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 StanfordSpezi/SpeziVibe --skill app-build-plannergit clone --depth 1 https://github.com/StanfordSpezi/SpeziVibeWrote 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/stanfordspezi/spezivibe/app-build-planner)<a href="https://agentmods.dev/skills/stanfordspezi/spezivibe/app-build-planner"><img src="https://agentmods.dev/badge/skills/stanfordspezi/spezivibe/app-build-planner/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/stanfordspezi/spezivibe/app-build-planner"><img src="https://agentmods.dev/badge/skills/stanfordspezi/spezivibe/app-build-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00036 | $0.03466 |
| Opus 5.5 | $0.00014 | $0.01386 |
| Sonnet 5.5 | $0.00007 | $0.00693 |
| Haiku 4.5 | $0.00004 | $0.00347 |
Grade A, and why
app-build-planner 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 2mo 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Build Planner
Turn your planning work into a concrete, ordered implementation plan. This skill reads the outputs from upstream planning skills, extracts buildable features, maps them to available packages or framework modules, and sequences everything into milestones that can be built and reviewed one at a time.
The primary deliverable is a structured implementation plan document saved in your project repository. You and your coding agent then work through it milestone by milestone.
When to Use
Use this skill when:
- you have completed one or more planning skills (UX planning, data model planning, compliance planning, etc.)
- you are ready to turn that planning into a milestone-based build sequence
Run this after the other planning skills and before spezi-platform-selection. The platform choice can be informed by what the plan reveals (HealthKit needs, cross-platform requirements, etc.).
Planning inputs make the plan much better, but they are not a hard requirement — if no planning documents exist, Step 1 falls back to asking the user to describe the app directly. Prefer running the planning skills first when the user has time for them.
Working Style
You are a directive implementation planner. You synthesize planning outputs and propose a concrete build sequence. You are not Socratic — you make decisions and present them for the user to review and adjust.
Your approach:
- Gather and read all available planning outputs
- Confirm the platform and backend choices
- Extract discrete, buildable features from the plans
- Map each feature to available packages or modules
- Sequence features into ordered milestones
- Produce the implementation plan document
Save the deliverable to disk. Write the finished plan to docs/implementation-plan.md in the project repository, then tell the developer: "Your implementation plan is saved at docs/implementation-plan.md. Your coding agent will use it as the sequenced build plan — milestone by milestone." If the current environment cannot write files (e.g., a chat-only session), output the full document in chat instead and ask the developer to save it at that path.
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.
- 2mo ago First seen · 301 lines · 36 tokens per session scan A dbd896599911
app-build-planner is a skill published in the GitHub repository StanfordSpezi/SpeziVibe (26 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 3,466 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
git-safety
Git safety rules. INVOKE WHEN: git push, force push, git reset, git clean, destructive git, push force, reset hard. NEVER force push or do destructive git operations.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
argent-tv-interact
Control and inspect TV apps via argent, Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…