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 hugobowne/show-us-your-agent-skills --skill project-planninggit clone --depth 1 https://github.com/hugobowne/show-us-your-agent-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/hugobowne/show-us-your-agent-skills/project-planning)<a href="https://agentmods.dev/skills/hugobowne/show-us-your-agent-skills/project-planning"><img src="https://agentmods.dev/badge/skills/hugobowne/show-us-your-agent-skills/project-planning/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/hugobowne/show-us-your-agent-skills/project-planning"><img src="https://agentmods.dev/badge/skills/hugobowne/show-us-your-agent-skills/project-planning.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 | $0.00064 | $0.00941 |
| Opus 5 | $0.00032 | $0.00470 |
| Sonnet 5 | $0.00013 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
project-planning 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 12d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Planning
Use this skill to turn a fresh project idea into a focused, MVP-first plan that favors prebuilt solutions and opinionated frameworks over custom complexity.
Workflow
- Read
references/project-planning.md. - Clarify the goal in one sentence and define the single-user MVP boundary: what ships in the first cut, what is explicitly out of scope.
- Decompose the goal into a small set of manageable tasks. Group by user-visible outcome, not by layer.
- Spawn subagents in parallel to research frameworks and libraries that could absorb whole tasks. Prefer pre-built solutions unless a clear constraint rules them out.
- Start from an official scaffold or starter via
bunx create-*(bunx create-next-app,bunx create-vite,bunx create-t3-app,bunx create-tanstack,bunx create-expo) instead of hand-rolling the project skeleton. - Before any dependency install in the new project, create or preserve
bunfig.tomlwith[install] minimumReleaseAge = 259200. Prefer scaffold flags that skip the initial install, then runbun install. - Pick an opinionated framework (e.g. Next.js, TanStack Start) when it improves organization and removes wiring decisions. Skip framework-grade tooling for one-screen utilities. Ask the user which framework to use if unclear.
- For UI, initialize shadcn/ui with
bunx shadcn@latest initand choose a minimalist preset - prefer shadcn blocks, you can ask the user to pick. Pull in components on demand, not preemptively. - Lay out components and services in a logical, opinionated structure before any code is written.
- Decide the minimum useful testing surface and the minimum useful git-hook surface. Both default to small.
- Produce a short plan: goal, MVP scope, task list, stack choices with one-line rationale, deferred items.
Planning Rules
- Build for one user first.
- Use Bun as the runtime, package manager, and script runner by default.
- Start every new project from an official scaffold or template, invoked through
bunx create-*(e.g.bunx create-next-app,bunx create-vite,bunx create-t3-app,bunx create-tanstack,bunx create-expo). - Every Bun project must include a root
bunfig.tomlwithminimumReleaseAge = 259200under[install]beforebun installorbun addresolves new packages. - For UI, default to shadcn/ui with a minimalist preset. Add components with
bunx shadcn@latest add <component>as they are actually needed. - Prefer prebuilt over bespoke. Reach for a library, hosted service, or framework primitive before writing your own.
- Choose boring, well-documented defaults. Novelty is a cost, not a feature.
- Cut features before cutting clarity. If the MVP is too big, remove scope, do not compress the design.
- Pick one opinionated framework per project. Do not mix two routing or data layers.
- Organize by feature or domain, not by file type, once there is more than one screen.
- Write tests for critical logic and infrastructure: money, auth, data integrity, deploy paths. Skip tests for trivial glue and UI that will churn.
- Use git hooks for formatting and fast static checks. Do not run full test suites or type-checks on every commit.
- Defer anything that is not on the path to a working MVP: analytics, feature flags, advanced error reporting, premature abstractions.
- Re-evaluate the plan once the first end-to-end slice runs. Replan from evidence, not from the original guess.
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.
- 12d ago First seen · 47 lines · 64 tokens per session scan A 41de4ed27d82
project-planning is a skill published in the GitHub repository hugobowne/show-us-your-agent-skills (67 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 941 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…