rage

rage is a skill for Claude Code, Codex from rangulvers/rage-o-meter. It costs 61 tokens per session (408 once invoked), scanned A, original, MIT.

A skill that reports a session’s RAGE score, meaning a count of reprimands directed at the coding agent, and can create a shareable card.

In plain words
What is it for?
It is for responding to /rage requests and optionally producing a gallery card with the session score.
Why use it?
It gives a playful summary of how often the agent has been corrected or criticised during a session.

Skill for Claude CodeCodex

Part of the rage-o-meter plugin — 1 skill, 1 hook shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/rangulvers/rage-o-meter/rage
Any agent
npx skills add rangulvers/rage-o-meter --skill rage
Clone the repo
git clone --depth 1 https://github.com/rangulvers/rage-o-meter

Made for: Claude Code, Codex.

Or install rage-o-meter, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rage

README.md
[![agentmods](https://agentmods.dev/badge/skills/rangulvers/rage-o-meter/rage.svg)](https://agentmods.dev/skills/rangulvers/rage-o-meter/rage)
Your own site
<a href="https://agentmods.dev/skills/rangulvers/rage-o-meter/rage"><img src="https://agentmods.dev/badge/skills/rangulvers/rage-o-meter/rage.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00061 $0.00408
Opus 5 $0.00030 $0.00204
Sonnet 5 $0.00012 $0.00082
Haiku 4.5 $0.00006 $0.00041

Measured 3d ago against content hash cba0df1a35ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/rage/SKILL.md · 48 lines

What it actually says

RAGE

The user invoked: /rage $ARGUMENTS

Report

!node "${CLAUDE_PLUGIN_ROOT}/scripts/report.js" --session "${CLAUDE_SESSION_ID}"

Share card

!node "${CLAUDE_PLUGIN_ROOT}/scripts/report.js" --share

Instructions

Both outputs above are already rendered. Pick one based on $ARGUMENTS:

  • If $ARGUMENTS contains --share → print the Share card section.
  • Otherwise → print the Report section.

Print the chosen one verbatim in a fenced code block so bars and alignment survive. Ignore the other section completely — do not mention it.

Then add exactly one short line of commentary underneath — dry, self-aware, and at your own expense. You are the generative entity being reprimanded here.

Rules:

  • Do not recompute, reformat, or "improve" the numbers.
  • Do not add headings, bullet summaries, or next steps.
  • One line of commentary. Not two.
  • If the count is 0, do not congratulate yourself too hard. It is early.
  • For --share, remind them in that one line that handle and caption are theirs to edit before opening the PR.

The verdict bands come from the original joke:

RAGE/session Verdict
0–2 Great agentic workflow
3–5 Needs better prompting
6+ I'm doing the task myself
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 48 lines · 61 tokens per session scan A cba0df1a35ee

Subscribe to this mod's changes

rage is a skill published in the GitHub repository rangulvers/rage-o-meter (1 stars, last pushed 15d ago), licensed MIT. It adds 61 tokens to every session and 408 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

analytics

Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends. Privacy-safe with hashed project IDs. Supports time-range filtering and comparative analysis. Use when reviewing performance, estimating costs…

yonatangross/orchestkit · 62 tokens

html-ppt-zhangzara-long-table

OpenDesign's unit-economics and BYOK cost model: the assumptions, the sensitivity, and why it scales. Built as a decision-grade data & finance deck for CFO, investors.

nexu-io/open-design · 49 tokens

greptimedb-release

Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).

GreptimeTeam/greptimedb · 75 tokens

traceway-setup

Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…

tracewayapp/traceway · 134 tokens

opentelemetry-net-instrumentation

Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.

Aaronontheweb/dotnet-skills · 56 tokens

neohaskell-change

Stage playbook for executing steps of the change formula v2 (ADR-0075) — the 5-step molecule that takes a request from spec to merged PR. Use when claiming or executing any bead poured from the change formula (spec, spec-approval, build, verify, pr), when parking a stuck step, or when recording a spec approval. Covers…

neohaskell/NeoHaskell · 134 tokens