caveman-compress

caveman-compress is a skill for Claude Code from hamzaPixl/pixl-ai. It costs 118 tokens per session (993 once invoked), scanned A, original, MIT.

A tool for shortening natural-language memory files such as CLAUDE.md, rules, references, and todos into compact wording. It preserves code, links, file paths, commands, headings, and Markdown structure, while saving a backup of the original.

In plain words
What is it for?
Use it to compress supported Markdown memory files, validate the result, and restore the original if compression fails.
Why use it?
It reduces how many input tokens these files use in each session without changing important technical text. Validation and rollback help catch formatting or content loss.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the pixl-crew plugin — 93 skills, 14 agents, 6 hooks shipped together

Good fit Use it to compress supported Markdown memory files, validate the result, and restore the original if compression fails.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamzapixl/pixl-ai/caveman-compress
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.

Any agent
npx skills add hamzaPixl/pixl-ai --skill caveman-compress
Clone the repo
git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

Made for: Claude Code.

Or install pixl-crew, the plugin that ships this one along with the rest of its 93 skills, 14 agents, 6 hooks.

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 caveman-compress

README.md
[![agentmods](https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/caveman-compress/github.svg)](https://agentmods.dev/skills/hamzapixl/pixl-ai/caveman-compress)
Your own site
<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/caveman-compress"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/caveman-compress/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for caveman-compress

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/caveman-compress"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/caveman-compress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 993 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00118 $0.00993
Opus 5 $0.00059 $0.00496
Sonnet 5 $0.00024 $0.00199
Haiku 4.5 $0.00012 $0.00099

Measured 11d ago against content hash 7c037584d154, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

caveman-compress 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 11d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/__init__.py, scripts/__main__.py, scripts/benchmark.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/crew/skills/caveman-compress/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Caveman Compress

Purpose

Compress natural-language files into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as <filename>.original.md.

Trigger

/caveman-compress <filepath> or when user asks to compress a memory file.

Safety

  • Skips non-natural-language files (code, JSON, YAML) automatically via detect.py
  • Aborts if <filename>.original.md backup already exists (prevents overwrite)
  • 500KB file-size cap
  • Validates headings, code blocks, URLs, file paths preserved exactly — retries up to 2 times with targeted fixes, restores original on final failure

Process

  1. Scripts live in skills/caveman-compress/scripts/ (adjacent to this SKILL.md).

  2. Run:

    cd path/to/pixl-crew/skills/caveman-compress && python3 -m scripts <absolute_filepath>
    

    Or from the project root, pointing at the vendored copy under packages/crew/skills/caveman-compress/.

  3. The CLI will:

    • detect file type (no tokens)
    • call Claude via ANTHROPIC_API_KEY env var OR the claude --print CLI (falls back)
    • validate output (no tokens) — headings, code blocks, URLs, paths must match
    • if errors: cherry-pick fix with Claude (targeted fixes only, no recompression)
    • retry up to 2 times
    • if still failing after 2 retries: restore original file, delete backup, report error
  4. Return result to user.

Environment

  • ANTHROPIC_API_KEY (optional): direct API call — requires pip install anthropic
  • Fallback: claude --print CLI (uses Claude Code desktop auth)
  • CAVEMAN_MODEL (optional): override model, default claude-sonnet-4-5

Compression Rules

Remove

  • Articles: a, an, the (except in lite mode)
  • Filler: just, really, basically, actually, simply, essentially, generally
  • Pleasantries: "sure", "certainly", "of course", "happy to", "I'd recommend"
  • Hedging: "it might be worth", "you could consider", "it would be good to"
  • Redundant phrasing: "in order to" → "to", "make sure to" → "ensure"
  • Connective fluff: "however", "furthermore", "additionally"

Read the full file on GitHub · 91 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 91 lines · 118 tokens per session scan A 7c037584d154

Subscribe to this mod's changes

caveman-compress is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 118 tokens to every session and 993 once invoked, about $0.0006 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens