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 BuildGreatProducts/builder-os --skill build-mvpgit clone --depth 1 https://github.com/BuildGreatProducts/builder-osWrote 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/buildgreatproducts/builder-os/build-mvp)<a href="https://agentmods.dev/skills/buildgreatproducts/builder-os/build-mvp"><img src="https://agentmods.dev/badge/skills/buildgreatproducts/builder-os/build-mvp/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/buildgreatproducts/builder-os/build-mvp"><img src="https://agentmods.dev/badge/skills/buildgreatproducts/builder-os/build-mvp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 34 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00168 | $0.01050 |
| Opus 5 | $0.00084 | $0.00525 |
| Sonnet 5 | $0.00034 | $0.00210 |
| Haiku 4.5 | $0.00017 | $0.00105 |
Grade A, and why
build-mvp 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build MVP
Build the complete app by executing every task in docs/product-roadmap.md, in order, until all tasks are checked off.
Setup
Read docs/product-roadmap.md first — it is the source of truth for what to build and in what order. docs/prd.md is the technical spec behind it; docs/design.md holds the visual design tokens; docs/product-vision.md holds the product strategy. Do not load these documents wholesale — each phase lists the specific Reference sections to read, plus whatever a task's Notes line points to. If docs/product-roadmap.md or docs/prd.md is missing, stop and tell the user to run the Product Planner skill first (part of BuilderOS: https://github.com/BuildGreatProducts/builder-os).
Work loop
Repeat until every task in the roadmap is complete:
- Find the first unchecked task (
- [ ]). Tasks are ordered intentionally — never skip ahead. - Read what the task needs — its Files and Notes lines, plus the current phase's Reference sections if not yet read this session.
- Implement the task exactly as specified — file paths, package names, and config values are deliberate. Follow the repo's
CLAUDE.md/AGENTS.mdguidelines: simplest implementation that satisfies the task, no speculative features, surgical changes only. - Test and verify before moving on. Run the verification step at the end of the task's Notes, run the app, run existing tests, and add tests for new logic. If verification fails, fix it first — never mark a failing task complete or start the next task with the app broken.
- Mark the task complete — change
- [ ]to- [x]and update the header status line (**Status:** X/Y tasks complete,**Current Phase:** ...). - At each phase boundary: run the app end to end and confirm the phase's Goal is true and demoable before starting the next phase. No git or GitHub actions here — version control happens once at the end, after every phase is complete.
Rules
- The PRD's stack choices are final — implement them, never substitute alternatives.
- Visual styling comes from
docs/design.mdtokens — never invent colors, type, or spacing. Ifdocs/design.mddoesn't exist, follow the roadmap's foundation-phase guidance: prompt the user to run the Design System skill before styling work begins. - If a task is ambiguous or conflicts with the PRD, check the PRD section it references; if still unclear, ask one specific question rather than guessing.
- If necessary work isn't covered by any task, surface it and propose adding a task — don't silently expand scope.
- Keep going until
**Status:** Y/Y tasks complete: every task checked, every phase verified, the magic moment working end to end. - No git or GitHub actions (init, commits, branches, pushes, PRs) until every phase is complete — version control is the wrap-up step, not part of the work loop.
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 · 44 lines · 168 tokens per session scan A 3508ca3e64a9
build-mvp is a skill published in the GitHub repository BuildGreatProducts/builder-os (218 stars, last pushed 2mo ago), licensed MIT. It adds 168 tokens to every session and 1,050 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.