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/snapdragonpartners/maestro/copilot-instructionsgit clone --depth 1 https://github.com/SnapdragonPartners/maestroWrote 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/snapdragonpartners/maestro/copilot-instructions)<a href="https://agentmods.dev/instructions/snapdragonpartners/maestro/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/snapdragonpartners/maestro/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 | $0.00952 | $0.00952 |
| Opus 5 | $0.00476 | $0.00476 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
maestro 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Code Review Instructions
Review Philosophy
This is a Go-based multi-agent AI orchestrator. Reviews should focus on correctness, DRYness, and testability — not style or formatting. We have aggressive linters (golangci-lint, pre-commit hooks) that handle formatting, naming, and import ordering. Do not comment on those.
Refer to AGENTS.md at the repository root for the full coding guidelines and severity levels (P0/P1). The rules there are authoritative. Key highlights:
- Only block on P0 (bugs, crashes, data corruption, severe security) and P1 (clear guideline violations harming maintainability).
- Everything else is a suggestion or question.
- This is a single-user, locally run app — be pragmatic about security.
Spec Compliance Check
When a PR includes new or modified markdown files (especially under docs/), determine whether any of them are specification documents. Specs typically have titles like *_SPEC.md, contain sections such as "Acceptance Criteria", "Implementation Plan", "Design", or "Architecture", or describe features/behaviors to be built.
If the PR contains a spec document:
- Read the spec thoroughly and identify its acceptance criteria, design constraints, and expected behaviors.
- Cross-reference the spec against the code changes in the PR. Assess whether the implementation is faithful and complete relative to the spec.
- Flag any gaps: acceptance criteria not addressed, behaviors described in the spec but missing from the code, or code that contradicts the spec.
- Flag scope creep: code changes that go significantly beyond what the spec describes without justification.
If the PR modifies an existing spec, check whether the code already in the PR (or referenced by it) still aligns with the updated spec.
Correctness
- Look for logic errors, off-by-one mistakes, race conditions, and unhandled edge cases.
- Verify error handling: errors should not be silently dropped. Check that errors are wrapped with context (
fmt.Errorf("doing X: %w", err)). - Watch for the Go nil-interface gotcha: a concrete nil pointer assigned to an interface is non-nil. We use
reflect.ValueOf(e).IsNil()in places where this matters (seeisExecutorUsable()). LocalExec.Run()returnserr == nileven for non-zero exit codes. Always checkresult.ExitCoderather than relying onerr != nil.- Verify that any bare type assertion (
x.(T)) is justified. We preferSafeAssert(a generics-based helper) for safety and clarity — see AGENTS.md section 2.
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 · 64 lines · 952 tokens per session scan A 81cfe72b3bb8
maestro copilot-instructions.md is an instructions file published in the GitHub repository SnapdragonPartners/maestro (24 stars, last pushed 15d ago), licensed MIT. It adds 952 tokens to every session, about $0.0048 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
codeg AGENTS.md
AGENTS.md instructions for xintaofei/codeg, covering agents.md, 项目概述, 技术栈, 代码检查与测试(任务完成后进行必要的检查) and 前端.
claude-context CLAUDE.md
Claude Code instructions for zilliztech/claude-context, covering claude.md, monorepo layout, commands, tests and running the mcp server locally.
openase AGENTS.md
Instructions for PacificStudio/openase, covering workspace notes and environment.
mue-x CLAUDE.md
Instructions for KorroAi/mue-x, covering mue — self-evolving ai agent for claude code, what you are in mue mode, commands, mode behavior and auto-start.
chiplab AGENTS.md
Instructions for veecle/chiplab, covering agents.md, what is chiplab, 1. install / connect chiplab, 2. verify the connection and 3. pick the example for the board you want.
chiplab copilot-instructions.md
Instructions for veecle/chiplab: Agent instructions for this repository live in AGENTS.md at the repo root. Please read that file for repository conventions, available workflows, and guidelines.