twist-ai: Instructions file for Codex

AGENTS.md

twist-ai AGENTS.md is an instructions file for Codex, OpenCode from Doist/twist-ai. It costs 419 tokens per session, scanned A, original, MIT.

Project-specific instructions for developing Twist AI’s MCP server, a service that lets language models call tools. They describe where new tools must be registered and what testing and documentation they require.

In plain words
What is it for?
Use them when adding or changing MCP tools in the Twist AI project. They cover tool files, registration points, parameter tests, build and type checks, documentation, and direct tool execution.
Why use it?
They reduce the chance that a new tool is registered in one place but missed in another, or shipped without the expected tests and documentation.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Doist/twist-ai's own configuration. It tells Codex and OpenCode how to work on twist-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything twist-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Doist/twist-ai. 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/Doist/twist-ai/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Doist/twist-ai

Made for: Codex, OpenCode.

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.

agentmods badge for twist-ai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/doist/twist-ai/agents-md/github.svg)](https://agentmods.dev/instructions/doist/twist-ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/doist/twist-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/doist/twist-ai/agents-md/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.

agentmods 80×15 button for twist-ai AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/doist/twist-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/doist/twist-ai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 419 This file is loaded in full into every session.
When invoked 419 The same file — it is already loaded in full.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00419 $0.00419
Opus 5.5 $0.00168 $0.00168
Sonnet 5.5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 2mo ago against content hash fde59a0404a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

twist-ai 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 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.

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.

AGENTS.md · 52 lines

What it actually says

Twist AI MCP Server - Development Guidelines

Adding a New Tool

When adding a new tool, it must be registered in all of these locations:

  1. src/utils/tool-names.ts — add tool name constant
  2. src/tools/<tool-name>.ts — create tool definition
  3. src/mcp-server.ts — import, register with registerTool(), and add to LLM instructions string
  4. src/index.ts — import and add to both the tools object and the named exports
  5. scripts/run-tool.ts — import and add to the tools record
  6. src/tools/__tests__/tool-annotations.test.ts — add annotation expectation entry
  7. src/tools/__tests__/<tool-name>.test.ts — create test file

Testing Requirements

When adding new tool parameters:

  1. Add comprehensive test coverage for new fields
  2. Test setting values
  3. Test clearing values (if applicable)
  4. Verify build and type checking pass
  5. Run full test suite (all tests must pass)

Documentation Requirements

When adding new tool features:

  1. Update tool schema descriptions in the source file
  2. Update src/mcp-server.ts tool usage guidelines
  3. Add tests demonstrating the feature
  4. Include examples in descriptions where helpful

Running Tools Directly

Use scripts/run-tool.ts to execute any tool without the MCP server:

npx tsx scripts/run-tool.ts <tool-name> '<json-args>'
npx tsx scripts/run-tool.ts --list  # list all tools

Examples:

npx tsx scripts/run-tool.ts user-info '{}'
npx tsx scripts/run-tool.ts search-content '{"query":"project update"}'
npx tsx scripts/run-tool.ts fetch-inbox '{"workspaceId":12345}'

Requires TWIST_API_KEY in .env (and optionally TWIST_BASE_URL).

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. 2mo ago First seen · 52 lines · 419 tokens per session scan A fde59a0404a0

Subscribe to this mod's changes

twist-ai AGENTS.md is an instructions file published in the GitHub repository Doist/twist-ai (3 stars, last pushed yesterday), licensed MIT. It adds 419 tokens to every session, about $0.0017 per session on Opus 5.5. 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 2026-08-31.

Related

twist-ai AGENTS.md compared with instructions from other repositories

twist-ai AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
twist-ai AGENTS.mdDoist/twist-aiInstructions file3yesterdayMITA419Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot