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/mpazik/binder/agents-mdgit clone --depth 1 https://github.com/mpazik/BinderWhat 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 | $0.00655 | $0.00655 |
| Opus 5 | $0.00328 | $0.00328 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
Binder AGENTS.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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Binder
Binder is a Local-first knowledge base with bidirectional Markdown sync, editor integration (LSP), MCP server, and CLI.
Status: Early development — APIs and data formats may change. Breaking changes are allowed.
Tech Stack
- TypeScript everywhere for type safety and better developer tooling
- Bun for development, testing, building, and package management
- Node.js 22+ as the production runtime (built CLI runs via
node) - SQLite as a database for both local and production (
bun:sqlitein dev,better-sqlite3in production) - Drizzle ORM for type-safe database operations and migrations
- Zod for runtime schema validation
- VS Code Language Server Protocol for editor integration and diagnostics
- Yargs for CLI argument parsing
Monorepo Structure
Bun workspaces monorepo with three packages under packages/:
@binder.do/cli— Main entry point. Contains the CLI, LSP server, MCP server, Markdown document sync/diffing, schema loading, validation logic, and LLM integration (via@mariozechner/pi-ai).@binder/repo— Knowledge graph engine. Entity/relationship storage, transaction processing, changeset computation, filtering. The@binder/repo/localsub-entry provides workspace bootstrap: config loading, path resolution, andinit/openfor using binder as a library.@binder/utils— Shared utilities. Pure helpers for arrays, strings, encoding, error handling etc.
Testing
- Unit tests —
bun testruns unit tests under each package'ssrc/directory. - E2E tests —
bun test:e2eruns end-to-end smoke tests underpackages/cli/tests/. These spin up temporary workspaces, seed data, and exercise CLI, LSP, and MCP workflows against a real runtime.
Development
Dev Instance
Two binder instances exist in the project. Use the right one:
bun run dev-- dev instance (.binder-dev/data). Use for experimentation, testing, inspecting data.- The
bindertool / CLI -- production instance. For reading docs and updating task records.
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.
- 2d ago First seen · 52 lines · 655 tokens per session scan A 0467468672cc
Binder AGENTS.md is an instructions file published in the GitHub repository mpazik/Binder (40 stars, last pushed 10d ago), licensed MIT. It adds 655 tokens to every session, about $0.0033 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.
Other instructions, from other repositories
engraphis AGENTS.md
Instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, 0. read this first — two architectures live in one package, 1. commands, ── unified dashboard + memory inspector ── and 2. the v2 recall pipeline (where the real work is).
llm-wiki-newsroom AGENTS.md
Instructions for alfadur7/llm-wiki-newsroom, covering llm wiki newsroom — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-newsroom GEMINI.md
Instructions for alfadur7/llm-wiki-newsroom, covering llm wiki newsroom — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
engraphis CLAUDE.md
Instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.
llm-wiki-newsroom CLAUDE.md
Instructions for alfadur7/llm-wiki-newsroom, covering llm wiki newsroom, roles, universal cycle, the four loops and reground.
kb AGENTS.md
Instructions for hraness/kb, a project described as: A knowledge base for coding agents, built from Markdown, backlinks, semantic search, and Git context.