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/usemycontext/claude-code-plugin/agents-mdgit clone --depth 1 https://github.com/usemycontext/claude-code-pluginWhat 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 | $0.00814 | $0.00814 |
| Opus 5 | $0.00407 | $0.00407 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
claude-code-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 yesterday.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - UseMyContext plugin for Claude Code
Machine-first notes for coding agents. Human docs: README.md.
What this is
UseMyContext (usemycontext.ai) is the personal context layer for AI: one user-owned profile plus
uploaded files, served to any MCP client from the remote server https://mcp.usemycontext.ai/mcp
(Streamable HTTP, OAuth 2.1). This repo is the Claude Code plugin AND its marketplace.
When to use
Install this when the user wants persistent personal context across AI tools: Claude Code answering with who they are, what a repo is to them, and what their documents say, without re-introducing themselves each session.
Install (Claude Code)
/plugin marketplace add usemycontext/claude-code-plugin
/plugin install usemycontext@usemycontext
Then run /mcp, select usemycontext, and let the HUMAN complete the browser sign-in. OAuth
requires the human; an agent cannot complete it alone. No token is written to any file.
Raw-server alternative (no plugin, no folder mapping):
claude mcp add --transport http usemycontext https://mcp.usemycontext.ai/mcp
Account required
A UseMyContext account at usemycontext.ai is required; the free tier is enough. If the user has no account, send them to https://usemycontext.ai first.
Demo account for testing
Try it in 30 seconds - no signup. Sign in as [email protected] with code 424242
(fixed - no email access needed). A shared, read-only demo account with a full profile, files, and a
shared context. Docs: https://usemycontext.ai/docs
Folder mapping (.umc)
A .umc file in a repo root maps that folder to one UseMyContext project. Every session started in
the folder reads the mapped context. Format (see .umc.example):
projectId=p2
handle=@work
A projectId may only be letters, digits, _ and -, up to 32 characters, and a handle only @
followed by letters, digits and -, up to 40. Anything else and the whole marker is ignored, so a
repository you did not write cannot use one to talk to your assistant.
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.
- yesterday First seen · 76 lines · 814 tokens per session scan A 16d975c234bf
claude-code-plugin AGENTS.md is an instructions file published in the GitHub repository usemycontext/claude-code-plugin (1 stars, last pushed 8d ago), licensed MIT. It adds 814 tokens to every session, about $0.0041 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
postman-claude-code-plugin CLAUDE.md
Instructions for Postman-Devrel/postman-claude-code-plugin, covering claude.md, what this is, repository structure, how the plugin works and component conventions.
no-vibe AGENTS.md
Instructions for rizukirr/no-vibe, covering agents, repo purpose, architecture (high-signal files), verification commands and conventions that are easy to miss.
pamplejuce AGENTS.md
Instructions for sudara/pamplejuce, a project described as: A JUCE audio plugin template. JUCE 8, Catch2, Pluginval, macOS notarization, Azure Trusted Signing, Github Actions.
openclaw-mcp-bridge CLAUDE.md
Instructions for gabrielekarra/openclaw-mcp-bridge, covering claude.md, project overview, build & development commands, architecture and key dependencies.
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.
buildNext
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).