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.
git clone --depth 1 https://github.com/hollandkevint/data-product-operatorWrote 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/hollandkevint/data-product-operator/reshape-sprint)<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/reshape-sprint"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/reshape-sprint/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.
<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/reshape-sprint"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/reshape-sprint.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00021 | $0.01117 |
| Opus 5 | $0.00010 | $0.00558 |
| Sonnet 5 | $0.00004 | $0.00223 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
reshape-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 10d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reshape a Sprint into a Shaped Pitch
Convert sprint-style artifacts (backlog items, user stories, story points, sprint plans) into a Shape Up pitch. Shape Up works better for data product teams because data work has inherent uncertainty that fixed-scope sprints can't accommodate.
The output is a shaped pitch that your team can evaluate at a betting table.
Gather Context
If $ARGUMENTS provides a file path or description, use it. Otherwise, ask:
Question 1: Share your sprint artifacts. Options: paste backlog items, provide a file/doc, or describe what the sprint is supposed to accomplish.
Question 2: How long is the current sprint? (1 week, 2 weeks, other)
Question 3: What's the actual problem this sprint is trying to solve? (not the list of stories, but the customer or business problem underneath them)
Question 4: What is this work worth to the business? How much time should you budget for a solution? (This becomes the appetite.)
Transformation Process
Step 1: Find the Problem
Sprint backlogs list solutions (stories, tasks). Strip those away and find the underlying problem.
Look for:
- The user story at the top of the backlog (that's closest to the problem)
- Acceptance criteria that describe outcomes (not implementation steps)
- Any "why" documented in epic descriptions or comments
Rewrite as a problem statement: "[Who] needs to [do what] because [why], but currently [obstacle]."
Step 2: Set the Appetite
Convert the sprint estimate into an appetite:
- Sprint velocity / story points are estimates of effort. Appetite is a budget of time.
- Ask: "If we could only spend [X weeks] on this, what's the smallest version that delivers value?"
- Standard appetites: 1 week (small batch) or 6 weeks (big batch)
- If the sprint is 2 weeks of work, that's a small batch (1 week appetite with buffer)
- If the sprint is 4-8 weeks of work, that's a big batch (6 week appetite)
Step 3: Sketch the Solution
Convert user stories into a solution sketch:
- Not wireframes or specifications
- A rough description of the approach at the right level of abstraction
- Focus on the flow, not the details
- Include enough for a senior engineer to understand the approach and fill in the blanks
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.
- 10d ago First seen · 120 lines · 21 tokens per session scan A be98a3e6824d
reshape-sprint is a command published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,117 once invoked, about $0.0001 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
quick-prd
Generate a complete PRD with competitive analysis in one workflow.
ompm
A general entry point that interprets a request and sends it to the most suitable product-management guide or workflow. Product management covers deciding what to build, why to build it, and how to deliver it.
full-pm-cycle
A command that coordinates product management from researching a market and users through planning, design, delivery, and measuring results.
feature-launch
A command that coordinates a feature from its product requirements document through release and analysis after launch. A product requirements document describes what a feature should do and why.
ceo-review
Run a CEO-level strategic review of a feature before development.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.