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/awslabs/agent-plugins/copilot-instructionsgit clone --depth 1 https://github.com/awslabs/agent-pluginsWhat 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 | $0.00586 | $0.00586 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
agent-plugins 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 2d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Custom Instructions for Agent Plugins for AWS
Project Overview
This repository contains Agent Plugins for AWS that equip AI coding agents with the skills to help architects, deploy, and operate on AWS. Plugins include deploy-on-aws (recommendations, cost estimates, and Infrastructure as Code generation) and amazon-location-service (maps, geocoding, routing, and geospatial features).
Technology Stack
- Language: Primarily TypeScript/JavaScript
- Framework: Claude Code plugins
- Cloud Platform: AWS
- Infrastructure as Code: CDK and CloudFormation
- Tools: MCP Servers (awsknowledge, awspricing, aws-iac-mcp)
Code Organization
/plugins- Plugin implementations/schemas- Data schemas and type definitions/tools- Utility tools and helpers/.github- GitHub workflows and configuration- Root files: Configuration for linting (markdownlint, semgrep), security (gitleaks), and formatting (dprint)
Development Practices
- Code Quality: Uses pre-commit hooks, semgrep for security analysis, and gitleaks for secret detection
- Documentation: Comprehensive guides including DEVELOPMENT_GUIDE.md, CONTRIBUTING.md, TROUBLESHOOTING.md
- Testing: Follow existing test patterns in the codebase
- Formatting: Use dprint for code formatting consistency
- Commit Signoff: Web commit signoff required (git commit -S flag)
Plugin Development Guidelines
- Follow the workflow pattern: Analyze → Recommend → Estimate → Generate → Deploy
- MCP Servers provide: AWS documentation, pricing data, and IaC best practices
- Skill triggers should be intuitive natural language phrases users would say
- Always include cost estimation and confirmation steps before deployment
- Generate infrastructure code with explanations and best practices
Important Reminders for Copilot
- AWS Best Practices: Recommend services aligned with AWS Well-Architected Framework
- Cost Awareness: Always estimate and display costs to users
- User Confirmation: Never deploy without explicit user confirmation
- Multi-Agent Support: Currently supports Claude Code; consider extensibility
- Security: Follow AWS security best practices and principle of least privilege
- Documentation: Provide clear explanations for architectural recommendations
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.
- 2d ago First seen · 58 lines · 586 tokens per session scan A adf8ec767e64
agent-plugins copilot-instructions.md is an instructions file published in the GitHub repository awslabs/agent-plugins (876 stars, last pushed 6d ago), licensed Apache-2.0. It adds 586 tokens to every session, about $0.0029 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
sample-autonomous-cloud-coding-agents AGENTS.md
AGENTS.md instructions for aws-samples/sample-autonomous-cloud-coding-agents, covering agents.md, your role, commands (run these), git workflow and where to make changes.
forge AGENTS.md
Instructions for automagik-dev/forge, covering genie agent framework, core identity, core purpose, task context (auto-loaded) and product documentation.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
agentic-workflow CLAUDE.md
Instructions for gtrabanco/agentic-workflow, covering claude.md, repository layout, working rules, authoring a skill and hand off, don't compose across a model/effort boundary.
skills CLAUDE.md
Instructions for capawesome-team/skills, covering claude.md, project overview, repository structure, skill.md format and writing agent-optimized skills.
agent-skills AGENTS.md
Instructions for powabase-ai/agent-skills, covering agents.md, repository structure, prerequisites & commands, writing skill.md files and frontmatter (required).