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/ianphil/promptbin/agents-mdgit clone --depth 1 https://github.com/ianphil/promptbinWhat 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 | $0.01040 | $0.01040 |
| Opus 5 | $0.00520 | $0.00520 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
promptbin 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
PromptBin is an MCP server example designed for easy distribution and usage via PyPI.
Primary workflow: uv add promptbin && uv run promptbin
Project Structure & Module Organization
- src/promptbin/app.py: Complete Flask web app with all routes, views, and lifecycle management.
- src/promptbin/mcp/server.py: Full MCP server implementation with subprocess integration.
- src/promptbin/managers/prompt_manager.py: File-based storage with search, categories, and metadata.
- src/promptbin/managers/share_manager.py: Secure sharing logic with ephemeral tokens.
- src/promptbin/managers/tunnel_manager.py: Microsoft Dev Tunnels integration with rate limiting and security.
- src/promptbin/utils/setup_checker.py: System validation and diagnostic tool.
- src/promptbin/utils/install_devtunnel.py: Cross-platform installer automation.
- src/promptbin/web/templates/ and static/: HTMX-powered UI templates and assets.
- ~/promptbin-data/: Local JSON prompt data, organized by category (coding, writing, analysis).
- TUNNELS.md: Comprehensive technical documentation for Dev Tunnels.
- ai_docs/: Internal planning and development prompts (completed phases).
Build, Test, and Development Commands
Production usage (PyPI):
- Install:
uv add promptbin(requires Python 3.11+ and uv). - Run both MCP + web:
uv run promptbin(primary use case). - Run MCP only:
uv run promptbin --mcp(MCP server mode). - Run web only:
uv run promptbin --web(standalone web mode). - Setup verification:
uv run promptbin-setup(validates system readiness). - Install Dev Tunnels:
uv run promptbin-install-tunnel(cross-platform installer).
Development (local):
- Install deps:
uv sync. - Run both MCP + web:
uv run promptbin. - Run MCP only:
uv run promptbin --mcp. - Run web only:
uv run promptbin --web. - Lint/format: None enforced; see style section below.
Coding Style & Naming Conventions
- Python style: PEP 8, 4‑space indents, descriptive names.
- Types: prefer type hints for public functions and return values.
- Modules: keep files focused (web in src/promptbin/app.py, protocol in src/promptbin/mcp/server.py, storage in src/promptbin/managers/prompt_manager.py).
- IDs: prompt files named
<id>.jsonunder~/promptbin-data/<category>/(IDs generated likeYYYYMMDD_HHMMSS_xxxxxxxx). - Categories: use one of
coding,writing,analysis.
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 · 65 lines · 1,040 tokens per session scan A 35d528686dbd
promptbin AGENTS.md is an instructions file published in the GitHub repository ianphil/promptbin (0 stars, last pushed 7mo ago), licensed MIT. It adds 1,040 tokens to every session, about $0.0052 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.