Agent skill

Token Meter GitHub Ops

by splunk in splunk/token-meter

A skill your agent uses when Token Meter GitHub issues, pull requests, review requests, checks, comments, merges, or closure need to be managed.

MITAuto-check passedDevelopment

Install Token Meter GitHub Ops

skills CLI
$ npx skills add splunk/token-meter --skill token-meter-github-ops -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install splunk/token-meter token-meter-github-ops --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/token-meter-github-ops .claude/skills/token-meter-github-ops && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
token-meter-github-ops
GitHub stars
110
Token cost
~1.2k tokens
SKILL.md length
648 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when Token Meter GitHub issues, pull requests, review requests, checks, comments, merges, or closure need to be managed.

  • Works in 5 steps: Identify the exact operation and target. → Recheck the current head, checks,… → Confirm the task envelope contains… → …
  • Token Meter GitHub issues
  • SKILL.md covers Purpose, Read path, Write gate and Reporter end-to-end delivery, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Token Meter GitHub Ops is an agent skill from splunk/token-meter. Use when Token Meter GitHub issues, pull requests, review requests, checks, comments, merges, or closure need to be managed.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: Open-source, local-first AI coding agent usage and cost dashboard for Claude Code, Codex, Cursor, OpenCode, Kiro, and Pi. The licence is MIT.

When your agent uses it

  • Token Meter GitHub issues
  • Review requests
  • Closure need to be managed

Example prompts

  • “/token-meter-github-ops”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Identify the exact operation and target.
  2. Recheck the current head, checks, findings, evidence freshness, and merge state.
  3. Confirm the task envelope contains explicit approval for that specific operation.
  4. For a user-visible write, require a current communication-manager result with the
  5. Perform only the approved operation without materially rewriting the draft, then

What it can do on your machine

Read from SKILL.md and the folder at commit 4ff456b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Token Meter GitHub Ops loads about 1.2k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 648 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from splunk/token-meter at commit 4ff456b, republished under its MIT licence (© splunk). 648 words, ~1,197 tokens.

Download SKILL.mdSave it as .claude/skills/token-meter-github-ops/SKILL.md (or your agent's skills folder).
name
token-meter-github-ops
description
Use when Token Meter GitHub issues, pull requests, review requests, checks, comments, merges, or closure need to be managed.

Token Meter GitHub Operations

Purpose

Maintain issue and pull-request state without confusing repository readiness with permission to act. Default to read-only inspection.

Read path

  • Read the complete issue or pull request, comments, reviews, checks, base, current head, and merge state.
  • Compare the pull-request head with the handoff's tested and reviewed head.
  • Confirm required tester and project-reviewer results satisfy .agents/workflow/review-policy.yaml.
  • Carry verified hosted review findings into the shared findings ledger. A hosted review is advisory and cannot satisfy the project gate.

Write gate

Immediately before a comment, edit, label change, review request, push, merge, close, or other external mutation:

  1. Identify the exact operation and target.
  2. Recheck the current head, checks, findings, evidence freshness, and merge state.
  3. Confirm the task envelope contains explicit approval for that specific operation.
  4. For a user-visible write, require a current communication-manager result with the exact draft, evidence mapping, destination, approval coverage, duplicate check, and sensitive-data check. Preview the draft and confirm it still matches current state.
  5. Perform only the approved operation without materially rewriting the draft, then read back its text and resulting state.

Approval for one comment does not cover another. Approval to implement, commit, push, request review, or merge does not imply any other action. If the head changes, return the work to verification and review.

Reporter end-to-end delivery

An envelope on the reporter-end-to-end route carries standing approval for the successful delivery sequence defined in .agents/workflow/routing.yaml. The coordinator commits only the scoped change before the gates so the tester and reviewer can bind their evidence to that exact commit. After confirming the frozen commit has every required tester/reviewer result and no open finding, the operator may push the dedicated branch and create the linked pull request without requesting approval again. After reading back the pull request and receiving the communication manager's linked drafts, the operator may post the detailed testing handoff on the linked issue. Read back the remote head, pull request, and issue comment after writing them.

The communication manager first drafts the pull-request title and body from the gated commit. After the operator creates and reads back the pull request, the communication manager drafts a separate detailed linked-issue handoff using the real pull-request URL. That handoff summarizes verified behavior, distinguishes pushed from merged or released, and includes useful clone, checkout, install, health-check, restoration, measurement, and procedural next steps. The communication manager also drafts the coordinator's Slack reply as one short paragraph with thanks, the pull-request link, a brief request to try it, and the Pratik's agent signature; Slack receives no code, commands, clone/install steps, procedural next steps, test matrix, or long technical summary.

