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/andreaselmi/threads-mcp/claude-mdgit clone --depth 1 https://github.com/andreaselmi/threads-mcpWhat 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 | $0.00591 | $0.00591 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
threads-mcp 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
threads-mcp
An MCP server for the Threads API, published as @andreaselmi/threads-mcp. It does platform
I/O and nothing else. Source: https://github.com/andreaselmi/threads-mcp
The boundary
Nothing product-specific enters this repo — no themes, no tone of voice, no editorial rules, no product names, not even inside a comment or an example. This package is used by projects that know what to post; it only knows how to post. If a change would make the server useful only to one caller, it belongs in that caller, not here.
Credentials live only in the environment (THREADS_ACCESS_TOKEN). Never in a file, never in a
log line, never in a test fixture that looks real. The test suite runs against a stubbed
fetch and must keep working with no token set.
Publishing is irreversible: a post goes live immediately and cannot be edited. Publish tools
are marked destructiveHint: true and any new one must be too.
Commands
npm test # vitest, no network
npm run build # tsc to dist/
npm run dev # run from source over stdio
Manual smoke test of the built server:
printf '%s\n' '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"t","version":"1"}}}' \
| THREADS_ACCESS_TOKEN=fake node dist/index.js
Shipping a change
Consumers get this package from npm, so a change that is committed but not published does not exist for them. The full cycle:
- Change the code and its tests.
npm teststays green. - Commit and push to
main. npm version patch(orminor— see below). This bumpspackage.json, commits, and tags.npm publishfrom a real terminal, not from an agent session: npm requires two-factor confirmation and the prompt needs a TTY.prepublishOnlyrebuilds and reruns the tests, so a broken package cannot go out.git push --follow-tags, so the tag on GitHub matches the version on npm.
patch for a fix, minor for a new tool or a new optional argument, major for anything that
changes or removes an existing tool's name, arguments or return shape. Callers pin ^0.1.0, so
a minor reaches them on their next restart and a major does not — which is the point.
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.
- 2d ago First seen · 53 lines · 591 tokens per session scan A 1b7f5fef8e2c
threads-mcp CLAUDE.md is an instructions file published in the GitHub repository andreaselmi/threads-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 591 tokens to every session, about $0.0030 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
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.