squadai: Instructions file for Claude Code

CLAUDE.md

squadai CLAUDE.md is an instructions file for Claude Code from PedroMosquera/squadai. It costs 608 tokens per session, scanned A, a copy of squadai AGENTS.md, MIT.

Instructions for Squadai, including a persistent project memory system that stores decisions, lessons, and incidents between sessions.

In plain words
What is it for?
Use them before major design or API decisions, after important fixes, and when maintaining or searching the project’s memory index.
Why use it?
They help an agent find earlier project knowledge and record new discoveries instead of repeating research or losing context.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions subagents; mentions Claude Code.

This is PedroMosquera/squadai's own configuration. It tells Claude Code how to work on squadai 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 squadai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PedroMosquera/squadai. 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/PedroMosquera/squadai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

Made for: Claude Code.

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 squadai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pedromosquera/squadai/claude-md.svg)](https://agentmods.dev/instructions/pedromosquera/squadai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pedromosquera/squadai/claude-md"><img src="https://agentmods.dev/badge/instructions/pedromosquera/squadai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 608 This file is loaded in full into every session.
When invoked 608 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 92% copy Near-identical to another mod 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 $0.00608 $0.00608
Opus 5 $0.00304 $0.00304
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 7d ago against content hash 811ec0aab1b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

squadai 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 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.

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.

Origin

This is a copy

92% identical to squadai AGENTS.md — 86 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Memory Protocol

docs/memory/ is this project's persistent, indexed memory store for decisions, learnings, and incidents. It survives across sessions — use it.

Search first. Before starting significant work, run /memory-search <query> (or squadai memory search <query> in the terminal) and pass any findings into your plan. Never skip memory-search before architecture or API decisions.

Capture as you go. After a decision, fix, or discovery, run /memory-add <note> (or squadai memory add "<note>"). Notes land in docs/memory/_inbox/ as drafts until promoted.

Housekeeping. Run /memory-promote periodically to graduate inbox drafts into permanent topic folders, and /memory-reindex after manual edits under docs/memory/ to keep the search index current.

For deeper multi-query research, ask the @librarian agent with a plain-language question; it returns ranked excerpts from the memory index.

                          *
    o      o      o     .---.
   /|\____/|\____/|\____|o o|    S Q U A D A I
   / \    / \    / \    '---'    x Claude Code

Session Efficiency Protocol

Work token-efficiently. These rules apply to every task in this repository.

Search before read. Locate code with grep/glob first; read only the files and line ranges you need. Never read a whole file when a targeted range works.

Never re-read a file you just edited. The edit either succeeded or errored; trust that result instead of re-opening the file to check.

Summarize long output. When a tool returns more than ~30 lines, extract the relevant findings instead of pasting the whole output into the transcript.

Delegate exploration. Send open-ended codebase exploration to sub-agents and request a compact report (files, symbols, one-line conclusions) — keep raw file dumps out of the main context.

Read the full file on GitHub · 61 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 · 61 lines · 608 tokens per session scan A 811ec0aab1b4

Subscribe to this mod's changes

squadai CLAUDE.md is an instructions file published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 608 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to squadai AGENTS.md, differing in 86 lines, and is treated as a copy.