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 suntay44/buildable-plugin-skills --skill plannergit clone --depth 1 https://github.com/suntay44/buildable-plugin-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/suntay44/buildable-plugin-skills/planner)<a href="https://agentmods.dev/skills/suntay44/buildable-plugin-skills/planner"><img src="https://agentmods.dev/badge/skills/suntay44/buildable-plugin-skills/planner.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.01146 |
| Opus 5 | $0.00032 | $0.00573 |
| Sonnet 5 | $0.00013 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
buildable-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 7d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buildable Planner Skill
Use this skill to classify prompts, choose an archetype, decide whether questions are needed, and produce a top-down phase plan plus app spec.
Inputs
- user prompt
- optional user-provided screenshots, documents, or source files
- optional existing repository context
- optional local preferences
Resolve all referenced paths from the Buildable plugin or repository root.
Reference Loading Contract
Mandatory order:
- Run
buildable plan "<prompt>"when available. Use--file <path>,--reference <path>, or--screenshot <path>for explicit user-provided files. It saves.buildable/phase-plan.md/json/toonby default; use--no-writeonly for terminal-only inspection. - Load only
appSpec.references. - Inspect only explicit
appSpec.referenceInputssupplied by the user. - Do not load all templates.
- Do not load whole
knowledge/ortemplates/directories. - Load starter source only for the selected template and only when generating or editing it.
Use knowledge/INDEX.md and templates/INDEX.md only for discovery when the CLI is unavailable.
Workflow
- Prefer
buildable plan "<prompt>"when the CLI is available. - Use
core/archetype-registry.jsontags for lightweight matching before opening archetype docs. - Apply
core/ask-vs-build-policy.md. - Apply
core/activation-policy.md. - Load the selected
knowledge/archetypes/<archetype>.md. - Load matching files from
knowledge/data-models/andknowledge/screen-graphs/when they exist. - Select the best
templates/<target>/<archetype>/template-spec.json. - Select compact UI/UX direction from
core/design-system-registry.jsonand include it asappSpec.designSystem. - Select compatible micro-blocks from
blocks/registry.jsonand include them asappSpec.blocks; append only selected block references toappSpec.references. - Include
appSpec.mockDatawith realistic local seed-data guidance and state coverage. - Include
appSpec.referenceInputswhen users attach screenshots/files; preserve paths and inspection instructions without pasting file contents into the prompt. - Include
appSpec.promptRefinementwith assumptions, optional sharpening questions, and default answers. - Include
appSpec.planAuditwith audit-first gates for scope, template status, references, mock data, UI/UX, local-first rules, auth/persistence, and review. - Produce an app spec using
core/app-spec-schema.md. - Include a phase plan: clarify if needed, plan, mock data, design, build, review.
- Include explicit non-goals to prevent hosted feature drift.
- Ask questions with restraint:
- Ask blocking
appSpec.questionsfirst whenquestionsNeededis true. - When there are no blockers, ask at most one or two
promptRefinement.optionalQuestionsonly if they would materially improve the result. - If the user wants to proceed, use
promptRefinementdefaults instead of continuing to interrogate.
- End with a short satisfaction checkpoint:
- If the user is not satisfied, ask them to stay in Buildable Planner and revise the saved plan with a prompt such as "Buildable Planner: keep this direction, but make the reminder features stronger."
- If the user is satisfied, suggest the correct next skill for the target: Buildable Web Builder for web or Buildable Mobile Builder for mobile. The builder must read the saved
.buildable/phase-plan.jsonor.buildable/phase-plan.tooncompact contract, then load onlyappSpec.referencesand the selected starter source.
- When the user asks for login, auth, accounts, protected routes, or an explicit auth flag, include
appSpec.authand the auth references. Default to local/mock auth behind an auth seam; do not choose a hosted provider unless the user names one.
What ships with it
1 file 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.
- 7d ago First seen · 85 lines · 65 tokens per session scan A f59faf24ff01
buildable-planner is a skill published in the GitHub repository suntay44/buildable-plugin-skills (53 stars, last pushed 12d ago), licensed MIT. It adds 65 tokens to every session and 1,146 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…