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/kasuken/github-copilot-superpowers/copilot-agentgit clone --depth 1 https://github.com/kasuken/github-copilot-superpowersWhat 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 | $0.02285 | $0.02285 |
| Opus 5 | $0.01143 | $0.01143 |
| Sonnet 5 | $0.00457 | $0.00457 |
| Haiku 4.5 | $0.00229 | $0.00229 |
Grade A, and why
github-copilot-superpowers copilot-agent.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 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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Agent Instructions
🎯 INSTRUCTION HIERARCHY
⚠️ subagents.instructions.md is the SINGLE SOURCE OF TRUTH (SSOT) and has HIGHEST PRIORITY.
Priority order when conflicts occur:
- subagents.instructions.md (SSOT) - Orchestrator delegation rules, absolute restrictions, Context Package contract
- copilot-agent.instructions.md (this file) - Developer runbook & quality standards
- task-direction-approval.instructions.md - User approval for direction changes
- taming-copilot.instructions.md - User-facing output format
- Other domain-specific instructions
Core principle: Delegation > Direct Execution
📋 Execution Order vs Priority
Priority (INSTRUCTION HIERARCHY) = Which rule wins when there's a conflict Execution Order = What happens first in the workflow sequence
Execution Order (Workflow Sequence)
- Sequential-thinking: Analyze problem (orchestrator executes directly - this is thinking, not I/O)
- SSOT rules apply: All investigation I/O → delegate to subagent
- Terminal verification: build/test/lint (orchestrator executes directly)
Note: Sequential-thinking is a thinking tool, not I/O. It runs BEFORE delegation rules apply.
⛔ MANDATORY RESPONSE TEMPLATE (EVERY REQUEST)
Execution order: Invoke Sequential-thinking → Display this template. See "DEVELOPER RUNBOOK - 6 PHASES" below for details.
⚠️ INTEGRITY CHECK: The status below MUST reflect ACTUAL delegations/tool calls made in THIS response. Marking ✅ without proper execution is a CRITICAL VIOLATION equivalent to lying to the user.
EVERY response MUST start with:
🛠️ **PREFLIGHT CHECK**
- [✅/❌] Sequential-thinking MCP: {Executed by orchestrator - reason}
- [✅/❌] **SSOT Tool Gate**: Check SSOT before every tool call
- [✅/⏭️] Delegation status: {Yes - task description / Skip - reason}
- [✅/⏭️] Serena MCP: {Delegated via subagent / Skip - reason} [Context Package: .copilot/docs/X.md]
- [✅/⏭️] Context7 MCP: {Delegated via subagent / Skip - reason} [Context Package: .copilot/docs/X.md]
- [✅/⏭️] GitHub MCP: {Delegated via subagent / Skip - reason} [Context Package: .copilot/docs/X.md]
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 · 227 lines · 2,285 tokens per session scan A cb30c0a8f32d
github-copilot-superpowers copilot-agent.instructions.md is an instructions file published in the GitHub repository kasuken/github-copilot-superpowers (16 stars, last pushed 6mo ago), licensed MIT. It adds 2,285 tokens to every session, about $0.0114 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
Project Guidelines
VS Code extension project guidelines for GitHub Copilot Insights. Covers project shape, code style, VS Code extension rules, build and test, and repository discipline.
Repo Validation Workflow
Use when: changing, validating, testing, or reviewing this VS Code extension repository. Covers npm compile, lint, test harness, Electron test caveats, and build output.
copilot-guide copilot-instructions.md
Instructions for nishanil/copilot-guide, covering copilot-guide — copilot instructions, what this repo is, contribution conventions, style rules and what not to change.
pt-ai-context platform-group.instructions.md
Instructions for osinfra-io/pt-ai-context, covering platform group instructions, ignored directories, workspace overview, platform architecture and code quality principles.
Copilot-Skills copilot-instructions.md
Instructions for TheSethRose/Copilot-Skills, covering copilot instructions, find what you're looking for, get file context before editing, understand related code and orchestration default.
Copilot-Skills kraken-analyst.instructions.md
Instructions for TheSethRose/Copilot-Skills, covering kraken analyst instructions, core capabilities, public api features (no authentication required), private api features (requires api keys) and default behaviors.