Borrowing it
Nothing to install: this file belongs to teamshared-ai/teamshared-plugin. 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/teamshared-ai/teamshared-plugin/main/AGENTS.mdgit clone --depth 1 https://github.com/teamshared-ai/teamshared-pluginWrote 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/teamshared-ai/teamshared-plugin/agents-md)<a href="https://agentmods.dev/instructions/teamshared-ai/teamshared-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/teamshared-ai/teamshared-plugin/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/teamshared-ai/teamshared-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/teamshared-ai/teamshared-plugin/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 | $0.01007 | $0.01007 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
teamshared-plugin 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 today.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TeamShared plugin — agent install
Connect once. Bind repos to orgs. Do not add a second TeamShared server.
Unbound https://teamshared.com/mcp keeps working (Connect-time org).
This file is for agents working in this plugin repo and for agents that
install TeamShared into a checkout. Human install: README.md.
Model
- One Connect — the plugin registers
https://teamshared.com/mcp. Cursor uses Settings → Tools & MCP → teamshared → Connect. Claude Code uses/mcp→ Authenticate. Codex uses plugin OAuth. Cursor Cloud / Grok Bot inherit the account-level Cursor Connect. - One org per repo —
teamshared org bind <slug>writes.teamshared/org({"v":1,"slug"}). Capture hooks read that file and POST tohttps://teamshared.com/o/{slug}/mcp. The plugin MCP entry stays on/mcp. - Unbound
/mcpkeeps working — missing or invalid.teamshared/orgis not an error. Tools and capture stay on the Connect-time org. - No second server — do not write
.cursor/mcp.json, project.mcp.json, or Codex[mcp_servers.teamshared]pointing at/o/{slug}/mcp(or a second/mcp). Those load a duplicate TeamShared tool set next to the plugin.
Bind
From an authenticated MCP chat, call org_list / org_context_get, then
org_bind(slug=..., scope=conversation|workspace). Conversation bind is
this Mcp-Session-Id only (else reason=no_session). Workspace bind is
account + repo slug. org_unbind clears the overlay. Precedence: path
/o/{slug}/mcp > conversation > workspace > OAuth/tsk_ default.
Membership is fail-closed; tsk_ keys cannot switch; path mounts cannot
be overridden; this is not a global account switch. Do not tell the user
to install the TeamShared CLI. The local CLI is an optional fallback that
writes .teamshared/org:
teamshared org bind <slug> --token "$TEAMSHARED_TOKEN"
teamshared org status
teamshared org unbind
bind checks membership, then writes only .teamshared/org. status and
unbind are offline. Commit the file. Never store the derived org URL.
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.
- today Changed · +10 lines · +157 tokens per session a926a68ddf88
- 2d ago First seen · 84 lines · 850 tokens per session scan A 987abb608870
teamshared-plugin AGENTS.md is an instructions file published in the GitHub repository teamshared-ai/teamshared-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 1,007 tokens to every session, about $0.0050 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 2026-09-16.
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.
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.
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).