Agent skill

Caveman Stats

by goern in goern/forgejo-mcp

Show real token usage and estimated savings for the current session, read from the session log.

GPL-3.0Auto-check passed

Install Caveman Stats

skills CLI
$ npx skills add goern/forgejo-mcp --skill caveman-stats -a claude-code

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

GitHub CLI
$ gh skill install goern/forgejo-mcp caveman-stats --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/goern/forgejo-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/caveman-stats .claude/skills/caveman-stats && 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
caveman-stats
GitHub stars
141
Token cost
~252 tokens
SKILL.md length
117 words
Files
2
Skills in repo
15
Repo updated
First seen
Licence
GPL-3.0

At a glance

Show real token usage and estimated savings for the current session, read from the session log.

  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Caveman Stats is an agent skill from goern/forgejo-mcp. Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.

Its SKILL.md is about 250 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

The repository describes itself as: MIRROR ONLY!! This Model Context Protocol (MCP) server provides tools and resources for interacting with the Forgejo (specifically Codeberg.org) REST API. The licence is GPL-3.0.

Example prompts

  • “/caveman-stats”

What it can do on your machine

Read from SKILL.md and the folder at commit 1f51f83. 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

Caveman Stats loads about 252 tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 117 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~252

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 goern/forgejo-mcp at commit 1f51f83, republished under its GPL-3.0 licence (© goern). 117 words, ~252 tokens.

Download SKILL.mdSave it as .claude/skills/caveman-stats/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
caveman-stats
description
Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.

This skill is delivered by hooks/caveman-stats.js (read by hooks/caveman-mode-tracker.js on /caveman-stats). The model does not need to do anything when this skill fires — the hook returns decision: "block" with the formatted stats as the reason. The user sees the numbers immediately.

Output also includes Est. rule overhead and Est. net lines wherever a savings estimate exists with a known turn count. Rule overhead is the estimated per-turn INPUT-token cost of the injected caveman rules (default 1,250 tokens/turn, override with CAVEMAN_RULE_OVERHEAD_TOKENS) times the turn count. Net is savings minus that overhead — when negative, the output says so plainly and suggests turning caveman off for that workload, rather than hiding the net-negative regime behind a gross-savings number (see docs/HONEST-NUMBERS.md).

© goern, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/caveman-stats of goern/forgejo-mcp.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 1f51f83

Compare with similar skills

Caveman Stats 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.

Caveman Stats compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Caveman Stats this skillgoern/forgejo-mcp141—~252Automated safety check: PassGPL-3.0
Caveman StatsJuliusBrussee/caveman110k—~491Automated safety check: PassApache-2.0
Caveman ModeJuliusBrussee/caveman110k—~1.2kAutomated safety check: PassApache-2.0
Caveman Evidence ReviewJuliusBrussee/caveman110k1 repos~927Automated safety check: PassApache-2.0
Ctx Statsmksglu/context-mode26k—~290Automated safety check: PassCustom licence
Caveman Experiment ManagerJuliusBrussee/caveman110k1 repos~975Automated safety check: PassApache-2.0

Similar skills

  • Caveman Stats

    JuliusBrussee/caveman

    Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report.

    110k GitHub stars~491 tokensUpdated today
    Auto-check passed
  • Caveman Mode

    JuliusBrussee/caveman

    Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact.

    110k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Caveman Evidence Review

    JuliusBrussee/caveman

    Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.

    110k GitHub starsUsed in 1 repo~927 tokens
    AI & LLM EngineeringAuto-check passed
  • Ctx Stats

    mksglu/context-mode

    Show how much context window context-mode saved this session.

    26k GitHub stars~290 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Caveman Experiment Manager

    JuliusBrussee/caveman

    Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.

    110k GitHub starsUsed in 1 repo~975 tokens
    AI & LLM EngineeringAuto-check passed
  • Caveman Optimization Evaluator

    JuliusBrussee/caveman

    Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

    110k GitHub starsUsed in 1 repo~1.2k tokens
    AI & LLM EngineeringAuto-check passed

More from goern/forgejo-mcp

All 15 skills in this repo
  • Release Openspec

    goern/forgejo-mcp

    A skill your agent uses when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut…

    141 GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed
  • Unified Notifications

    goern/forgejo-mcp

    Fetch and display notifications from both GitHub and Codeberg in a unified markdown view with clickable links.

    141 GitHub stars~802 tokensUpdated today
    Auto-check passed
  • Caveman Compress

    goern/forgejo-mcp

    Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.

    141 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check: notes
  • Draft Openspec Docs

    goern/forgejo-mcp

    Collaborative page-drafting mode for the OpenSpec docs. An agent skill from goern/forgejo-mcp.

    141 GitHub starsUsed in 1 repo~815 tokens
    Auto-check passed
  • Verify Openspec Docs

    goern/forgejo-mcp

    Fact-checks OpenSpec user documentation with a fresh-context subagent that re-runs commands and checks claims against source.

    141 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Wt Switch Create

    goern/forgejo-mcp

    Create a new worktrunk worktree (optionally in another repo) and switch this session's working directory into it.

    141 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Questions about Caveman Stats

What does Caveman Stats do?

Show real token usage and estimated savings for the current session, read from the session log. Caveman Stats is an agent skill from goern/forgejo-mcp. Show real token usage and estimated savings for the current session, read from the session log.

How do I install Caveman Stats in Claude Code?

Run `npx skills add goern/forgejo-mcp --skill caveman-stats -a claude-code`. Or copy the skill folder (.agents/skills/caveman-stats in goern/forgejo-mcp) into .claude/skills/caveman-stats in your project. Claude Code loads it when a task matches its description.

How do I install Caveman Stats in Codex?

Run `npx skills add goern/forgejo-mcp --skill caveman-stats -a codex`. Or copy the skill folder (.agents/skills/caveman-stats in goern/forgejo-mcp) into .agents/skills/caveman-stats in your project. Codex loads it when a task matches its description.

Can I use Caveman Stats 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 goern/forgejo-mcp --skill caveman-stats -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/caveman-stats, .gemini/skills/caveman-stats, .github/skills/caveman-stats and .opencode/skills/caveman-stats in your project.

What does Caveman Stats need to run?

SKILL.md names no scripts, command-line tools or credentials: Caveman Stats is instructions for the agent only.

Does Caveman Stats 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 Caveman Stats 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 Caveman Stats use?

Caveman Stats is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Caveman Stats use?

About 252 tokens (SKILL.md is roughly 1k 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 Caveman Stats?

Skills that share tags, products or a category with Caveman Stats: Caveman Stats (JuliusBrussee/caveman, 110k stars), Caveman Mode (JuliusBrussee/caveman, 110k stars), Caveman Evidence Review (JuliusBrussee/caveman, 110k stars) and Ctx Stats (mksglu/context-mode, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Caveman Stats?

goern (a GitHub user) maintains it in goern/forgejo-mcp, which has 141 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 8, 2026.

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