agentmods.dev

XActions copilot-instructions.md

Repository instructions for Copilot contributors working on XActions, an automation project for X. They explain which rules apply to browser scripts, Node.js services, and the API server.

In plain words
What is it for?
Use them before suggesting or making changes to XActions, especially when choosing selectors, handling automation delays, reading results, or working with GraphQL queries.
Why use it?
They prevent changes that work in one runtime but fail in another, trigger account suspensions, hide read errors, or bypass usage limits.

Instructions file for GitHub Copilot

496 +4 5d ago A scan 457 tokens original Apache-2.0
View the source file nirholas/XActions
Install

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.

agentmods
npx agentmods add instructions/nirholas/xactions/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/nirholas/XActions

Made for: GitHub Copilot.

Per session 457 This file is loaded in full into every session.
When invoked 457 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00457 $0.00457
Opus 5 $0.00229 $0.00229
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00046 $0.00046

Measured 2d ago against content hash a67ffa2eab5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

XActions copilot-instructions.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.

.github/copilot-instructions.md · 28 lines

What it actually says

XActions: instructions for Copilot

Read AGENTS.md. It is the single source of truth for how to work in this repository, and it is kept current. This file adds only what you need before you suggest a change; it deliberately does not restate AGENTS.md, because the last time four files described the repository they drifted apart.

  • Three runtime contexts, and code correct in one is broken in another. Browser console scripts have no Node APIs. The library, CLI and MCP server are Node >= 20 ESM (CI runs 20, 22 and 24). The API server is Express with Prisma and Redis. AGENTS.md has the table.
  • X's DOM changes constantly. Prefer data-testid selectors; the current set is in docs/agents/selectors.md.
  • Never remove the delays between actions. Every automation path paces itself on purpose. Removing that is how a user's account gets suspended. The MCP server also enforces per-account daily caps that survive a restart; do not route around them.
  • An empty result is an error, not a zero. Read paths throw rather than reporting "0 results", because a silent zero looks exactly like an account with nothing on it.
  • Do not pin GraphQL query IDs. They are discovered from x.com's own bundles and cached, and every request is signed with an x-client-transaction-id header. Both are load-bearing; a hand-rolled request that skips either gets a worse answer from X.
  • One licence: Apache-2.0. npm run check:licenses enforces it, and anything adapted from another project is recorded in THIRD-PARTY-NOTICES.md first.
  • Tests are npm test (Vitest). New behaviour needs a test; the suite runs offline. npm run lint and npm run docs:check also run in CI.

Everything else is in AGENTS.md.

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. 2d ago First seen · 28 lines · 457 tokens per session scan A a67ffa2eab5d

Subscribe to this mod's changes

XActions copilot-instructions.md is an instructions file published in the GitHub repository nirholas/XActions (496 stars, last pushed 5d ago), licensed Apache-2.0. It adds 457 tokens to every session, about $0.0023 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.

ai-agentautomationclaudegptmass-unfollowmcp
Related

Other instructions, from other repositories

generative-ai-for-beginners AGENTS.md

Instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.

microsoft/generative-ai-for-beginners · 2,850 tokens

big-AGI CLAUDE.md

Claude Code instructions for enricoros/big-AGI, covering claude.md, architecture overview, development commands, git/github remotes and repository layout.

enricoros/big-AGI · 2,703 tokens

openagent CLAUDE.md

Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).

the-open-agent/openagent · 1,049 tokens

langroid CLAUDE.md

Claude Code instructions for langroid/langroid, covering claude.md, commands, development, testing and linting and type checking.

langroid/langroid · 2,637 tokens

helicone AGENTS.md

AGENTS.md instructions for Helicone/helicone, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

Helicone/helicone · 791 tokens

AstrBot copilot-instructions.md

Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).

AstrBotDevs/AstrBot · 736 tokens