agentmods.dev

AKS-Lab-GitHubCopilot: Command for GitHub Copilot

.github/prompts/feature-from-issue.prompt.md

feature-from-issue is a command for GitHub Copilot from microsoft/AKS-Lab-GitHubCopilot. It costs 24 tokens per session (748 once invoked), scanned A, original, MIT.

A staged workflow that turns a GitHub issue or feature description into a reviewed, tested, and deployed pull request. It hands each phase to a specialist agent, stopping for human approval between phases.

In plain words
What is it for?
Use it to write a specification, coordinate domain and infrastructure changes, add unit and integration tests, run local verification, and prepare a deployed pull request.
Why use it?
It gives a large feature request a defined path from requirements to implementation, tests, local checks, and deployment instead of mixing all those jobs together.

Command for GitHub Copilot ✓ vendor

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: mentions AGENTS.md.

This is microsoft/AKS-Lab-GitHubCopilot's own configuration. It tells GitHub Copilot how to work on AKS-Lab-GitHubCopilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AKS-Lab-GitHubCopilot configures →

not rated 10repo 8d ago A scan 24 tokens original MIT
View source ↗ microsoft/AKS-Lab-GitHubCopilot
About the project

ZavaShop on AKS and Azure Container Apps is a hands-on lab for delivering a multi-agent retail supply-chain application from requirements through deployment. It demonstrates a team of six GitHub Copilot custom coding agents working across specifications, application code, MCP servers, tests, infrastructure, and CI. The catalogue entries define the agents, skills, and instructions used in that workflow.

microsoft/AKS-Lab-GitHubCopilot · 10 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/AKS-Lab-GitHubCopilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/microsoft/AKS-Lab-GitHubCopilot/main/.github/prompts/feature-from-issue.prompt.md
Clone the repo
git clone --depth 1 https://github.com/microsoft/AKS-Lab-GitHubCopilot

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for feature-from-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/microsoft/aks-lab-githubcopilot/feature-from-issue/github.svg)](https://agentmods.dev/commands/microsoft/aks-lab-githubcopilot/feature-from-issue)
Your own site
<a href="https://agentmods.dev/commands/microsoft/aks-lab-githubcopilot/feature-from-issue"><img src="https://agentmods.dev/badge/commands/microsoft/aks-lab-githubcopilot/feature-from-issue/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.

agentmods 80×15 button for feature-from-issue

Your own site · 80×15
<a href="https://agentmods.dev/commands/microsoft/aks-lab-githubcopilot/feature-from-issue"><img src="https://agentmods.dev/badge/commands/microsoft/aks-lab-githubcopilot/feature-from-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 748 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00748
Opus 5.5 $0.00010 $0.00299
Sonnet 5.5 $0.00005 $0.00150
Haiku 4.5 $0.00002 $0.00075

Measured 1mo ago against content hash beffa4da4b83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

feature-from-issue 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 1mo 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.

.github/prompts/feature-from-issue.prompt.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow: Feature from Issue → Deployed PR

You are running the full ZavaShop delivery loop for one GitHub issue. You will invoke a different agent at each phase. At every handoff, stop and ask the human to /-invocation the next agent — do not silently impersonate other agents.

Inputs

The user gives you either:

  • a GitHub issue number (use githubRepo tool to fetch), or
  • a freeform feature description.

Phases (you must say where you are at all times)

Phase 1 — Specification

Mode: requirements-analyst Produce specs/<slug>.md. Stop. Ask user to review.

Phase 2 — Domain implementation

For each Affected agent from the spec, in dependency order:

  • If MCP server changes are needed → mode: mcp-builder.
  • Then → mode: agent-builder for each specialist.
  • Then → mode: orchestrator-architect if the workflow topology or shared modules change.

Each sub-phase produces one PR-sized diff. Stop after each.

Phase 3 — Tests

Mode: test-author Produce unit + integration + eval coverage for every acceptance criterion. Must reach pytest --cov-fail-under=80.

Phase 4 — Local verification

Run:

docker compose up -d --build
ZAVA_ENDPOINT=http://localhost:8000 uv run python -m tests.evals.run_evals

If any eval fails, return to Phase 2 with the failing case as input.

Phase 5 — PR

Push a feature branch and open a PR titled feat: <slug>. Body must:

  • Link the issue.
  • Quote the Acceptance criteria from the spec.
  • Paste the uv run poe check and eval output.
  • List the agents used at each phase.

Phase 6 — Deploy

After merge, mode: deploy-engineer. Run the full rollout sequence (see .github/agents/deploy-engineer.agent.md). Smoke /plan against the AKS LB. Run evals against the cloud endpoint.

Rules

  1. Never skip a phase. Never combine phases in a single turn.
  2. If a phase fails, do not move forward — return to the failing phase's mode.
  3. Always invoke the agent that owns the path you are about to edit. Each agent carries the right tools, skills, and refusal rules.
  4. Every commit message starts with feat:, fix:, chore(infra):, or test: per AGENTS.md §7.
  5. The Copilot SDK model is gpt-5.5. Always.

Read the full file on GitHub · 74 lines

Changes

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.

  1. 1mo ago First seen · 74 lines · 24 tokens per session scan A beffa4da4b83

Subscribe to this mod's changes

feature-from-issue is a command published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (10 stars, last pushed 8d ago), licensed MIT. It adds 24 tokens to every session and 748 once invoked, about $0.0001 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 2026-09-19.

PlanningProject management
Related

feature-from-issue compared with commands from other repositories

feature-from-issue next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
feature-from-issuemicrosoft/AKS-Lab-GitHubCopilotCommand108d agoMITA24GitHub Copilot
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code
convergegithub/spec-kitCommand148kyesterdayMITA35Claude Code
implementgithub/spec-kitCommand148kyesterdayMITA14Claude Code