Borrowing it
Nothing to install: this file belongs to unknowlei/minimax-h3-opencode-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/unknowlei/minimax-h3-opencode-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/unknowlei/minimax-h3-opencode-skillsWrote 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.
[](https://agentmods.dev/instructions/unknowlei/minimax-h3-opencode-skills/agents-md)<a href="https://agentmods.dev/instructions/unknowlei/minimax-h3-opencode-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/unknowlei/minimax-h3-opencode-skills/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.
<a href="https://agentmods.dev/instructions/unknowlei/minimax-h3-opencode-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/unknowlei/minimax-h3-opencode-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00530 | $0.00530 |
| Opus 5 | $0.00265 | $0.00265 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
minimax-h3-opencode-skills 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 9d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Installation Contract
When a user gives you this repository URL and asks you to install it, perform the installation instead of only explaining commands.
Install Target
Install globally for OpenCode unless the user explicitly requests project-local installation.
- Windows global target:
$HOME\.config\opencode\skills - Linux/macOS global target:
$HOME/.config/opencode/skills - Project-local target:
<project>/.opencode/skills
Required Installation
- Clone or download this repository to a temporary directory.
- Locate every directory under
skills/that containsSKILL.md. - Before replacing an existing same-name skill, create a timestamped backup beside it. Do not delete unrelated skills.
- Copy all six bundled skill directories into the selected OpenCode skills target.
- Install the official
h3-prompt-writingdependency from:https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills/h3-prompt-writing - Prefer a shallow sparse clone of
https://github.com/MiniMax-AI/MiniMax-H3.gitrestricted toskills/h3-prompt-writing, then copy that directory to<target>/h3-prompt-writing. - Confirm that these seven files exist:
<target>/h3-prompt-writing/SKILL.md<target>/minimax-h3-creative-director/SKILL.md<target>/minimax-h3-multishot-planner/SKILL.md<target>/minimax-h3-text-video-prompt/SKILL.md<target>/minimax-h3-reference-video-prompt/SKILL.md<target>/minimax-h3-keyframe-video-prompt/SKILL.md<target>/minimax-h3-prompt-reviewer/SKILL.md
- If
opencodeis available, runopencode debug skilland verify that all seven names are discovered. - Report the exact target directory, installed skill names, backup paths, and validation result.
- Tell the user to start a new OpenCode session so previously loaded skill content is not reused.
Safety
- Preserve unrelated files and skills.
- Never recursively delete the complete OpenCode skills directory.
- Treat the official dependency as upstream content; fetch it from the MiniMax repository rather than substituting a reconstructed copy.
- If network access prevents fetching the official dependency, install the six bundled skills, clearly report the missing dependency, and provide the exact retry step.
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.
- 9d ago First seen · 40 lines · 530 tokens per session scan A 8394d225a313
minimax-h3-opencode-skills AGENTS.md is an instructions file published in the GitHub repository unknowlei/minimax-h3-opencode-skills (111 stars, last pushed 1mo ago), licensed MIT. It adds 530 tokens to every session, about $0.0027 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.