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/hadriangateway/platter/claude-mdgit clone --depth 1 https://github.com/hadriangateway/platterWrote 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/hadriangateway/platter/claude-md)<a href="https://agentmods.dev/instructions/hadriangateway/platter/claude-md"><img src="https://agentmods.dev/badge/instructions/hadriangateway/platter/claude-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 5.1 | $0.00645 | $0.00645 |
| Opus 5 | $0.00322 | $0.00322 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
platter CLAUDE.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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Platter is an MCP (Model Context Protocol) server that exposes file and bash tools over Stdio and StreamableHTTP transports. It gives AI agents controlled access to a computer's resources. Built with Bun, compiles to standalone executables.
Commands
bun install # install dependencies
bun run dev # run from TypeScript directly
bun run build # bundle to dist/
bun run compile # standalone binary for current platform -> ./platter
bun run compile:all # cross-compile for all platforms
bun run format # format with Biome
bun run format:check # check formatting only
bun run lint # lint with Biome
bun run lint:fix # lint and auto-fix
bun run typecheck # TypeScript type checking
bun test # run all tests
bun test tests/edit.test.ts # run a single test file
Architecture
Entry point: src/index.ts — CLI argument parsing, transport selection (stdio/http/tray), server initialization.
Server: src/server.ts — Creates McpServer, registers 7 tools (read, write, edit, bash, glob, grep, js), wires up security validators.
Security: src/security.ts — Tool access control, path validation with symlink resolution, command regex whitelisting, sandbox configuration.
Config: src/config.ts — Persists settings to ~/.config/platter/config.json.
Process registry: src/process-registry.ts — Tracks child processes with soft timeouts, output buffering, reattachment support, and automatic stale process cleanup.
Tools (src/tools/): Each tool has its own file. sandbox-bash.ts is an alternative bash implementation using just-bash (TypeScript bash reimplementation with virtual FS).
Tray (src/tray/): Linux system tray integration via DBus (SNI protocol + DBus menus). Also contains the HTTP controller for dynamic tool toggling and clipboard support.
Key patterns
- All tool output is truncated to last 2000 lines or 50KB (errors tend to be at the end).
- Path validation resolves symlinks via
realpath()before comparison. - The edit tool uses fuzzy matching that normalizes smart quotes, dashes, and Unicode whitespace.
- Process reattachment: long-running bash commands can be paused and resumed by PID.
- The JS tool auto-returns the last expression and can load packages from unpkg.com.
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 · 57 lines · 645 tokens per session scan A b4a89d1af1c3
platter CLAUDE.md is an instructions file published in the GitHub repository hadriangateway/platter (0 stars, last pushed 2mo ago), licensed MIT. It adds 645 tokens to every session, about $0.0032 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.