Qwen Mtp Gguf
R6410418/Jackrong-llm-finetuning-guide
Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.
A skill your agent uses when a Token Meter issue or approved feature needs diagnosis or implementation in the repository.
Install Token Meter Development
$ npx skills add splunk/token-meter --skill token-meter-development -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install splunk/token-meter token-meter-development --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-development .claude/skills/token-meter-development && rm -rf skills-srcUse ~/.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/
Install the "token-meter-development" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-development into .claude/skills/token-meter-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-development", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-developmentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add splunk/token-meter --skill token-meter-development -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install splunk/token-meter token-meter-development --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/token-meter-development .agents/skills/token-meter-development && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "token-meter-development" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-development into .agents/skills/token-meter-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-development", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add splunk/token-meter --skill token-meter-development -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install splunk/token-meter token-meter-development --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/token-meter-development .cursor/skills/token-meter-development && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "token-meter-development" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-development into .cursor/skills/token-meter-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-development", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/splunk/token-meter.git --path .agents/skills/token-meter-development--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add splunk/token-meter --skill token-meter-development -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install splunk/token-meter token-meter-development --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/token-meter-development .gemini/skills/token-meter-development && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "token-meter-development" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-development into .gemini/skills/token-meter-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-development", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install splunk/token-meter token-meter-developmentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add splunk/token-meter --skill token-meter-development -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/token-meter-development .github/skills/token-meter-development && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "token-meter-development" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-development into .github/skills/token-meter-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-development", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add splunk/token-meter --skill token-meter-development -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install splunk/token-meter token-meter-development --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/token-meter-development .opencode/skills/token-meter-development && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "token-meter-development" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-development into .opencode/skills/token-meter-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-development", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
token-meter-development- GitHub stars
- 110
- Token cost
- ~857 tokens
- SKILL.md length
- 433 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a Token Meter issue or approved feature needs diagnosis or implementation in the repository.
- Works in 6 steps: Read specs/AGENTS.md, the relevant… → Confirm this role owns tracked-file… → For a product or technical design… → …
- A Token Meter issue
- SKILL.md covers Purpose, Select the mode and Developer result
- Calls git
What it does
Token Meter Development is an agent skill from splunk/token-meter. Use when a Token Meter issue or approved feature needs diagnosis or implementation in the repository.
Its SKILL.md is about 860 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 AI & LLM Engineering. 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
- A Token Meter issue
- Approved feature needs diagnosis
- Implementation in the repository
Example prompts
- “/token-meter-development”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Read specs/AGENTS.md, the relevant implementation and tests, the task envelope,
- Confirm this role owns tracked-file writes. Another writer must hand off before
- For a product or technical design decision, complete the approved design gate.
- REQUIRED SUB-SKILL: Use superpowers:test-driven-development. Write a focused
- Run relevant self-checks without representing them as independent verification.
- Reinspect callers, public projections, platform behavior, packaging, documentation,
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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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 Development loads about 857 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 433 words of instructions outside code blocks.
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). 433 words, ~857 tokens.
Download SKILL.mdSave it as
.claude/skills/token-meter-development/SKILL.md (or your agent's skills folder).- name
- token-meter-development
- description
- Use when a Token Meter issue or approved feature needs diagnosis or implementation in the repository.
Token Meter Development
Purpose
Diagnose unexplained behavior or implement an approved Token Meter change as the single writer for the assigned worktree. Return evidence; do not certify readiness.
Select the mode
Diagnosis-only
Use when the envelope does not authorize implementation. Reproduce the symptom when practical, trace the actual execution and data path, distinguish observed facts from inference, and identify the smallest credible cause.
REQUIRED SUB-SKILL: Use superpowers:systematic-debugging for failures or
unexpected behavior.
Return cause, evidence, uncertainty, affected surfaces, options, and the exact next approval needed. Diagnosis-only mode prohibits tracked-file edits.
Standard implementation
Use for standard or high-risk work only with explicit implementation authority and approved acceptance criteria.
- Read
specs/AGENTS.md, the relevant implementation and tests, the task envelope, and current dirty-tree inventory. - Confirm this role owns tracked-file writes. Another writer must hand off before editing the same worktree.
- For a product or technical design decision, complete the approved design gate.
- REQUIRED SUB-SKILL: Use
superpowers:test-driven-development. Write a focused regression test, observe the expected failure, implement the smallest complete change, and observe the focused pass. - Run relevant self-checks without representing them as independent verification.
- Reinspect callers, public projections, platform behavior, packaging, documentation, and installed-runtime effects implicated by the diff.
