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/teleomorph/pinako-mcp/agents-mdgit clone --depth 1 https://github.com/teleomorph/pinako-mcpWrote 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/teleomorph/pinako-mcp/agents-md)<a href="https://agentmods.dev/instructions/teleomorph/pinako-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/teleomorph/pinako-mcp/agents-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 | $0.00588 | $0.00588 |
| Opus 5 | $0.00294 | $0.00294 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
pinako-mcp 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 3d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guidance for AI coding agents
This repo is the Pinako AI Bridge - the local MCP (Model Context Protocol) server that connects Pinako, a browser tab / session / bookmark organizer, to desktop AI clients (Claude Code, Claude Desktop, Cursor, ChatGPT-Codex, VS Code, and any HTTP MCP client).
If you're here to USE Pinako (not develop this repo)
You probably don't need this codebase at all:
- Local bridge already installed? Connect your MCP client to
http://127.0.0.1:37421/mcp(the installer appends a machine-local access token to the configured URL; without it the surface is read-only). - No install: use the hosted Remote MCP Connector at
https://connect.pinako.pro/mcp(OAuth sign-in). - Tool list with descriptions: https://pinako.pro/.well-known/mcp/server-card.json
- Setup + troubleshooting: https://pinako.pro/docs/mcp-setup/ (markdown: https://pinako.pro/docs/mcp-setup/index.md)
- Product overview for agents: https://pinako.pro/llms.txt
If you're developing in this repo
- Layout:
host.jsis the native-messaging host + HTTP MCP server;install.js/setup/handle client auto-configuration;installer/is the Tauri Windows installer;src/holds shared modules;tests/runs on vitest (npx vitest run). - The extension is the source of truth for tool behavior. The bridge relays tool calls to the Pinako extension over native messaging; it does not reimplement tree logic. Tool schemas here must stay in parity with the extension's chat tools and the hosted connector (the "tool-surface parity" rule: a tool added or changed on one surface must land on all of them).
- Writes are guarded. Destructive operations return
CONFIRMATION_REQUIREDuntil explicitly confirmed;bulk_applybatches up to 250 sub-ops as one undoable step. Keep those invariants - clients depend on the structured{ok, error}result shape. - Don't bump versions or publish. Releases are cut from the private
product repo's release ritual (build → tag → GitHub Release). Leave
package.jsonversion, tags, andRELEASE_NOTES_NEXT.mdto the maintainer unless asked. - Docs for the product live at https://pinako.pro/docs/ (markdown twin: https://pinako.pro/docs/index.md) - prefer reading those over guessing product behavior from this repo's code.
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.
- 3d ago First seen · 44 lines · 588 tokens per session scan A 2bfba5bc1098
pinako-mcp AGENTS.md is an instructions file published in the GitHub repository teleomorph/pinako-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 588 tokens to every session, about $0.0029 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.