microsoft/waza is a Go command-line tool for building and evaluating AI agent skills through test suites, benchmarks, and model comparisons. It is for developers who need to measure and improve how reliably agent skills work. The catalogue entries are Waza's own skills, instructions, agent, and MCP integration.
Borrowing it
Nothing to install: this file belongs to microsoft/waza. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/waza/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/microsoft/wazaWrote 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/microsoft/waza/copilot-instructions)<a href="https://agentmods.dev/instructions/microsoft/waza/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/waza/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/microsoft/waza/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/waza/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02105 | $0.02105 |
| Opus 5.5 | $0.00842 | $0.00842 |
| Sonnet 5.5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
waza 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 5d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository-wide Copilot Instructions
Read AGENTS.md before changing this repository. Its review-derived standards, required checks, and completion gates apply to ordinary Copilot work as well as Squad work. Keep detailed standards there; this file is the execution checklist, not a second specification.
Before handing off any change
- Trace changed values through every affected consumer: native loaders, eval/task/checkpoint schemas, preflight, execution/resume, cache keys, run/regrade serialization, API, UI, exports, and documentation. Reuse shared effective-config/path/tool-name helpers; check overrides and disabled paths.
- Preserve omitted/null/empty/zero/false distinctions and intentional legacy compatibility. Keep artifact reader defaults and writer versions separate. Do not invent missing scores, billing, provenance, or verified evidence.
- Keep offline/static validation free of model, subprocess, ambient-config, and external-schema side effects. Aggregate independent diagnostics; unresolved prerequisites must not hide invalid configuration. Failures must propagate to final status/exit policy, not only an error message.
- For filesystem changes, test containment, symlink/parent replacement, exclusive creation, and write/close/cleanup failures. Retain owned handles for guarantees that require them; never delete competing/user-owned files or claim transaction, durability, or platform support that is not implemented.
- Add a regression through the production caller, not just the helper. Prove fixtures/setup exercise the intended case and assert the actual contract, including negative and alternative-valid cases. Historical compatibility needs a frozen oracle; two matching new outputs prove only repeatability.
- Review dependency updates for caller API changes, peer/engine minimums, coordinated modules, CI/deploy runtimes, lockfiles, and embedded SDK/CLI bundles. A package version bump is not automatically integration-safe.
- Run the applicable checks in
AGENTS.mdand record exact commands/results against the tested head/platform. Missing tools, skipped jobs/test families, cross-compilation, and helper-only smoke tests are not execution evidence. Instruction-only prose does not require Go/frontend builds. - Read review bodies and conversation comments as well as inline threads, including Previously missed and suppressed findings. Do not equate "0 open findings" or green CI with completed review. Verify fixes before resolving threads; document demonstrated false positives or agreed deferrals.
- Keep the PR template, scope, docs/examples, and current generated output in sync with the full final diff, including stacked changes. Recheck after the last source/base update; obtain independent approval and required checks without silently bypassing branch protection.
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.
- 5d ago Changed · +66 lines · +873 tokens per session scan C → A 5d492a2b0b17
- 1mo ago First seen · 127 lines · 1,232 tokens per session scan C f3646cef4eaa
waza copilot-instructions.md is an instructions file published in the GitHub repository microsoft/waza (1,424 stars, last pushed today), licensed MIT. It adds 2,105 tokens to every session, about $0.0084 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.