Show full SKILL.md (231 more words)Show less
Low-risk fast path
Use the low-risk fast path only when the coordinator names it explicitly and every
eligibility condition in .agents/workflow/review-policy.yaml remains true. The
envelope must name one allowed change kind and evidence for every eligibility
condition. This is a separate mode: follow the common input and ownership checks in
steps 1-2 above, then run only the focused checks named in the envelope and
git diff --check. Do not inherit the standard design, TDD, consumer-scan,
independent tester/reviewer, full-suite, browser, native, installation, or live-runtime
steps unless the focused acceptance criteria require them. Record what was not run.
Escalate to the standard route before continuing if eligibility is uncertain, scope expands, an unexpected failure appears, a cross-surface consumer is implicated, or acceptance depends on runtime behavior. Do not stretch the fast path to finish work that no longer qualifies.
Do not modify or discard unrelated changes. Do not patch only the staged runtime. Change source first; installation and live checks belong to the verification route.
Developer result
Return:
- Status and current head commit or explicit uncommitted state.
- Files changed, owner, and reason for each.
- Reproduction and red/green test evidence.
- Commands run with outcomes.
- Claimed behavior and affected risk categories.
- Unverified behavior, blockers, and recommended next state.
Implementation approval does not authorize commit, push, Slack or GitHub writes, review requests, merge, deployment, or self-certification. The coordinator routes the result to independent testing and review.
© 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-development of splunk/token-meter.
Open the folder on GitHubat commit 4ff456b
Compare with similar skills
Token Meter Development 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Token Meter Development this skillsplunk/token-meter | 110 | — | ~857 | Automated safety check: Pass | MIT | |
| Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide | 1.7k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Agent Eval Engineeringlangchain-ai/langchain-skills | 1.3k | — | ~4k | Automated safety check: Pass | MIT | |
| Skill Conductorsmixs/skill-conductor | 179 | — | ~6.6k | Automated safety check: Pass | MIT | |
| Veomni New ModelByteDance-Seed/VeOmni | 2.2k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Evaluate RAGai-evals-course/evals-skills | 1.5k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Agent Eval Engineering
langchain-ai/langchain-skills
Builds agent evaluations in stages: inspect the repository and traces, agree a Task Spec with you, then build, audit and run a Harbor task with an independent verifier.
Skill Conductor
smixs/skill-conductor
Create, edit, evaluate, and package agent skills. An agent skill from smixs/skill-conductor.
Veomni New Model
ByteDance-Seed/VeOmni
A skill your agent uses when adding support for a new model to VeOmni.
Evaluate RAG
ai-evals-course/evals-skills
Guides evaluation of a RAG system by diagnosing failures in traces, building a retrieval test set and scoring retrieval and generation separately.
Synthetic Eval Data Generator
ai-evals-course/evals-skills
Builds diverse synthetic test inputs for LLM pipeline evaluation by defining failure-focused dimensions, drafting tuples with you and turning them into realistic queries.
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.
Token Meter GitHub Ops
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.
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.
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.
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.
Related
Categories
Questions about Token Meter Development
What does Token Meter Development do?
A skill your agent uses when a Token Meter issue or approved feature needs diagnosis or implementation in the repository. Token Meter Development is an agent skill from splunk/token-meter. Use when a Token Meter issue or approved feature needs diagnosis or implementation in the repository.
When should I use Token Meter Development?
Token Meter Development fits situations like: A Token Meter issue; approved feature needs diagnosis; implementation in the repository.
How do I install Token Meter Development in Claude Code?
Run `npx skills add splunk/token-meter --skill token-meter-development -a claude-code`. Or copy the skill folder (.agents/skills/token-meter-development in splunk/token-meter) into .claude/skills/token-meter-development in your project. Claude Code loads it when a task matches its description.
How do I install Token Meter Development in Codex?
Run `npx skills add splunk/token-meter --skill token-meter-development -a codex`. Or copy the skill folder (.agents/skills/token-meter-development in splunk/token-meter) into .agents/skills/token-meter-development in your project. Codex loads it when a task matches its description.
Can I use Token Meter Development 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-development -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-development, .gemini/skills/token-meter-development, .github/skills/token-meter-development and .opencode/skills/token-meter-development in your project.
What does Token Meter Development need to run?
Going by SKILL.md and its folder, Token Meter Development needs the command-line tools its instructions call (git).
Does Token Meter Development access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Token Meter Development 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 Development use?
Token Meter Development 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 Development use?
About 857 tokens (SKILL.md is roughly 3.4k 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 Development?
Skills that share tags, products or a category with Token Meter Development: Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars), Agent Eval Engineering (langchain-ai/langchain-skills, 1.3k stars), Skill Conductor (smixs/skill-conductor, 179 stars) and Veomni New Model (ByteDance-Seed/VeOmni, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Token Meter Development?
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.