What is vthink-agent-toolkit AGENTS.md?

A toolkit of reusable instructions, AI roles, and workflows for coding assistants such as Claude Code, Cursor, Windsurf, and GitHub Copilot. It maps common development requests to the relevant skill or agent.

Organizing skills and agents, following repository-specific workflows, and finding the right instructions for tasks such as committing code or extending the toolkit.

It helps an assistant choose the right procedure and project guidance for a task across different coding tools.

vthink-agent-toolkit AGENTS.md — Instructions file by vthinkdeveloper

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/vthinkdeveloper/vthink-agent-toolkit/agents-md

Clone the repo

git clone --depth 1 https://github.com/vthinkdeveloper/vthink-agent-toolkit

Made for: Codex, OpenCode.

Per session 471 This file is loaded in full into every session.

When invoked 471 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.

Model	Per session	Once invoked
Fable 5	$0.00471	$0.00471
Opus 5	$0.00235	$0.00235
Sonnet 5	$0.00094	$0.00094
Haiku 4.5	$0.00047	$0.00047

Measured yesterday against content hash 41b1790c8736, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vthink-agent-toolkit 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 yesterday.

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 · 44 lines

What it actually says

AGENTS.md

This file provides guidance to AI coding agents (Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, etc.) when working with code in this repository.

Repository Overview

vthink-agent-toolkit is a collection of production-grade skills, agents, and workflows for AI coding agents. Skills and agents are plain natural-language procedural instructions — they work in any agent runtime that can read markdown files.

Structure

skills/<skill-name>/SKILL.md     # Skills — invoke by describing what you want
agents/<agent-name>/AGENT.md     # Agents — specialised sub-agents with a defined role
.claude/commands/                # Slash commands (Claude Code)
platforms/claude-code/           # Claude Code-specific: hooks, settings-templates, mcp, rules
playbooks/                       # Recipes for combining skills and agents
output-styles/                   # Response style files controlling tone and formatting

When Working in This Repo

If a task matches a skill, invoke it. Skills are located at skills/<skill-name>/SKILL.md.

Intent → Skill Mapping

What you're doing	Use this skill
Commit and push changes	`commit-push` or `ship`
Commit, push, and open a PR	`commit-push-pr`
Just need a commit message	`give-me-a-commit-message`
Check code against conventions	`conventions-check`
Write BDD / Gherkin scenarios	`bdd-gherkin`
Generate a QA test plan for a PR	`qa-guide`
Scaffold a CRUD endpoint	`generate-endpoint`
Anonymize a prompt for external tools	`anonymize-prompt`

Contribution Rules

All skill/agent files must have name and description frontmatter only
Skills go in skills/<name>/SKILL.md, agents in agents/<name>/AGENT.md
Claude Code-specific assets (hooks, settings, MCP configs, rules) go in platforms/claude-code/
Update CATALOG.md after every addition
See CONTRIBUTING.md for full standards

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.

yesterday First seen · 44 lines · 471 tokens per session scan A 41b1790c8736

Subscribe to this mod's changes

vthink-agent-toolkit AGENTS.md is an instructions file published in the GitHub repository vthinkdeveloper/vthink-agent-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 471 tokens to every session, about $0.0024 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 2026-08-31.

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

vthink-agent-toolkit AGENTS.md