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/rios0rios0/guide/copilot-instructionsgit clone --depth 1 https://github.com/rios0rios0/guideWrote 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/rios0rios0/guide/copilot-instructions)<a href="https://agentmods.dev/instructions/rios0rios0/guide/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/rios0rios0/guide/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 | $0.03009 | $0.03009 |
| Opus 5 | $0.01504 | $0.01504 |
| Sonnet 5 | $0.00602 | $0.00602 |
| Haiku 4.5 | $0.00301 | $0.00301 |
Grade A, and why
guide 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 today.
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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Development Guide Repository
This is a comprehensive documentation repository containing software development standards, best practices, and guidelines organized across multiple categories including Code Style, Life Cycle processes, and practical Cookbooks.
Always reference these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.
Working Effectively
Quick Setup and Validation
- Validate repository structure:
ls -la README.md Home.md .editorconfig .github/workflows/update-wiki.yml - Build the wiki sync tool:
cd .github/workflows/update-wiki go build -o update-wiki ./...- Build time: ~1 second. NEVER CANCEL. Set timeout to 30+ seconds for safety.
- Build the AI rules generator:
cd .github/workflows/generate-ai-rules go build -o generate-ai-rules ./... - Run basic validation:
find . -name "*.md" | wc -l(should show 80+ Markdown files)
Core Build Process
The repository has two Go-based tools under .github/workflows/:
update-wiki (Go 1.26.2)
Syncs documentation to GitHub Wiki:
- Build location:
.github/workflows/update-wiki/ - Build command:
go build -o update-wiki ./... - Expected build time: ~1 second
generate-ai-rules (Go 1.26.2)
Generates AI assistant rule files for Claude Code, Cursor, Codex, and GitHub Copilot from the guide's own documentation.
- Build location:
.github/workflows/generate-ai-rules/ - Build command:
go build -o generate-ai-rules ./... - Run:
./generate-ai-rules - Expected build time: ~1 second
NEVER CANCEL BUILD COMMANDS - Even though builds are fast (~1s), set timeouts of 30+ seconds.
GitHub Actions Workflows
Six workflows are defined under .github/workflows/:
| File | Trigger | Purpose |
|---|---|---|
update-wiki.yml |
Push to main, manual dispatch |
Syncs docs to GitHub Wiki |
generate-ai-rules.yaml |
Push to main (docs paths), manual dispatch |
Regenerates AI rules on generated branch |
sync-docs.yaml |
Pull request (any .md change) |
Validates TOC sync across README.md, Home.md, _Sidebar.md |
claude-review.yaml |
PR opened/synchronize/ready_for_review/reopened | AI-assisted PR review; calls a reusable workflow in rios0rios0/pipelines |
claude-mention.yaml |
Issue/PR comments, issue events, PR reviews | Claude Code automation for issues and PRs; calls a reusable workflow in rios0rios0/pipelines |
release.yaml |
Push to main |
Automated release via reusable workflow |
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.
- today Changed · +26 tokens per session dca074077463
- 3d ago First seen · 255 lines · 2,983 tokens per session scan A 61c4f0b752ff
guide copilot-instructions.md is an instructions file published in the GitHub repository rios0rios0/guide (2 stars, last pushed today), licensed MIT. It adds 3,009 tokens to every session, about $0.0150 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.
Other instructions, from other repositories
neat CLAUDE.md
Instructions for neat-technologies/neat, covering claude.md, binding rules, what neat is, what success looks like and conventions.
open-claude-code-skills CLAUDE.md
Instructions for xcodethink/open-claude-code-skills, covering 全局开发规则, ⭐ 决策自主 + 激活反射 + 形态ui (始终生效, 2026-06-28), ⭐ 每回合进度+性质汇报 (始终生效, 2026-07-29, 所有项目所有对话), ⭐ 完整规范全景图 (2026-05-30 v1.2 收敛版, 始终生效) and ★ layer b 任务执行纪律 (tep) — 防遗漏/防跑偏/防无限循环.
claude-multi-agent-architecture AGENTS.md
Instructions for mnzralee/claude-multi-agent-architecture, covering agents.md - cross-tool agent configuration, project overview, conventions, code style (illustrative defaults; adapt to your stack) and git.
Agent-Guidance-Python AGENTS.md
Instructions for JunMystery/Agent-Guidance-Python, covering agents.md, token saving — built-in optimization, critical — tool rules (read first), agent guidance mcp — tool selection priority and standard workflow lifecycle & feedback loops.
codingbuddy nestjs.instructions.md
Instructions for JeremyDev87/codingbuddy, covering nestjs mcp server code review, module structure, mcp protocol and dependency injection.
claude-skills CLAUDE.md
Instructions for 0xMassi/claude-skills, covering development partner, behavior, communication, domain thinking and code standards.