What is shinobi CLAUDE.md?

Repository instructions for Shinobi, an MCP server that gives coding agents shared project memory, task tracking, decisions, dead ends, and context. An MCP server is a tool service an agent can call during a coding session.

Use them when developing Shinobi, especially before substantial changes, when checking known failed approaches, or when recording decisions and project progress.

They ensure work on Shinobi uses its own project context and records important decisions and failed approaches for future sessions.

How numbererikson/shinobi configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to numbererikson/shinobi. 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/numbererikson/shinobi/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/numbererikson/shinobi

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/numbererikson/shinobi/claude-md.svg)](https://agentmods.dev/instructions/numbererikson/shinobi/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/numbererikson/shinobi/claude-md"><img src="https://agentmods.dev/badge/instructions/numbererikson/shinobi/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,118 This file is loaded in full into every session.

When invoked 1,118 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.01118	$0.01118
Opus 5	$0.00559	$0.00559
Sonnet 5	$0.00224	$0.00224
Haiku 4.5	$0.00112	$0.00112

Measured 7d ago against content hash 6e3c5919d0fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

shinobi 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.

CLAUDE.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for AI coding agents (Claude Code, Cursor, Cline, Zed, …) working in this repository.

What this is

Shinobi is an MCP server that gives AI coding agents a persistent, shared brain: a task spine, decisions log, actively-searched dead ends, approvals, and project context — reachable over stdio or remote streamable HTTP so one brain serves every device (laptop, cloud session, mobile). Node + TypeScript, SQLite (better-sqlite3), Hono dashboard, plugin system.

Dogfooding — use Shinobi to build Shinobi

This project is developed through Shinobi. If the Shinobi MCP tools (mcp__shinobi__*) are connected in your session:

Start by calling agent_bootstrap for the relevant project to pull context, the latest plan, the next task, open decisions, and relevant dead ends. Engineering work lives in the "Shinobi engine" project; the next feature wave in "Shinobi autonomous agents"; launch work in "Shinobi Launch v2".
Before implementing a non-trivial approach, call check_dead_ends — we log failures so they aren't repeated. This is the product's core idea; honor it while building the product.
Record durable decisions with log_decision and failures with log_dead_end as you go.
End with session_closeout (summary, changed files, completed tasks). It refreshes the project summary even without a server-side LLM key.

Dev commands

npm run dev            # run the CLI from source (tsx)
npm run dashboard      # dashboard + (if SHINOBI_MCP_HTTP=on) the /mcp endpoint
npm run build          # tsc + vite build of the dashboard SPA
npm test               # build + vitest + the smoke suite (run before pushing)
npm run test:vitest    # unit tests only
npm run smoke:tools    # exercise the tool registry directly

Layout

src/cli.ts — command dispatch (init, serve, dashboard, mcp, migrate, sync, cost, digest)
src/server/ — MCP server: tool definitions (server/tools/) + stdio and HTTP (server/http.ts) transports
src/models/ — data layer, one module per entity; direct better-sqlite3, parameterized queries only, row/entity hydration split
src/services/ — embeddings, plugins, push, relay, extraction/summarizer
src/dashboard/ — Hono app + auth
src/lib/ — db, migrations, config, fts, paths, rate-limit
migrations/ — forward-only NNNN_name.sql, checksum-validated at startup
scripts/ — smoke harnesses + vm-autodeploy.sh

Read the full file on GitHub · 90 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.

7d ago First seen · 90 lines · 1,118 tokens per session scan A 6e3c5919d0fb

Subscribe to this mod's changes

shinobi CLAUDE.md is an instructions file published in the GitHub repository numbererikson/shinobi (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,118 tokens to every session, about $0.0056 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.

Claude Code Memory and context Project management agent-memory ai-agents ai-coding-assistant cline cursor

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

shinobi: Instructions file for Claude Code