Borrowing it
Nothing to install: this file belongs to Peiiii/nextclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/skills/x-twitter-bird/SKILL.mdgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/skills/peiiii/nextclaw/x-twitter-bird)<a href="https://agentmods.dev/skills/peiiii/nextclaw/x-twitter-bird"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/x-twitter-bird/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.
<a href="https://agentmods.dev/skills/peiiii/nextclaw/x-twitter-bird"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/x-twitter-bird.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.00939 |
| Opus 5 | $0.00022 | $0.00469 |
| Sonnet 5 | $0.00009 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
x-twitter-bird 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 today.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X / Twitter 读取与发布
Primary contract
- Credentials live in a user-local file, not in the repo:
- default path:
~/.nextclaw/secrets/x-bird.json
- default path:
- CLI 操作统一通过
scripts/x-bird.mjs；真实浏览器操作走当前可用的 Computer Use 工具，不受 CLI 路径限制。 - The script passes
--auth-tokenand--ct0explicitly tobird - 不依赖 bird 自动读取凭据环境变量；由 wrapper 显式传入。版本从实际解析到的
@steipete/bird/package.json核对，不把历史版本当成本机现状。
操作路由
读取与搜索使用下方命令。发布、浏览器操作或 CLI 故障时，读取发布路径与故障处理。已有发布授权不重复询问。
Setup
Store credentials once:
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs auth set --auth-token '<token>' --ct0 '<token>'
Check the current account:
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs whoami --plain
Common commands
Read bookmarks:
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs bookmarks -n 20 --json
Read likes:
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs likes -n 20 --json
Search:
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs search 'DeepSeek V4 reasoning_content' -n 10 --json
Read a tweet or thread:
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs read <tweet-id-or-url> --json
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs thread <tweet-id-or-url> --json
Post only after the user explicitly asks:
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs tweet 'text here'
node .agents/skills/x-twitter-bird/scripts/x-bird.mjs reply <tweet-id-or-url> 'text here'
Rules
- Treat
auth_tokenandct0as full login credentials - Never write them into repo files, docs, tests, or iteration logs
- 发布授权按发布路径 reference 处理。已授权的稳定 minor 发布在发布核验及公共链接检查完成后直接执行，不重复确认。
- Stable minor release posts should include one public-safe, high-information image by default. Choose the best fit among a real product screenshot, a benchmark/release summary card, AI-generated campaign art, or an AI-assisted composition containing an unaltered real screenshot. Never present generated UI as a real product screenshot or change verified release facts. Patch releases do not post unless the user explicitly overrides this rule.
- When
HTTP_PROXY/HTTPS_PROXYis required, invoke this wrapper with a Node version that supports environment proxies (for exampleNODE_USE_ENV_PROXY=1 <node-24+> scripts/x-bird.mjs ...). The wrapper launchesbirdwith the same Node executable so the proxy setting reaches X requests. - The wrapper refreshes current GraphQL query IDs before every
tweetorreply. 报错后区分 query ID、网络、频率限制和 226，不把所有错误归为账号封控；后续操作遵守 reference 的查重与停止条件。 - A successful write response is not completion by itself. 通过浏览器详情或 wrapper 回读已知 ID，核对作者、完整正文及素材后才报告成功并记录 URL。缺少 ID、回读失败或内容不符不能盲目重发。多个平台分别报告状态，一个成功不代表整批完成；新发不隐含授权删除旧帖。
- Prefer
--jsonfor read/search workflows so downstream analysis stays structured - If the user asks for only reading, do not post, like, follow, or unbookmark anything
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -4 lines · +4 tokens per session 806e577c579a
- 10d ago First seen · 83 lines · 40 tokens per session scan A 7a71fa4cb326
x-twitter-bird is a skill published in the GitHub repository Peiiii/nextclaw (256 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 939 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.
tmux-lane-orchestrator
Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.
ghcrawl-cluster-operator
Use when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the ghcrawl CLI.
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
crabpot-perf-metrics
Interpret Crabpot and OpenClaw performance dashboard metrics, import-loop profiles, runtime profiles, and branch-to-branch perf deltas without over-reading noisy samples.
org-branch-cleanup
Audit and safely prune stale branches across a GitHub organization with immutable snapshots, conservative merged-PR classification, live SHA/protection/open-PR revalidation, resumable deletion ledgers, and post-delete verification. Use when a maintainer asks to clean up old, dead, merged, bot-created, or abandoned…