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/shangyankeji/super-dev/copilot-instructionsgit clone --depth 1 https://github.com/shangyankeji/super-devWrote 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/shangyankeji/super-dev/copilot-instructions)<a href="https://agentmods.dev/instructions/shangyankeji/super-dev/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shangyankeji/super-dev/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00828 | $0.00828 |
| Opus 5 | $0.00414 | $0.00414 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
super-dev 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 3d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Super Dev IDE Rules (vscode-copilot)
Positioning
- Super Dev is a host-level workflow governor, not an LLM platform.
- Keep using the host's model capabilities; do not expect extra model APIs from Super Dev.
- The host remains responsible for actual coding, tool execution, and file changes.
Runtime Contract
- Treat Super Dev as the local Python workflow tool plus this host rule file, not as a separate coding engine.
- When the user says
/super-dev ...,super-dev: ..., orsuper-dev：..., immediately enter the Super Dev pipeline. - Use host-native browse/search/web for research and host-native editing/terminal for implementation.
- Use local
super-devcommands when you need to generate or refresh documents, spec artifacts, quality reports, or delivery manifests.
First-Response Contract
- On the first reply after
/super-dev ...,super-dev: ..., orsuper-dev：..., explicitly state that Super Dev pipeline mode is now active rather than normal chat mode. - Before the first reply, read
.super-dev/WORKFLOW.mdandoutput/*-bootstrap.mdwhen present, and treat them as the explicit bootstrap contract for this repository. - The first reply must explicitly state that the current phase is
research, and that you will readknowledge/plusoutput/knowledge-cache/*-knowledge-bundle.jsonfirst when available before similar-product research. - The first reply must explicitly state the next sequence: research -> three core documents -> wait for user confirmation -> Spec / tasks -> frontend first with runtime verification -> backend / tests / delivery.
- The first reply must explicitly promise that you will stop after the three core documents and wait for approval before creating Spec or writing code.
Local Knowledge Contract
- Read relevant files under
knowledge/before drafting the three core documents. - If
output/knowledge-cache/*-knowledge-bundle.jsonexists, read it first and inherit its matched local knowledge into PRD, architecture, UIUX, Spec, and execution. - Treat local knowledge hits as hard project constraints, especially for standards, anti-patterns, checklists, and scenario packs.
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.
- 3d ago First seen · 52 lines · 828 tokens per session scan A 905a536272b5
super-dev copilot-instructions.md is an instructions file published in the GitHub repository shangyankeji/super-dev (274 stars, last pushed 2mo ago), licensed MIT. It adds 828 tokens to every session, about $0.0041 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
BitFun AGENTS.md
BitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.
MonkeyCode AGENTS.md
AGENTS.md instructions for chaitin/MonkeyCode, covering git 提交与推送规则, ohmydesign-tmp 例外, 启动 monkeycode debug app（开发与测试）, 1. 编译 agent（必须用最新功能分支代码） and 2. 启动 debug app（ui-next 热加载）.
coco-workflow CLAUDE.md
Instructions for skullninja/coco-workflow, covering claude.md -- coco, project overview, architecture, key files and tracker (lib/tracker.sh).
ai-auto-work CLAUDE.md
Claude Code instructions for chaohong-ai/ai-auto-work, covering gamemaker - ai native 游戏创作平台, 项目简介, ai 工作目录约定 and 按需加载（不默认装载）.
agent-feed AGENTS.md
Instructions for fqmyysjjd/agent-feed, covering agent-feed ai development instructions, startup policy, rule priority, responsibility boundary and mandatory gates.
agent-feed CLAUDE.md
Instructions for fqmyysjjd/agent-feed, a project described as: Turn AI coding chats into a source-controlled workflow: AGENTS.md, rules, skills, verification gates, and adapters for Codex, Claude Code, and Cursor.