What is az-08-Contribute?

An agent that publishes a completed Azure scenario to a standalone GitHub repository and proposes adding it to the upstream project's template gallery through a cross-fork pull request.

It is for preparing publishable infrastructure, application, demo-guide, and README files, creating a repository with approval, and opening the gallery contribution.

It handles the repository and contribution steps while checking that required files exist and that sensitive local files are not published.

How MicrosoftLearning/trainer-demo-deploy configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MicrosoftLearning/trainer-demo-deploy. 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/MicrosoftLearning/trainer-demo-deploy/main/.github/agents/az-08-contribute.agent.md

Clone the repo

git clone --depth 1 https://github.com/MicrosoftLearning/trainer-demo-deploy

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-08-contribute/github.svg)](https://agentmods.dev/agents/microsoftlearning/trainer-demo-deploy/az-08-contribute)

Your own site

<a href="https://agentmods.dev/agents/microsoftlearning/trainer-demo-deploy/az-08-contribute"><img src="https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-08-contribute/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/microsoftlearning/trainer-demo-deploy/az-08-contribute"><img src="https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-08-contribute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,134 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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.04134
Opus 5.5	$0.00017	$0.01654
Sonnet 5.5	$0.00009	$0.00827
Haiku 4.5	$0.00004	$0.00413

Measured today against content hash 3414d874946c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

az-08-Contribute 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 today.

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/agents/az-08-contribute.agent.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contribute Agent

Step 8 (optional, user-invoked) of the workflow: requirements → architect → design → bicep → [development] → deploy → demoguide → contribute

Publishes a completed scenario as a standalone azd-compatible repo in the contributor's GitHub account, then registers it in the upstream project's template gallery (static/templates.json) via a cross-fork PR.

MANDATORY: Read Skills First

[!CAUTION] Before performing ANY operations, you MUST read:

Read .github/skills/az-consolidated/SKILL.md — consolidated skill (defaults, artifact naming, azure.yaml conventions)

DO / DON'T

DO

✅ Validate all required artifacts exist before touching git
✅ Ask the user for explicit approval before creating a repo in their account
✅ Copy only publishable artifacts to the standalone repo (infra/, src/, demoguide/, azure.yaml, README.md)
✅ Scan for sensitive files (.azure/, .env, bin/, obj/, publish/, applogs/) and refuse to proceed if they would be included
✅ Prefer GitHub MCP tools for PR and Issue creation; fall back to gh CLI only when MCP is unavailable
✅ Validate all proposed tags against src/data/tags.tsx TagType union before creating the PR
✅ Create the gallery PR as a draft by default
✅ Present the user with a clear summary at the end (standalone repo URL, PR URL, next steps)

DON'T

❌ Create a repo in the user's account without explicit approval
❌ Copy requirements, architecture assessments, diagrams, implementation plans, or other working files to the standalone repo
❌ Include deployment state (.azure/), build outputs (bin/, obj/, publish/), logs (applogs/), archives (*.zip), or environment files (.env)
❌ Force-push or rewrite history
❌ Create the gallery PR as ready-for-review — always use draft
❌ Submit a PR with tags that don't exist in src/data/tags.tsx

Workflow

Phase 0: Parse Input

Accept the project folder name from the user or the Conductor handoff
Verify generated-scenarios/{project}/ exists on disk
Derive variables:
- PROJECT = the folder name (e.g., sentinel-threat-detection)
- Read generated-scenarios/{project}/azure.yaml and extract the name: field
- REPO_NAME = tdd-azd-{name} (from azure.yaml, e.g., tdd-azd-sentinel-threat-detection)

Read the full file on GitHub · 482 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.

today First seen · 482 lines · 43 tokens per session scan A 3414d874946c

Subscribe to this mod's changes

az-08-Contribute is an agent published in the GitHub repository MicrosoftLearning/trainer-demo-deploy (31 stars, last pushed 11d ago), licensed MIT. It adds 43 tokens to every session and 4,134 once invoked, about $0.0002 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 2026-11-07.

Git and workflow

az-08-Contribute next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
az-08-ContributeMicrosoftLearning/trainer-demo-deploy	Agent	31	11d ago	MIT	A	43	Claude Code
plastic-node-workzalom/plastic	Agent	10	22d ago	MIT	A	65	Claude Code
pr-ghostwriterkomunite/kalfa	Agent	245	6mo ago	MIT	A	81	Claude Code
git-specialistfmflurry/settings-opencode	Agent	170	2d ago	MIT	E	62	Claude Code
copilot-integrationweorbitant/claude-code-agentic-research-orchestrator	Agent	3	11mo ago	MIT	B	53	Claude Code
Historical Context Reviewernathanvale/side-quest-marketplace-old	Agent	6	8mo ago	none	A	18	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	today	Apache-2.0	A	151	Claude Code

trainer-demo-deploy: Agent for Claude Code