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/dezxbt/agentx/agents-mdgit clone --depth 1 https://github.com/DezXBT/AgentXWhat 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 | $0.00760 | $0.00760 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
AgentX AGENTS.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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentx — agent integration guide
This file tells an autonomous agent how to drive X/Twitter through agentx.
Contract
- Drive everything through the
agentxbinary (or importpkg/agentin Go). - Every command prints one JSON object to stdout and nothing else:
- success:
{"ok":true,"schema_version":"1","data":...,"pagination":{"nextCursor":"..."}} - failure:
{"ok":false,"schema_version":"1","error":{"code":"...","message":"..."}} - process exit code is
0on success,1on a handled error.
- success:
- Parse the envelope; never scrape human text.
datashape depends on the command (a tweet array for timelines, a user object foruser, etc.).
Decision guide
| Goal | Command |
|---|---|
| Read my home feed | agentx feed -n N (add --latest for chronological) |
| Search | agentx search --type Top|Latest "<query>" -n N |
| Look up a profile | agentx user <handle> |
| Read someone's tweets | agentx posts <handle> -n N |
| Read one tweet (no login needed) | agentx tweet <id|url> |
| Read a tweet + replies | agentx thread <id|url> |
| Publish | agentx post "<text>" |
| Reply / quote | agentx reply <id> "<text>" / agentx quote <id> "<text>" |
| Engage | agentx like|unlike|retweet|unretweet|bookmark|delete <id> |
<id|url> accepts a numeric id or any https://x.com/<user>/status/<id> URL.
Multi-account
- Register once:
agentx account add --name <n> --auth-token <t> --ct0 <c> [--cookie "<full cookie>"]. - Choose per call with
-a <name>or setAGENTX_ACCOUNT. - The first account becomes the default; change it with
agentx account default <name>. - Inspect with
agentx account list(returns names + which is default).
Prefer supplying the full browser cookie string via --cookie: it keeps the
session looking like a real browser, which makes the cookies last much longer.
Pagination
Timeline-style results include pagination.nextCursor. To page, re-issue the
same command with --cursor <nextCursor>. Stop when nextCursor is empty or
stops changing.
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 · 66 lines · 760 tokens per session scan A 62df0cddecff
AgentX AGENTS.md is an instructions file published in the GitHub repository DezXBT/AgentX (38 stars, last pushed 2mo ago), licensed MIT. It adds 760 tokens to every session, about $0.0038 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 instructions, from other repositories
Upsonic CLAUDE.md
Claude Code instructions for Upsonic/Upsonic, covering claude.md, project overview, ai operational guides, default pre-work consultation and keep documents/ai/explanation/ in sync with code.
Undefined CLAUDE.md
Instructions for 69gg/Undefined, covering claude.md, 项目概述, 开发命令, 依赖安装 / 初始化 and 启动.
Undefined AGENTS.md
Instructions for 69gg/Undefined, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and tools & features.
ouro CLAUDE.md
Instructions for ouro-ai-labs/ouro, covering ouro — agent instructions, command discovery (no guessing), core workflow (verify → explore → plan → implement → ship), quickstart (local dev) and three-layer architecture (read first).
ouro AGENTS.md
Instructions for ouro-ai-labs/ouro, a project described as: Ouro is an open-source AI agent — run it as a Coding agent CLI or deploy it as a bot just like JARVIS.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.