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/nevaaron/x-smart-read/agents-mdgit clone --depth 1 https://github.com/nevaaron/x-smart-readWhat 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 | $0.02001 | $0.02001 |
| Opus 5 | $0.01001 | $0.01001 |
| Sonnet 5 | $0.00400 | $0.00400 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
x-smart-read 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — X (Twitter) Skill (Machine-Readable Reference)
This file is for AI agents (Claude Code, OpenClaw, Cursor, Copilot, etc.). For human docs, see README.md. For setup instructions, see SETUP.md.
Setup
Credentials directory: ~/.openclaw/skills-config/x-twitter/
Required files: config.json (created by setup)
uv run scripts/x_setup.py # Interactive setup — imports keys, validates, picks budget tier
Commands
All scripts use uv run (auto-installs dependencies). Run from the skill directory. All commands support --dry-run to preview cost and --no-budget to skip budget checks.
x_briefing.py — Combined Morning Briefing
# Full briefing: posts + mentions + profile (~$0.020)
uv run scripts/x_briefing.py
# Custom lookback period
uv run scripts/x_briefing.py --hours 48
# Preview cost
uv run scripts/x_briefing.py --dry-run
x_timeline.py — Your Posts + Engagement
# Recent posts with engagement metrics (~$0.005)
uv run scripts/x_timeline.py recent
uv run scripts/x_timeline.py recent --max 5
uv run scripts/x_timeline.py recent --hours 24
# Top posts by engagement — FREE, reads from local store
uv run scripts/x_timeline.py top --days 7 --max 10
# Refresh one tweet's metrics (~$0.005)
uv run scripts/x_timeline.py refresh <TWEET_ID>
# Accountability check — how active on X? (~$0.005)
uv run scripts/x_timeline.py activity
# Preview cost without calling API
uv run scripts/x_timeline.py --dry-run recent
x_mentions.py — Mentions & Replies
# Recent mentions (~$0.005)
uv run scripts/x_mentions.py recent
uv run scripts/x_mentions.py recent --max 10 --hours 24
# Mentions with parent tweet context (~$0.005-0.030) [EXPENSIVE]
uv run scripts/x_mentions.py recent --context
x_read.py — Read Any Tweet or Thread
# Read a tweet by URL or ID (~$0.005)
uv run scripts/x_read.py https://x.com/user/status/123456
uv run scripts/x_read.py 123456
# Fetch full thread (~$0.005-0.010)
uv run scripts/x_read.py 123456 --thread
# Preview cost
uv run scripts/x_read.py --dry-run https://x.com/user/status/123456
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 · 206 lines · 2,001 tokens per session scan A e0877c5ceb6f
x-smart-read AGENTS.md is an instructions file published in the GitHub repository nevaaron/x-smart-read (11 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 2,001 tokens to every session, about $0.0100 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
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.