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 escaping-the-build-trapgit 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/escaping-the-build-trap)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/escaping-the-build-trap"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/escaping-the-build-trap/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/escaping-the-build-trap"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/escaping-the-build-trap.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 | $0.00270 | $0.02864 |
| Opus 5 | $0.00135 | $0.01432 |
| Sonnet 5 | $0.00054 | $0.00573 |
| Haiku 4.5 | $0.00027 | $0.00286 |
Grade A, and why
escaping-the-build-trap 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 11d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Escaping the Build Trap
Melissa Perri's diagnostic + operational frame for product organizations — distilled from Escaping the Build Trap (O'Reilly, 2018), Product Operations (with Denise Tilles, 2023), her 2024 "Four Dimensions of a Great Product Management Organization" model, 271+ episodes of the Product Thinking podcast (weekly since 2020), her Substack (active since 2023), the melissaperri.com blog archive (2014–), and her ongoing LinkedIn commentary through 2026.
This skill helps you think in Perri's method, not just recite it. The method is opinionated because Perri is opinionated: the build trap is a systems pathology, not a PM performance problem. Applying her frame means resisting the reflex to blame the PM, add a process, or ship more features — and instead diagnosing where in the org the strategy vacuum, the misassigned accountability, or the missing operational scaffolding is producing the symptoms.
When this skill activates
Use this skill when the user is:
- Diagnosing why their product team ships features but customer/business metrics stay flat.
- Auditing the PM function — role clarity, career ladders, hiring, seniority mix.
- Rebuilding the roadmap because it has become a Gantt chart / sales contract / feature promise machine.
- Deploying strategy from Vision down to team-level work and losing coherence along the way.
- Considering whether/how to stand up a Product Operations function.
- Trying to make OKRs actually produce outcomes instead of output disguised as outcomes.
- Debating the "PM as mini-CEO" model or the "one throat to choke" accountability trap.
- Redesigning teams around value streams instead of components/features.
- Reading Cagan on the Product Operating Model and wondering where Perri fits.
- Evaluating whether their org is actually product-led or just uses the vocabulary.
Do NOT use this skill when:
- The org is pre-product/market-fit — Perri's frame assumes you have a product and a team large enough to have the pathology. Pre-PMF startups need discovery + search frames (Torres, Moesta/JTBD, Lean Startup).
- The question is pure engineering ("how do we ship faster?", "what's our CI/CD stack?"). Suggest Shape Up, DORA, or SRE frames.
- The question is about the top-level org transformation (Product Operating Model change). Perri explicitly cedes that altitude to Marty Cagan (Transformed, 2024) and works one level down. Point the user to Cagan and use this skill for the operational scaffolding underneath.
- The user just wants a summary of Escaping the Build Trap. Give the book link and don't run the diagnostic.
What ships with it
11 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 8.7 KB
- README.md 7.3 KB
- references/applications.md 10 KB
- references/author-live-sources.md 9.5 KB
- references/examples.md 11 KB
- references/heuristics.md 18 KB
- references/method.md 13 KB
- references/post-book.md 17 KB
- references/prompts.md 11 KB
- references/sources.md 8.2 KB
- references/voice-and-tone.md 12 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.
- 11d ago First seen · 101 lines · 270 tokens per session scan A d178df25a096
escaping-the-build-trap is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 270 tokens to every session and 2,864 once invoked, about $0.0014 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 skills, from other repositories
cc-skill-project-guidelines-example
Project Guidelines Skill (Example).
grace-status
Show GRACE 4 project health across .grace context, graph, verification, active changes, scopes, and migration boundaries.
belbin-team-roles
Analyzes team composition using Belbin's nine team roles across Thinking, Action, and People categories. Maps team members to roles such as Plant, Shaper, Coordinator, Implementer, and others to identify gaps, overlaps, and imbalances. Use when hiring to fill role gaps, diagnosing recurring team conflicts, auditing…
doblin-ten-types
Maps and designs innovation strategy using Doblin's Ten Types of Innovation across Configuration (Profit Model, Network, Structure, Process), Offering (Product Performance, Product System), and Experience (Service, Channel, Brand, Customer Engagement). Use when auditing current innovation profile, identifying…
hackman-enabling-conditions
Diagnoses and designs team effectiveness using Hackman's six enabling conditions: a real team, compelling direction, right people, sound structure, supportive context, and expert coaching. Shifts focus from blaming team members to establishing the structural and environmental conditions that make high performance…
myers-briggs-type-indicator
Maps team cognitive diversity using the MBTI four-dichotomy personality framework: Extraversion/Introversion, Sensing/Intuition, Thinking/Feeling, Judging/Perceiving. Use when diagnosing co-founder communication friction, designing cognitively diverse teams, adapting communication style for different audiences…