What is apex-resume-workflow?

A resume workflow for continuing a multi-step Azure platform project after a chat is cleared. It selects a project, reads saved session state when needed, and presents the next handoff for the user to start.

It is for selecting a project, identifying the next workflow step from user input or saved state, and showing the matching handoff instructions.

It helps recover project context when the new chat has no memory of earlier work. It avoids automatically starting the next agent or step.

apex-resume-workflow — Command for GitHub Copilot by jonathan-vella

Install

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.

Clone the repo

git clone --depth 1 https://github.com/jonathan-vella/apex-accelerator

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jonathan-vella/apex-accelerator/apex-resume-workflow/github.svg)](https://agentmods.dev/commands/jonathan-vella/apex-accelerator/apex-resume-workflow)

Your own site

<a href="https://agentmods.dev/commands/jonathan-vella/apex-accelerator/apex-resume-workflow"><img src="https://agentmods.dev/badge/commands/jonathan-vella/apex-accelerator/apex-resume-workflow/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/commands/jonathan-vella/apex-accelerator/apex-resume-workflow"><img src="https://agentmods.dev/badge/commands/jonathan-vella/apex-accelerator/apex-resume-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,050 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	$0.00045	$0.02050
Opus 5	$0.00023	$0.01025
Sonnet 5	$0.00009	$0.00410
Haiku 4.5	$0.00005	$0.00205

Measured 2d ago against content hash 63bac5d29cfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

apex-resume-workflow 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 2d 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/apex-resume-workflow.prompt.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resume Workflow (Simplified)

Pick the project to resume, then either tell me the next step or let me read session state and confirm what I find. End by surfacing the matching handoff button — never call #runSubagent.

This prompt is safe to invoke immediately after /clear. Step agents emit a verbatim handoff line (Run /clear, then switch the chat agent picker to 01-Orchestrator and send resume <project> to continue Step N+1.) at completion; the user runs /clear, switches the agent picker back to 01-Orchestrator, and sends resume <project>, which lands here in a fresh chat with zero memory of prior turns.

Goal

Resume the multi-step Azure platform engineering workflow with the minimum number of round-trips: one question to pick the project, one question to decide who names the next step (user vs detection), and one confirmation if detection was used.

Workflow

Step 1 — Pick the project

List candidate projects:

ls -1 agent-output/ 2>/dev/null | grep -v '^README\.md$' | head -20

If exactly one project folder with a 00-session-state.json exists, use it and announce: Resuming project: <name>.
Otherwise, call vscode/askQuestions with one question:
- header: project-pick
- question: Which project do you want to resume?
- options: one per discovered folder; allow freeform input for projects not listed.

Stop if no agent-output/<project>/00-session-state.json exists for the chosen name.

Step 2 — Decide how to find the next step

Call vscode/askQuestions with one question:

header: next-step-mode
question: Do you already know which step is next?
options:
- Yes — I'll type the step (recommended when you remember the state)
- No — read session state and tell me what's next
allowFreeformInput: true

Branch A — User types the step

If the user picks Yes, ask one follow-up via vscode/askQuestions:

header: next-step-value
question: Which step is next?
options (label = handoff button label):
- Step 1: Gather Requirements
- Step 2: Architecture Assessment
- Step 3: Design Artifacts
- Step 3.5: Governance Discovery
- Step 4: Implementation Plan (Bicep)
- Step 4: IaC Plan (Terraform)
- Step 5: Generate Bicep
- Step 5: Generate Terraform
- Step 6: Deploy (Bicep)
- Step 6: Deploy (Terraform)
- Step 7: As-Built Documentation
- 🔍 Run Challenger Review

Read the full file on GitHub · 204 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.

2d ago First seen · 204 lines · 45 tokens per session scan A 63bac5d29cfa

Subscribe to this mod's changes

apex-resume-workflow is a command published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 2,050 once invoked, about $0.0002 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 2026-09-07.

Planning Project management agentic-ai azure bicep copilot github-copilot iac

backlot

Open the Backlot living storyboard — the browser board that shows pipeline stages, script, scene plan, and generated assets live as a production runs.

calesthio/OpenMontage · 29 tokens

test-management

Organize, classify, and trace Katalon True Platform/TestOps test assets. Use when you need to structure test cases into folders and suites, move or reorganize cases, search and find existing assets at scale, link or unlink requirements to test cases, or produce a requirement-to-test traceability report (which…

katalon-labs/true-skills · 124 tokens

apex-resume-workflow