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/peter-gy/anywidget-mcp/agents-mdgit clone --depth 1 https://github.com/peter-gy/anywidget-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/peter-gy/anywidget-mcp/agents-md)<a href="https://agentmods.dev/instructions/peter-gy/anywidget-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/peter-gy/anywidget-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 | $0.02371 | $0.02371 |
| Opus 5 | $0.01185 | $0.01185 |
| Sonnet 5 | $0.00474 | $0.00474 |
| Haiku 4.5 | $0.00237 | $0.00237 |
Grade A, and why
anywidget-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 5d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anywidget-mcp
anywidget-mcp is a uv and pnpm workspace for exposing AnyWidget classes and
factories as interactive MCP Apps. Python owns registration, widget sessions,
traitlets, and model-visible state. The browser app owns AnyWidget rendering
and MCP host integration. Preserve that split.
Read this file before changing the repository.
Commands
| Purpose | Command | Expected result |
|---|---|---|
| Install Python | uv sync --all-packages --group dev |
Workspace and development dependencies resolve |
| Install JavaScript | pnpm install --frozen-lockfile |
Vite+ workspace installs from pnpm-lock.yaml |
| Check JavaScript | pnpm check |
Formatting, linting, and type checks pass |
| Test browser app | pnpm test |
Vite+ tests pass |
| Test Python | pnpm --filter @anywidget-mcp/python build && uv run --package anywidget-mcp pytest -q packages/anywidget-mcp/tests |
Browser resource builds, then Python contract tests pass |
| Build browser assets | pnpm build |
Package builds and the single-file app are produced |
| Build distribution | make package |
Wheel, sdist, wheel-from-sdist, import, and CLI checks pass |
| Full handoff gate | make check |
Every local gate passes |
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.
- 5d ago First seen · 212 lines · 2,371 tokens per session scan A 1f39e316a768
anywidget-mcp AGENTS.md is an instructions file published in the GitHub repository peter-gy/anywidget-mcp (6 stars, last pushed 18d ago), licensed MIT. It adds 2,371 tokens to every session, about $0.0119 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
tutorclaw-mcp AGENTS.md
AGENTS.md instructions for mohsinsheikhani/tutorclaw-mcp, covering session start, tutoring flow, tool selection rules and when tools return errors.
tutorclaw-mcp CLAUDE.md
Claude Code instructions for mohsinsheikhani/tutorclaw-mcp, covering tutorclaw mcp server, rules and after every build.
RivalSearchMCP AGENTS.md
Instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
mcp-steroid CLAUDE.md
Claude Code instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
calibremcp AGENTS.md
AGENTS.md instructions for sandraschi/calibremcp, covering calibremcp — agent guide, entry points, standards, key files and http daemon + stdio proxy.