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 skills/drvoss/everything-copilot-cli/sprint-workflownpx skills add drvoss/everything-copilot-cli --skill sprint-workflowgit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWrote 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/skills/drvoss/everything-copilot-cli/sprint-workflow)<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/sprint-workflow"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/sprint-workflow.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.02244 |
| Opus 5 | $0.00026 | $0.01122 |
| Sonnet 5 | $0.00010 | $0.00449 |
| Haiku 4.5 | $0.00005 | $0.00224 |
Grade A, and why
sprint-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 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Workflow
A structured end-to-end development sprint using Copilot CLI's full capability stack. Inspired by Garry Tan's gstack approach — each step feeds the next, nothing falls through.
Think → Plan → Build → Review → Test → Ship → Monitor
When to Use
- Starting a new feature or significant refactor
- Any task that spans multiple files or requires sequencing
- When you want structured, reviewable output rather than ad-hoc changes
- Team environments where pull requests are the delivery mechanism
Prerequisites
-
Copilot CLI authenticated (
gh auth status) -
For the Review step: standard mode (no extra setup)
-
For the sprint-retro skill after this sprint: enable experimental features first:
/experimental on⚠️
/chronicle(used insprint-retro) requires/experimental onto be run in the same session.
The Sprint
Step 1: Think — Frame the Problem
Before writing a line, challenge the premise:
> I want to build [X]. What am I actually trying to solve?
Push back on your own framing. Identify:
- The real user pain (not the feature request)
- Assumptions that could be wrong
- The simplest possible version that delivers value
Step 2: Plan — Structured Implementation Plan
Switch to Plan Mode (Shift+Tab) and describe the task:
[Plan Mode]
> Implement paginated results for the /api/users endpoint
Copilot will ask clarifying questions, then produce a structured plan. Review it carefully.
Approve with exit_plan_mode when ready.
For complex tasks, prompt for explicit sections:
[Plan Mode]
> Design the pagination feature. Include:
> 1. Data flow and API contract
> 2. Edge cases and error handling
> 3. Test plan (unit + integration)
> 4. Files to change and why
Step 3: Build — Autopilot Execution
After plan approval, switch to Autopilot Mode (Shift+Tab) and let Copilot execute:
[Autopilot Mode]
> Implement the plan
Copilot works autonomously. You can monitor progress or continue other work. For parallelizable tasks (multiple independent files), use:
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 · 278 lines · 52 tokens per session scan A 579e4a6f77ed
sprint-workflow is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 2,244 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
speckit-workflow
Manage and run Spec Kit automation workflows via specify workflow. USE FOR: running a workflow by ID or local YAML, resuming a paused/failed run, checking run status, listing/installing/removing workflows, searching the workflow catalog, showing a workflow step graph. DO NOT USE FOR: extensions (use…
omc-ado-sprint
Sprint planning and iteration management for Azure DevOps projects. WHEN: User wants to plan sprints, manage iterations, check team capacity, groom backlogs, or assign work to sprints. DO NOT USE FOR: Work item triage (use omc-ado-triage), PR reviews (use omc-ado-review), pipeline management, or non-ADO projects.
omc-ado-triage
Azure DevOps work item triage — surfaces untriaged items, active work, open PRs, pipeline failures, and security alerts. WHEN: User wants to check ADO board status, triage work items, see pipeline health, review open PRs, or get a project health overview. DO NOT USE FOR: Sprint planning (use omc-ado-sprint), PR code…
omc-ado-setup
Configure Azure DevOps integration for the current project. WHEN: User wants to set up ADO integration, connect a project to Azure DevOps, configure .omg/config.json for ADO, or troubleshoot ADO connection issues. DO NOT USE FOR: Work item triage (use omc-ado-triage), sprint planning (use omc-ado-sprint), PR review…
omc-gh-project
GitHub Projects (v2) board management — list items, update status, manage iterations, and add issues/PRs to projects. WHEN: User wants to manage project boards, move cards between statuses, check project progress, or assign items to iterations. DO NOT USE FOR: Issue triage (use omc-gh-triage), PR review (use…
omc-gh-setup
Configure GitHub integration for the current project. WHEN: User wants to set up GitHub integration, connect a project to GitHub, configure .omg/config.json for GitHub, or troubleshoot GitHub connection issues. DO NOT USE FOR: Issue triage (use omc-gh-triage), project board management (use omc-gh-project), PR review…