agentleFS
aarontzengaarontzeng/dev-lead/skills/quota-setup/SKILL.md

quota-setup

Skill3 starsChanged 7 days agoMITView on GitHub

Set this host up so that the dev-lead quota pane shows numbers for claude, cursor, agy and opencode-go instead of NO DATA or STALE. Use when the pane says "run /dev-lead:quota-setup", or the user asks why a CLI's quota is missing.

  • Installs packages

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

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

    Show the plan: Run it without --apply and show the user every line.

    line 22
  2. Very specific:

    Ask before applying: Only on the user's yes, run it again with --apply and show what it printed (done: lines, backups).

    line 30
  3. Distinctive:

    Not on Windows yet: the script says so and changes nothing.

    line 36

≈ “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

Quota setup: give the quota pane something to read

The pane (dev-lead-panel) reads caches that other things write; on a host with none of them it shows NO DATA. quota-setup.py sets them up. It only ADDS: a refresh mode the host already chose, or an agy status line the person already has, is never replaced.

Procedure

# newest installed release, by number (no `sort -V`: stock macOS sort lacks it)
DEV_LEAD=${DEV_LEAD_ROOT:-$(python3 -c 'import glob,os,re;d=glob.glob(os.path.expanduser("~/.claude/plugins/cache/dev-lead/dev-lead/*"));d=[p for p in d if re.fullmatch(r"\d+(\.\d+)*",os.path.basename(p))];print(max(d,key=lambda p:[int(x) for x in os.path.basename(p).split(".")]) if d else "")')}
[ -f "$DEV_LEAD/scripts/quota-setup.py" ] || { echo "dev-lead root unresolved — set DEV_LEAD_ROOT to your checkout"; exit 1; }
python3 "$DEV_LEAD/scripts/quota-setup.py"
  1. Show the plan. Run it without --apply and show the user every line. Say in plain words what --apply would change, especially:
    • claude / cursor refresh: fetch means dev-lead's quota-fetch.py will read this host's Claude Code / Cursor login and ask that vendor's usage endpoint every few minutes while the pane is open. The token goes only to the vendor's own endpoint and is never written anywhere.
    • agy install sets agy's status line (agy had none).
    • opencode-go install copies the Go usage plugin into opencode's plugins.
  2. Ask before applying. Only on the user's yes, run it again with --apply and show what it printed (done: lines, backups).
  3. Then: the pane fills in on its next poll (about a minute), or at once with /quota. agy and opencode caches need tmux to refresh on their own; without it they update while their CLI is open.

Not on Windows yet: the script says so and changes nothing.

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.