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.
npx agentmods add instructions/mahmoudimus/simba/claude-mdgit clone --depth 1 https://github.com/mahmoudimus/simbaWrote 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.
[](https://agentmods.dev/instructions/mahmoudimus/simba/claude-md)<a href="https://agentmods.dev/instructions/mahmoudimus/simba/claude-md"><img src="https://agentmods.dev/badge/instructions/mahmoudimus/simba/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01888 | $0.01888 |
| Opus 5 | $0.00944 | $0.00944 |
| Sonnet 5 | $0.00378 | $0.00378 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
simba 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Read .claude/rules/CORE_INSTRUCTIONS.md for rules that apply to ALL contexts (main session + subagents).
When dispatching subagents, inject the contents of that file into the prompt.
Repository Overview
This is a monorepo ("simba") containing 4 independent Claude Code plugin/tooling projects. Each project has its own git history, package.json, and distribution channel. They all extend Claude Code's capabilities through the hooks system.
| Project | Purpose | Language | Deps |
|---|---|---|---|
claude-tailor |
Error memory + persistent patterns via JSONL reflections | JS (ESM) | Zero |
claude-memory |
Semantic memory daemon with vector DB (LanceDB + llama-cpp-python) | JS (CJS) | express, @lancedb/lancedb, uuid |
claude-turbo-search |
Fast file search + semantic indexing via ripgrep/fzf/QMD | Bash + JS | System tools (ripgrep, fzf, jq, bun, qmd) |
claude-md-memory-guardian |
CLAUDE.md rule reinforcement via <!-- CORE --> tag extraction |
Bash | None |
Architecture
All projects use Claude Code hooks to inject behavior at specific lifecycle points:
SessionStart → Auto-start daemons, inject patterns/rules, show memory count
UserPromptSubmit → Recall memories, suggest files, reinforce core rules
PreToolUse → Inject context from vector DB based on Claude's thinking
PreCompact → Export transcripts for learning extraction
StopHook → Monitor for [✓ rules] signal (memory-guardian)
Hook output follows the Claude Code hook protocol: read JSON from stdin, write hookSpecificOutput JSON to stdout with additionalContext for context injection.
The simba Python package supports three coding-agent runtimes: Claude Code (native hooks), Codex (.codex/hooks.json, same handlers including PreCompact plus PermissionRequest), and pi (@earendil-works/pi-coding-agent) via a thin bundled src/simba/pi/extension/simba.ts bridge that forwards pi lifecycle events to the daemon's POST /hook/{event} endpoint (CLI fallback). Install per runtime with simba install / simba codex-install / simba pi-install.
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.
- 4d ago First seen · 150 lines · 1,888 tokens per session scan A f2758fbd49f8
simba CLAUDE.md is an instructions file published in the GitHub repository mahmoudimus/simba (6 stars, last pushed 1mo ago), licensed MIT. It adds 1,888 tokens to every session, about $0.0094 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.
Other instructions, from other repositories
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.
pi-extensions CLAUDE.md
Claude Code instructions for MattDevy/pi-extensions, covering claude.md, commands, architecture, data flow and key modules.
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
brainlayer AGENTS.md
Instructions for EtanHey/brainlayer, covering brainlayer — a letter from etan, brainlayer agent notes (operational), review guidelines, key paths and database.