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 marcos-sponton/frameworks-as-skills --skill continuous-discovery-habitsgit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/continuous-discovery-habits)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/continuous-discovery-habits"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/continuous-discovery-habits/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/marcos-sponton/frameworks-as-skills/continuous-discovery-habits"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/continuous-discovery-habits.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 | $0.00265 | $0.03099 |
| Opus 5.5 | $0.00106 | $0.01240 |
| Sonnet 5.5 | $0.00053 | $0.00620 |
| Haiku 4.5 | $0.00026 | $0.00310 |
Grade A, and why
continuous-discovery-habits 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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Discovery Habits
Teresa Torres's practitioner method for product discovery — distilled from Continuous Discovery Habits (Product Talk, 2021), the ongoing Product Talk essay archive (2013–present, still active weekly-ish through 2026), the All Things Product podcast (co-hosted with Petra Wille, 2025+), the Product Talk Academy (16,000+ students across 102 countries), her post-book refinements (adding "ethical" as the 5th assumption category, the Ladder of Evidence, the Interview Coach AI she built in 2025), and her position on the Product Operating Model + AI + Discovery debates through 2026.
This skill helps the assistant think in Torres's method, not just recite the tree diagram. Torres's method is a set of habits — the weekly cadence is non-negotiable, the trio is non-negotiable, the story-based interview rules are non-negotiable. Softening any of those collapses the method into generic user-research advice. Applying her frame means holding those constraints and coaching the user to build the habit, not just draw a tree.
When this skill activates
Use this skill when the user is:
- Setting up (or trying to sustain) a weekly customer interview cadence with their product team.
- Building, updating, or debugging an Opportunity Solution Tree — Outcome → Opportunities → Solutions → Assumption Tests.
- Running story-based customer interviews and wanting help with the technique (opening question, timeline walk, redirecting generalizations).
- Framing a product outcome (vs a business outcome vs an output) for a team.
- Mapping assumptions across desirability, viability, feasibility, usability, and ethical categories.
- Designing small assumption tests for a solution — instead of jumping to a full A/B experiment.
- Forming or fixing a product trio (PM + designer + engineer) so discovery is team-based, not PM-solo.
- Diagnosing why "we already talk to users" isn't producing new insight (usually project-based, not continuous).
- Reframing "opportunities" that turn out to be features in disguise.
- Auditing whether a discovery practice is actually continuous or is one-and-done research relabeled.
- Deciding how AI tools fit into a discovery cadence without replacing customer contact.
What ships with it
12 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.
- evals/evals.json 12 KB
- examples/.gitkeep 0 B
- README.md 8.2 KB
- references/applications.md 13 KB
- references/author-live-sources.md 12 KB
- references/examples.md 9.0 KB
- references/heuristics.md 15 KB
- references/method.md 17 KB
- references/post-book.md 14 KB
- references/prompts.md 12 KB
- references/sources.md 11 KB
- references/voice-and-tone.md 15 KB
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.
- 1mo ago First seen · 100 lines · 265 tokens per session scan A ac127536f6fd
continuous-discovery-habits is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (2 stars, last pushed 20d ago), licensed MIT. It adds 265 tokens to every session and 3,099 once invoked, about $0.0011 per session on Opus 5.5. 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 skills, from other repositories
design-explore
Explore 2-4 design options with pros/cons/criteria matrix before writing code. Use for L3-L4 tasks (refactors, architecture, new subsystems). Pairs with savedecision MCP tool.
awesome-design-md
Create a DESIGN.md style baseline BEFORE building UI. Use FIRST when no design draft exists — installs a proven visual style, then invoke frontend-design to implement. For borrowing a known product style, getting consistent typography/colors/spacing, or needing a fast visual starting point.
kirby-panel-and-blueprints
Designs Kirby 6 blueprints and Panel UI, including reuse/extends, programmable blueprints, value/display fields and areas. Use when changing Panel schemas or migrating legacy sections.
build-webgl-liquid-glass
Build production-ready GPU liquid-glass surfaces with liquid-gl for React or DOM UIs. Default for refractive cards, notifications, panels, GPU bevels, and WebGL glass.
build-sdf-liquid-glass
Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.
favicon-exporter
Prepare and export favicon assets from Figma in common web sizes and formats.