twitter-mcp: Instructions file for Claude Code

CLAUDE.md

twitter-mcp CLAUDE.md is an instructions file for Claude Code from tangivis/twitter-mcp. It costs 1,543 tokens per session, scanned A, original, MIT.

Repository instructions for tangivis/twitter-mcp, an MCP project connected to Twitter/X. They define rules for pull requests, automated review, continuous-integration checks, and preserving callback behavior.

In plain words
What is it for?
Use them when changing twitter-mcp, especially for pull requests, CI failures, review fixes, repeated review cycles, and callback-chain reliability.
Why use it?
They tell an agent how to respond to review and test results without re-deriving the project's process. This helps keep changes aligned with the maintainer's merge policy.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is tangivis/twitter-mcp's own configuration. It tells Claude Code how to work on twitter-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything twitter-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tangivis/twitter-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tangivis/twitter-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tangivis/twitter-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for twitter-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tangivis/twitter-mcp/claude-md.svg)](https://agentmods.dev/instructions/tangivis/twitter-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tangivis/twitter-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tangivis/twitter-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,543 This file is loaded in full into every session.
When invoked 1,543 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01543 $0.01543
Opus 5 $0.00772 $0.00772
Sonnet 5 $0.00309 $0.00309
Haiku 4.5 $0.00154 $0.00154

Measured 8d ago against content hash 1e4deae20c60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

twitter-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 8d 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.

CLAUDE.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — repo-specific conventions for Claude Code sessions

This file is read by Claude Code when a session starts in this repo. It captures non-obvious conventions the maintainer has explicitly chosen, so any future session (or sub-agent) immediately knows the local rules without re-deriving them from chat history.

Out of scope here: things already documented in README.md (install + usage), CONTRIBUTING.md (test strategy, CI structure), docs/TECHNICAL.md (architecture).


Merge policy — zero-confirmation when checks are green

When you (Claude Code) open a PR via mcp__github__create_pull_request and the follow-up CI runs land, act on the result without prompting the maintainer:

Condition Action
CI 6/6 green AND MiniMax review decision is approve OR comment Immediately call mcp__github__merge_pull_request (squash). Don't ask.
CI 6/6 green AND review decision is request-changes Read the review's must_fix items. Push fixes for the real ones, skip false-positives. Trigger a new review iteration.
CI red Inspect the failing job, push a fix. Don't ask.
MiniMax can't converge after 5 iterations The pr-review.yml workflow auto-escalates to Sonnet 4.6 (issue #60). If Sonnet also blocks, it opens a needs-human issue — at that point ping the maintainer.

You merge through the user's MCP-authenticated path (their token, not workflow GITHUB_TOKEN), so the resulting push: main cascades to publish.yml and docs.yml automatically. No PAT needed (issue #54).

Only prompt the maintainer when:

  • The MiniMax review is genuinely ambiguous (you can't tell true from false positive)
  • The PR changes user-facing public API surface (PyPI version, MCP tool schema, etc.)
  • A workflow fails in a way you haven't seen before (novel error class)
  • The maintainer explicitly says "wait for me" / "I'll merge"

The instinct to "ask before merging" is wrong here. The maintainer has already delegated this decision via #54's pipeline simplification + repeated explicit agreement. Asking again per-PR is friction without value.

Read the full file on GitHub · 127 lines

Changes

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.

  1. 8d ago First seen · 127 lines · 1,543 tokens per session scan A 1e4deae20c60

Subscribe to this mod's changes

twitter-mcp CLAUDE.md is an instructions file published in the GitHub repository tangivis/twitter-mcp (10 stars, last pushed 22d ago), licensed MIT. It adds 1,543 tokens to every session, about $0.0077 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens