agentleFS
Sign inStart free
zoranmarticzoranmartic/coord-wright/skills/coord-tokens/SKILL.md

coord-tokens

Skill0 starsChanged 47 days agoApache-2.0View on GitHub

Show current token spend per agent across coord tasks. Read-only — no commits. Use when the user says "/coord-tokens", "show tokens", "how many tokens left", or before deciding which agent to assign.

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

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

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a helper exits non-zero, print its stderr and continue with whatever output is available — partial data is still useful.

    line 23
  2. Distinctive:

    Do not summarise, do not interpret — show the raw output so the user sees what the helpers actually report.

    line 28
  3. Very specific:

    Read-only; never call coord update, git add, git commit, or git push.

    line 34

≈ “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

Display token usage for Claude and Codex coord runs. Read-only; never mutates anything.

Project-root preflight:

  • Resolve the canonical project checkout before running token helpers: COORD_MAIN=$("${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord-project-root") && cd "$COORD_MAIN"
  • This is required when the skill is invoked from a sibling task worktree; token reporting should reflect the main queue and worker state.

Syntax

/coord-tokens

Workflow

  1. Run the helpers.
    • Claude side: bash "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord-tokens.sh"
    • Codex side: bash "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord-tokens.sh" --agent=codex
    • If a helper exits non-zero, print its stderr and continue with whatever output is available — partial data is still useful.
  2. Present output.
    • Print a short header: Token spend (Claude / Codex).
    • Stream each helper's output with a one-line label per section.
    • Do not summarise, do not interpret — show the raw output so the user sees what the helpers actually report.
  3. No commits, no pushes, no file edits. This skill is observational.

Rules

  • Read-only; never call coord update, git add, git commit, or git push.
  • Surface helper errors verbatim; do not retry or work around them.

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.

Check your setup, free