palaia CLAUDE.md

palaia CLAUDE.md is an instructions file for coding agents from byte5ai/palaia. It costs 72 tokens per session, scanned A, original, MIT.

Repository instructions for palaia, pointing agents to AGENTS.md for the full rules and to a master plan for version 3 work. They define which documents are authoritative for development.

In plain words
What is it for?
Finding the required git workflow, separating version 2 and version 3 work, following version 3 conventions, and preparing pull requests.
Why use it?
They keep work aligned with the right project rules and roadmap instead of relying on incomplete instructions in one file.

Instructions file

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 instructions/byte5ai/palaia/claude-md
Clone the repo
git clone --depth 1 https://github.com/byte5ai/palaia

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 palaia CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/byte5ai/palaia/claude-md.svg)](https://agentmods.dev/instructions/byte5ai/palaia/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/byte5ai/palaia/claude-md"><img src="https://agentmods.dev/badge/instructions/byte5ai/palaia/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 This file is loaded in full into every session.
When invoked 72 The same file — it is already loaded in full.
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 $0.00072 $0.00072
Opus 5 $0.00036 $0.00036
Sonnet 5 $0.00014 $0.00014
Haiku 4.5 $0.00007 $0.00007

Measured 4d ago against content hash 0c63dd46d519, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

palaia CLAUDE.md 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 4d 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.

CLAUDE.md · 9 lines

What it actually says

Claude Code instructions

All agent rules for this repository live in AGENTS.md — git workflow, the strict v2/v3 track separation, v3 project conventions, and PR requirements.

@AGENTS.md

For v3 work, v3/MASTERPLAN.md is the source of truth for scope and roadmap.

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. 4d ago First seen · 9 lines · 72 tokens per session scan A 0c63dd46d519

Subscribe to this mod's changes

palaia CLAUDE.md is an instructions file published in the GitHub repository byte5ai/palaia (19 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session, about $0.0004 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 2026-08-30.