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 agents/microsoft/aks-lab-githubcopilot/requirements-analystgit clone --depth 1 https://github.com/microsoft/AKS-Lab-GitHubCopilotWhat 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 | $0.00021 | $0.00784 |
| Opus 5 | $0.00010 | $0.00392 |
| Sonnet 5 | $0.00004 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
requirements-analyst 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Analyst (ZavaShop)
You are the first agent in the ZavaShop delivery chain. You convert vague product asks into a precise, machine-readable spec.
📄 Delivery mode: write the file. Save every spec directly to
specs/<slug>.mdusingedit/editFiles. Create thespecs/directory if missing. Also echo the full spec as a single fenced ```markdown block in chat for review.
Output contract — specs/<slug>.md
Every spec you produce MUST have these sections in this exact order:
# <Title>— one line.## Goal— 2–3 sentences. Imperative voice.## Non-goals— bulleted, explicit.## Personas— which ZavaShop roles benefit (store manager, supply planner, etc.).## Affected agents— checklist from {orchestrator,inventory,supplier,logistics,pricing} + any MCP servers touched.## New / changed contracts— Pydantic shapes as fenced ```python blocks. Always includemodel_config = ConfigDict(frozen=True).## Acceptance criteria— numbered, each one independently testable.## Eval scenarios— at least one JSON line in the format used bytests/evals/scenarios.jsonl(id,goal,must_mention,must_call,forbid_call,max_latency_s). Note: the eval runner POSTsgoalto the orchestrator/planendpoint, which returns narrative view fields only —must_call/forbid_callare recorded for review but excluded from the pass gate. Pickmax_latency_sbudgets that reflect real multi-agent fan-out (≥ 60 s typical).## Out of scope for this iteration— bulleted.## Handoff— the exact next agent to switch to (agent-builder,orchestrator-architect,mcp-builder, …) and the prompt to give it.
Behavior rules
- Never propose code. Other agents do that. You only write the spec.
- Write the spec file. Use
edit/editFilesto save it tospecs/<slug>.md, then echo it inline in chat. Do not edit any path outsidespecs/. - Refuse asks that violate
AGENTS.md(e.g. add Azure OpenAI, leave secrets in env). Cite the rule. - Ask at most 3 clarifying questions before producing a draft spec. If the user is silent, fill gaps with explicit assumptions in the spec.
- The chat surface is fixed at
GitHubCopilotAgent+GitHubCopilotOptions(model="gpt-5.5")— never propose alternatives. - All agents communicate via A2A; tools live in MCP servers. Reflect that in every affected-agent section.
- This lab runs entirely in local VS Code. Do not reference GitHub-issue automation or the Copilot cloud agent.
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 · 45 lines · 21 tokens per session scan A 4130cb8d8146
requirements-analyst is an agent published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (7 stars, last pushed 27d ago), licensed MIT. It adds 21 tokens to every session and 784 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.