agentleFS
elfrostelfrost/ai-patchlab/.agents/skills/upgrade-status/SKILL.md

upgrade-status

Skill1 starsChanged 31 days agoMITView on GitHub

Compare the current project's template adoption to the latest template state and report what's available but not yet pulled in. Use to decide whether to run `ez-upgrade-project.ps1 -Force`.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read-only report of the gap between this project's template version and the latest available state of the EzProject template repo.

    line 8
  2. Distinctive:

    Ask the user for the path if none of the above resolve

    line 15
  3. Very specific:

    Verify by checking that the resolved path contains template/.ezproject.json, DECISIONS.md, and template/.claude/commands/.

    line 17
  4. Very specific:

    Read .ezproject.json in the current directory and extract template_version, created, mode, stack, runtimes.

    line 20
  5. Distinctive:

    Never modify the project. Read-only.

    line 42
  6. Distinctive:

    Always print the exact command to run, with the full path resolved.

    line 43
  7. Distinctive:

    Keep output under 40 lines.

    line 44
  8. Very specific:

    If the template path cannot be located, ask once and suggest setting EZ_TEMPLATE_PATH.

    line 45

≈ “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

Upgrade Status

Read-only report of the gap between this project's template version and the latest available state of the EzProject template repo.

Phase 1: Locate the template repo

Try in order:

  1. $EZ_TEMPLATE_PATH env var
  2. <user-home>/OneDrive/ez-project-template/ (Windows default; resolve <user-home> via the standard home-directory API)
  3. ~/ez-project-template/ or ~/dev/ez-project-template/ (Unix defaults)
  4. Ask the user for the path if none of the above resolve

Verify by checking that the resolved path contains template/.ezproject.json, DECISIONS.md, and template/.claude/commands/.

Phase 2: Read project state

Read .ezproject.json in the current directory and extract template_version, created, mode, stack, runtimes. If missing, this is not a generated EzProject — explain and exit.

Phase 3: Read template state

  • <template>/template/.ezproject.json for current template_version
  • <template>/DECISIONS.md for ADRs with **Date:** YYYY-MM-DD and **Status:** accepted
  • Listings of <template>/template/.claude/commands/, <template>/template/.claude/agents/, and (if Codex is enabled) <template>/template/.agents/skills/

Phase 4: Compute drift

  1. ADRs accepted strictly after the project's created date
  2. Commands present in template but missing in project
  3. Agents present in template but missing in project
  4. Codex skills present in template but missing in project (only if runtimes includes Codex)

Phase 5: Output

Print a compact report:

  • Project version + created date + mode/stack/runtimes
  • Template version and its on-disk path
  • ADRs added since project creation (count + list)
  • New commands / agents / skills available (counts + lists)
  • Recommendation: exact ez-upgrade-project.ps1 -Force command with full template path, or "in sync, nothing to do"

Rules

  • Never modify the project. Read-only.
  • Always print the exact command to run, with the full path resolved.
  • Keep output under 40 lines.
  • If the template path cannot be located, ask once and suggest setting EZ_TEMPLATE_PATH.

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.