.claude/agents
Copilot~/.copilot/agents
Pi~/.pi/agent/agents

If you cannot determine which tool you are, ask the user.

Workflow

1. Determine the current tool and target directory

First determine which tool is currently running this skill:

  • If you are Claude Code, set:
    • TARGET_DIR=~/.claude/agents
    • SKILL_DIR=~/.claude/skills/update-agents
  • If you are Copilot, set:
    • TARGET_DIR=~/.copilot/agents
    • SKILL_DIR=~/.copilot/skills/update-agents
  • If you are Pi, set:
    • TARGET_DIR=~/.pi/agent/agents
    • SKILL_DIR=~/.pi/agent/skills/update-agents

If you cannot determine which tool you are, ask the user before proceeding.

Only use the directory for the currently running tool. Do not check or update the other tool's agents directory.

2. Check for updates

Run the check script using the current tool's skill directory:

bash "$SKILL_DIR/scripts/check-updates.sh" "$TARGET_DIR"

3. Parse the output

The script outputs one line per agent file with a status prefix:

PrefixMeaning
UP_TO_DATE:<name>No changes
CHANGED:<name>Files differ - diff follows until END_DIFF line
MISSING_LOCALLY:<name>Exists in repo but missing locally
ALL_UP_TO_DATENo updates available at all

Agent files that exist locally but not in the remote repo are ignored.

4. Present results to the user

  • If ALL_UP_TO_DATE: tell the user all agents are up to date and stop
  • Otherwise, FOR EACH CHANGED or MISSING_LOCALLY agent file:
    • List the file name and summarise what changed
    • Show the diff in a code block
    • Ask the user if they want to apply this update

5. Apply updates

For each agent file the user approves, run:

bash "$SKILL_DIR/scripts/apply-update.sh" "$TARGET_DIR" <agent-file>

Report success or failure for each.

6. Summary

After processing all agents, print a summary:

  • How many agents were updated
  • How many were skipped
  • How many were already up to date

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.