Borrowing it
Nothing to install: this file belongs to teleomorph/pinako-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/teleomorph/pinako-mcp/main/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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.00599 | $0.00599 |
| Opus 5.5 | $0.00240 | $0.00240 |
| Sonnet 5.5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
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 1mo 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 every tool refuses, with a message). - No install: use the hosted Remote MCP Connector at
https://connect.pinako.pro/mcp(OAuth sign-in; name it "Pinako (cloud)"). - 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.
- 1mo ago Changed · +2 tokens per session 6bfdc1a4eb3f
- 1mo ago Changed · +9 tokens per session 4d7908f248d6
- 2mo 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 16d ago), licensed MIT. It adds 599 tokens to every session, about $0.0024 per session on Opus 5.5. 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.
pinako-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pinako-mcp AGENTS.mdteleomorph/pinako-mcp | Instructions file | 1 | 16d ago | MIT | A | 599 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |