ice_age: Instructions file for Claude Code

CLAUDE.md

ice_age CLAUDE.md is an instructions file for Claude Code, Codex from pomagrenate/ice_age. It costs 3,141 tokens per session, scanned B, original, Apache-2.0.

Project instructions for iceage, a tool that changes AI coding-agent responses into shorter prose, and for maintaining its README and project files. They define what each file owns and which files are the source of truth.

In plain words
What is it for?
Use them when editing the iceage README, installation information, feature tables, project structure, benchmarks, or agent list.
Why use it?
They prevent documentation and project-structure changes from becoming inaccurate, hard to understand, or inconsistent with the actual product.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: SessionStart hook event, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is pomagrenate/ice_age's own configuration. It tells Claude Code and Codex how to work on ice_age itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ice_age configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pomagrenate/ice_age. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pomagrenate/ice_age/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pomagrenate/ice_age

Made for: Claude Code, Codex.

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 ice_age CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pomagrenate/ice_age/claude-md.svg)](https://agentmods.dev/instructions/pomagrenate/ice_age/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pomagrenate/ice_age/claude-md"><img src="https://agentmods.dev/badge/instructions/pomagrenate/ice_age/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,141 This file is loaded in full into every session.
When invoked 3,141 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03141 $0.03141
Opus 5 $0.01571 $0.01571
Sonnet 5 $0.00628 $0.00628
Haiku 4.5 $0.00314 $0.00314

Measured 7d ago against content hash 2aad8e7592fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

ice_age CLAUDE.md scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Standalone install** — `hooks/install.sh` (macOS/Linux) or `hooks/install.ps1` (Windows) copies hook files into `~/.claude/hooks/` and patches `~/.claude/settings.json` to register SessionStart and UserPromptSubmit hoo
CLAUDE.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — iceage

README is a product artifact

README = product front door. Non-technical people read it to decide if iceage worth install. Treat like UI copy.

Rules for any README change:

  • Readable by non-AI-agent users. If you write "SessionStart hook injects system context," invisible to most — translate it.
  • Keep Before/After examples first. That the pitch.
  • Install table always complete + accurate. One broken install command costs real user.
  • What You Get table must sync with actual code. Feature ships or removed → update table.
  • Preserve voice. Iceage speak in README on purpose. "Brain still big." "Cost go down forever." "One rock. That it." — intentional brand. Don't normalize.
  • Benchmark numbers from real runs in benchmarks/ and evals/. Never invent or round. Re-run if doubt.
  • Adding new agent to install table → add detail block in <details> section below.
  • Readability check before any README commit: would non-programmer understand + install within 60 seconds?

Project overview

Iceage makes AI coding agents respond in compressed iceage-style prose — cuts ~65-75% output tokens, full technical accuracy. Ships as Claude Code plugin, Codex plugin, Gemini CLI extension, agent rule files for Cursor, Windsurf, Cline, Copilot, 40+ others via npx skills.


File structure and what owns what

Single source of truth files — edit only these

File What it controls
skills/iceage/SKILL.md Iceage behavior: intensity levels, rules, wenyan mode, auto-clarity, persistence. Only file to edit for behavior changes.
rules/iceage-activate.md Always-on auto-activation rule body. CI injects into Cursor, Windsurf, Cline, Copilot rule files. Edit here, not agent-specific copies.
skills/iceage-commit/SKILL.md Iceage commit message behavior. Fully independent skill.
skills/iceage-review/SKILL.md Iceage code review behavior. Fully independent skill.
skills/iceage-help/SKILL.md Quick-reference card. One-shot display, not a persistent mode.
skills/iceage-batch/SKILL.md Batch compress behavior. Fully independent skill.
skills/compress/SKILL.md Compress sub-skill behavior.

Read the full file on GitHub · 217 lines

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. 7d ago First seen · 217 lines · 3,141 tokens per session scan B 2aad8e7592fa

Subscribe to this mod's changes

ice_age CLAUDE.md is an instructions file published in the GitHub repository pomagrenate/ice_age (2 stars, last pushed 19d ago), licensed Apache-2.0. It adds 3,141 tokens to every session, about $0.0157 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.