This route does not authorize merge, release, close, label changes, or hosted review requests. Those actions still require separate explicit approval.

Show full SKILL.md (192 more words)Show less

Review requests

Request Codex or Claude hosted review only when separately approved. Record the requested service and head. Verify every returned claim before routing a fix; do not apply suggestions merely because an automated reviewer sounds confident.

Contributor status replies

When the user explicitly authorizes checking out, reviewing, or managing pull requests, that request includes standing approval for one contributor-facing status reply on each inspected PR. Before posting, inspect the current head and existing discussion and preview the exact text. Do not duplicate an equivalent same-head status reply.

Thank the contributor, state the evidence-backed merge status or next step, and identify the message as from Pratik's agent. Mention a follow-up only when the team owns an actual next action; when the work is complete, do not promise one. This standing approval covers only those status replies. A merge, close, push, review request, or unrelated external action still requires explicit authority in the current task.

Operator result

Return the repository and pull request, inspected head, gate evidence, exact approved action, resulting state, links, remaining findings, and recommended next state. Omit credentials, private paths, traces, prompts, responses, reasoning, and tool contents from public text.

© splunk, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/token-meter-github-ops of splunk/token-meter.

Open the folder on GitHubat commit 4ff456b

Compare with similar skills

Token Meter GitHub Ops next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Token Meter GitHub Ops compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Token Meter GitHub Ops this skillsplunk/token-meter110—~1.2kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

More from splunk/token-meter

  • Token Meter Communication

    splunk/token-meter

    A skill your agent uses when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication.

    110 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Token Meter Development

    splunk/token-meter

    A skill your agent uses when a Token Meter issue or approved feature needs diagnosis or implementation in the repository.

    110 GitHub stars~857 tokensUpdated today
    Auto-check passed
  • Token Meter Review

    splunk/token-meter

    A skill your agent uses when a Token Meter change needs independent requirements, correctness, regression, privacy, or cross-surface review.

    110 GitHub stars~603 tokensUpdated today
    Auto-check passed
  • Token Meter Verification

    splunk/token-meter

    A skill your agent uses when Token Meter changes or claims need independent source, test, runtime, native, browser, privacy, or platform verification.

    110 GitHub stars~558 tokensUpdated today
    Auto-check passed
  • Token Meter Intake

    splunk/token-meter

    A skill your agent uses when a Token Meter Slack or GitHub request needs contextual intake, clarification, triage, acknowledgment, or closure.

    110 GitHub stars~1.4k tokensUpdated today
    Auto-check: warnings

Works with

Categories

Questions about Token Meter GitHub Ops

What does Token Meter GitHub Ops do?

A skill your agent uses when Token Meter GitHub issues, pull requests, review requests, checks, comments, merges, or closure need to be managed. Token Meter GitHub Ops is an agent skill from splunk/token-meter. Use when Token Meter GitHub issues, pull requests, review requests, checks, comments, merges, or closure need to be managed.

When should I use Token Meter GitHub Ops?

Token Meter GitHub Ops fits situations like: token Meter GitHub issues; review requests; closure need to be managed.

How do I install Token Meter GitHub Ops in Claude Code?

Run `npx skills add splunk/token-meter --skill token-meter-github-ops -a claude-code`. Or copy the skill folder (.agents/skills/token-meter-github-ops in splunk/token-meter) into .claude/skills/token-meter-github-ops in your project. Claude Code loads it when a task matches its description.

How do I install Token Meter GitHub Ops in Codex?

Run `npx skills add splunk/token-meter --skill token-meter-github-ops -a codex`. Or copy the skill folder (.agents/skills/token-meter-github-ops in splunk/token-meter) into .agents/skills/token-meter-github-ops in your project. Codex loads it when a task matches its description.

Can I use Token Meter GitHub Ops in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add splunk/token-meter --skill token-meter-github-ops -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/token-meter-github-ops, .gemini/skills/token-meter-github-ops, .github/skills/token-meter-github-ops and .opencode/skills/token-meter-github-ops in your project.

What does Token Meter GitHub Ops need to run?

SKILL.md names no scripts, command-line tools or credentials: Token Meter GitHub Ops is instructions for the agent only.

Does Token Meter GitHub Ops access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Token Meter GitHub Ops safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Token Meter GitHub Ops use?

Token Meter GitHub Ops is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Token Meter GitHub Ops use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Token Meter GitHub Ops?

Skills that share tags, products or a category with Token Meter GitHub Ops: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Token Meter GitHub Ops?

splunk (a GitHub organization) maintains it in splunk/token-meter, which has 110 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 7, 2026.

Source: splunk/token-meter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.