A command-line tool for reading, searching, posting on, and managing engagement on X/Twitter. It uses browser-cookie authentication and can rotate between multiple accounts.

Use it to read or search posts, publish content, handle engagement commands, authenticate with cookies, and distribute requests across accounts.

It lets scripts and terminal workflows work with X/Twitter without the older Node-based bird tool.

How guzus/ai-research-arm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to guzus/ai-research-arm. 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/guzus/ai-research-arm/main/.claude/skills/birdy/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/guzus/ai-research-arm

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/guzus/ai-research-arm/birdy/github.svg)](https://agentmods.dev/skills/guzus/ai-research-arm/birdy)

Your own site

<a href="https://agentmods.dev/skills/guzus/ai-research-arm/birdy"><img src="https://agentmods.dev/badge/skills/guzus/ai-research-arm/birdy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/guzus/ai-research-arm/birdy"><img src="https://agentmods.dev/badge/skills/guzus/ai-research-arm/birdy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,796 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.01796
Opus 5.5	$0.00010	$0.00718
Sonnet 5.5	$0.00005	$0.00359
Haiku 4.5	$0.00002	$0.00180

Measured 2mo ago against content hash 763725c3cd31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

birdy scanned grade C with 2 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 2mo 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

# or: curl -fsSL https://raw.githubusercontent.com/guzus/birdy/main/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

# or: curl -fsSL https://raw.githubusercontent.com/guzus/birdy/main/install.sh | bash

.claude/skills/birdy/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

birdy

Fast X/Twitter CLI using GraphQL + cookie auth. One static Go binary — no Node runtime.

Replaced the Node bird CLI (@steipete/bird), retired 2026-08-08. birdy began as a rotation proxy in front of bird and has served all 24 commands natively since v1.0.0. Command and flag names are unchanged, so bird X is birdy X. npm reports @steipete/bird as "no longer supported" — do not reinstall it. Note that birdy still falls back to bird when its native path errors, so a bird CLI not found message means the native call failed (usually a rate limit), not that you need to install bird.

Install

brew tap guzus/tap && brew trust guzus/tap && brew install birdy
# or: curl -fsSL https://raw.githubusercontent.com/guzus/birdy/main/install.sh | bash
# in CI: use .github/actions/install-birdy

Authentication

birdy uses cookie-based auth, and can rotate several accounts to spread rate-limit pressure.

Use --auth-token / --ct0 to pass cookies directly, or --cookie-source for browser cookies.

Run birdy check to see which source is active. For Arc/Brave, use --chrome-profile-dir <path>.

Multi-account rotation

birdy account add main            # store an account
birdy account list                # list accounts
birdy account disable <name>      # take out of rotation without removing
birdy status                      # current rotation status
birdy budget                      # per-account 429 history + cooldown state
birdy -a main read <id>           # pin one account, skipping rotation
birdy -s quota-aware search "ai"  # route around accounts marked "hot"

Rotation strategies (-s): round-robin (default), least-recently-used, least-used, random.

Commands

Account & Auth

birdy whoami                    # Show logged-in account
birdy check                     # Show credential sources
birdy query-ids --fresh         # Refresh GraphQL query ID cache

Reading Tweets

birdy read <url-or-id>          # Read a single tweet
birdy <url-or-id>               # Shorthand for read
birdy thread <url-or-id>        # Full conversation thread
birdy replies <url-or-id>       # List replies to a tweet

Read the full file on GitHub · 225 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.

2mo ago First seen · 225 lines · 24 tokens per session scan C 763725c3cd31

Subscribe to this mod's changes

birdy is a skill published in the GitHub repository guzus/ai-research-arm (14 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,796 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Marketing and SEO ai ai-agents claude github-actions news

birdy next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
birdyguzus/ai-research-arm	Skill	14	today	MIT	C	24	Claude Code
horizonThysrael/Horizon	Skill	13k	yesterday	MIT	A	95	Claude Code, Codex
pr-review-triagecobusgreyling/loop-engineering	Skill	12k	yesterday	MIT	A	35	Claude Code
install-loopcobusgreyling/loop-engineering	Skill	12k	yesterday	MIT	A	59	Claude Code
loop-verifiercobusgreyling/loop-engineering	Skill	12k	yesterday	MIT	A	47	Claude Code
changelog-scancobusgreyling/loop-engineering	Skill	12k	yesterday	MIT	A	35	Claude Code
draft-release-notescobusgreyling/loop-engineering	Skill	12k	yesterday	MIT	A	23	Claude Code

ai-research-arm: Skill for Claude Code