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 skills add product-on-purpose/pm-skills --skill tool-design-sprint-map-and-targetgit clone --depth 1 https://github.com/product-on-purpose/pm-skillsWrote 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/product-on-purpose/pm-skills/tool-design-sprint-map-and-target)<a href="https://agentmods.dev/skills/product-on-purpose/pm-skills/tool-design-sprint-map-and-target"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/tool-design-sprint-map-and-target/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/skills/product-on-purpose/pm-skills/tool-design-sprint-map-and-target"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/tool-design-sprint-map-and-target.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00101 | $0.02093 |
| Opus 5 | $0.00051 | $0.01046 |
| Sonnet 5 | $0.00020 | $0.00419 |
| Haiku 4.5 | $0.00010 | $0.00209 |
Grade A, and why
tool-design-sprint-map-and-target 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 9d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Sprint Map and Target (Monday)
Produce Monday's bundled artifact: the long-term goal that names success in 1-5 years; 3-7 sprint questions converting team fears into testable risks; a 5-15 step customer or system map from key player to outcome; expert interview notes from cameo experts run in parallel; HMW (How Might We) clusters synthesized from the team; and the Decider's chosen target moment. Monday's output becomes Tuesday's design target.
Family contract: docs/reference/skill-families/design-sprint-skills-contract.md. This skill is a member of design-sprint-skills.
When to Use
- It is Day 1 of the Design Sprint and the brief is locked (via
tool-design-sprint-brief). - The team is together (in-person, remote, or hybrid) for the full Monday workshop.
- Expert interviews are scheduled for Monday afternoon (cameo role; 15-30 minutes each).
- The team needs to converge from "five days of work ahead" to "this specific target moment is what we're prototyping."
When NOT to Use
- The brief is not locked. Return to
tool-design-sprint-brief; without sprint questions, this skill has nothing to converge toward. - The challenge is so broad that "long-term goal" would be longer than 5 years. Return to problem framing.
- The team is missing the Decider. The target-moment selection at the end of Monday is the Decider's call; without that call the team disperses Tuesday with no agreed direction.
- The team has already pre-decided the target moment. Monday's value is in the convergence; if it's been pre-decided, Monday becomes ratification theater.
What This Skill Produces
A single bundled artifact with six sections:
- Long-term goal: one sentence naming success in 1-5 years. Aspirational; cannot be hit in this sprint, but should be visible from the target moment.
- Sprint questions: 3-7 questions converting team fears into testable risks. Phrased as "Can we... ?" or "Will... ?" or "How... ?"; NOT phrased as solutions.
- Customer or system map: 5-15 step flow from key player(s) at the left to outcome (long-term goal) at the right. Includes major actors, decision points, and current alternatives.
- Expert interview notes: synthesized observations from 2-4 cameo experts interviewed Monday afternoon. Surfaced as HMW candidates for the cluster board.
- HMW cluster board: 30-100+ How Might We notes from the team, clustered into 4-8 themes; voted with
tool-note-and-voteheat-map mechanic to surface top clusters. - Target moment: the single point on the map (or a tight cluster of points) the Decider picks as the prototyping target. Wednesday's storyboard begins from here.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 129 lines · 101 tokens per session scan A 31d6673b1d58
tool-design-sprint-map-and-target is a skill published in the GitHub repository product-on-purpose/pm-skills (663 stars, last pushed yesterday), licensed Apache-2.0. It adds 101 tokens to every session and 2,093 once invoked, about $0.0005 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
product-designer
Use when the user asks to review a design, critique a UI or mockup, give design feedback, or check a screen for usability and accessibility issues. Do NOT use for visual brand or aesthetic preference debates, or for reviewing copy before layout is settled.
design-sprint
Use when asked to "run a design sprint", "5-day sprint", "prototype in a week", "test ideas before building", or "Jake Knapp sprint". Helps teams go from problem to tested prototype in five days. The Design Sprint framework (created by Jake Knapp at Google Ventures) compresses months of work into one focused week.
hooked-model
Use when asked to "build habit-forming products", "Hooked model", "trigger action reward investment", "create sticky behavior loops", or "design habit loops". Helps design products that form unprompted user habits. The Hooked Model (created by Nir Eyal) explains how products create habits through Trigger, Action…
breadboarding
Turn a shaped solution into a breadboard: user actions, UI affordances, system responsibilities, and wiring so it can be sliced and implemented.
deck-open-slide-canvas
OpenDesign's architecture review: the local daemon + agent-runtime design, the tradeoffs, and the decision to lock. Built as a decision-grade product management deck for staff eng, tech leads, security.
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…