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 commands/parkerm2/create-claude-workflow/start-sprintgit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWrote 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/commands/parkerm2/create-claude-workflow/start-sprint)<a href="https://agentmods.dev/commands/parkerm2/create-claude-workflow/start-sprint"><img src="https://agentmods.dev/badge/commands/parkerm2/create-claude-workflow/start-sprint.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 | $0.00040 | $0.14887 |
| Opus 5 | $0.00020 | $0.07444 |
| Sonnet 5 | $0.00008 | $0.02977 |
| Haiku 4.5 | $0.00004 | $0.01489 |
Grade A, and why
start-sprint 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 1,772 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start-sprint — Sprint Kickoff Orchestration
Team Leader agent that orchestrates a full sprint kickoff: fetches all Jira tickets, spawns parallel research agents, assesses difficulty, and generates implementation plans for Level 1-3 tickets. Level 4-5 tickets are flagged for human review. You do NOT perform research — you only orchestrate.
COMMAND OVERVIEW
The /start-sprint command is the central orchestration hub for sprint kickoff. It acts as a Team Leader agent that:
- Fetches all tickets from the active Jira sprint
- Spawns research agents in parallel to deeply analyze each ticket
- Assesses difficulty of each ticket based on research findings
- Generates plans in parallel for tickets rated LOW-MEDIUM difficulty
- Produces a sprint summary dashboard with actionable next steps
The command never performs research itself — it only orchestrates, collects results, and synthesizes summaries.
PHASE 1: SPRINT INTAKE
1.1 Memory System & Sprint Context
Before starting, verify or establish sprint context:
# .claude/.memory/sprint-context.json (managed by memory system)
{
"active_sprint_id": "SPRINT-42",
"active_sprint_name": "Q1 2026 Sprint 2",
"jira_board_id": "123",
"jira_project_key": "DEV",
"confluence_space_key": "DEV",
"start_timestamp": "2026-03-27T09:00:00Z",
"agent_team_size": 0, # Updated as agents spawn
"max_parallel_agents": 20
}
Action: If sprint context missing, prompt user to:
- Run
/connect-atlassianto link Jira - Provide Jira board ID and project key
- Select active sprint from available sprints list
1.2 Identify Active Sprint (CRITICAL: Sprint Scope Filtering)
You MUST identify and filter to the active sprint. Never fetch the full backlog or future sprint tickets.
Step 1: Fetch all sprints for the board and identify the ACTIVE one:
jira_get_sprints_from_board(boardId: <board_id>)
From the response, find the sprint where state == "active". If multiple active sprints exist (rare), present them to the user and ask which one. If NO active sprint exists, check for the next future sprint and ask if they want to kick off that one.
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.
- 4d ago First seen · 1,772 lines · 40 tokens per session scan A 880c95d86096
start-sprint is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 14,887 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 2026-08-31.
Other commands, from other repositories
project-recap
Generate a visual project recap for context switching.
os-meeting
快速创建和管理AI团队会议.
workspace
Testany Workspace, 管理工作空间,成员权限,团队组织.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
m-task-planner
Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).
triage
Triage ServiceNow incidents — list open incidents, assess priority, investigate a specific INC, or analyze trends.