Borrowing it
Nothing to install: this file belongs to daniloc/mnemion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/daniloc/mnemion/main/.claude/skills/how-to-build-software/SKILL.mdgit clone --depth 1 https://github.com/daniloc/mnemionWrote 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/daniloc/mnemion/how-to-build-software)<a href="https://agentmods.dev/skills/daniloc/mnemion/how-to-build-software"><img src="https://agentmods.dev/badge/skills/daniloc/mnemion/how-to-build-software/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/daniloc/mnemion/how-to-build-software"><img src="https://agentmods.dev/badge/skills/daniloc/mnemion/how-to-build-software.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 | $0.00051 | $0.00590 |
| Opus 5 | $0.00026 | $0.00295 |
| Sonnet 5 | $0.00010 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
how-to-build-software 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 9d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This is an accord: an orientation document that gives humans and LLM agents common language and expectations for achieving goals together. Accords are packaged as Agent Skills for agents, and quick-reference HTML guides for humans.
This accord covers three domains essential to building software.
Structuring code
Software is never completed, only abandoned. Structure must be planned carefully to ease maintenance, refinement, and understanding. The key ideas:
- Separation of concerns: different responsibilities belong in different containers.
- Encapsulation: conceal a component's details inside a boundary.
- Abstraction: expose a contract, or interface, that specifies what consumers can send and receive.
- Composition: combine components by chaining or nesting them.
- Dependencies: external components are relationships, not free building blocks. Evaluate what you're inviting inside.
- Version control: git captures your program's shape over time. Commit at every validated step.
See Structuring code.
Data is destiny
Structuring data is at least as consequential as structuring code.
- Models define the shape of data. They are contracts that describe what components can expect to input and output.
- State is the concrete value of that data at a given moment. Where it lives, whether it's duplicated, and its overall source of truth..
Store truth once, then compute its consequences.
See Data is destiny.
Creating a strong first draft
Writing software is a gamble — an investment of time against uncertain returns. Manage that risk in stages:
- Prototype the scariest unknowns first. Sloppy code, ugly interfaces. Confirm feasibility before building further.
- Vertical slice: prove that every layer of your stack can work together in one narrow path. Something complex that works must emerge from something simple that worked.
- Scope narrowly, especially when using LLM tools. The ability to generate fast can lock you into directions that conceal problems.
- Iterate: refine repeatedly, commit what works, discard what doesn't.
- Get your work in front of real people. The real test is whether it solves a problem.
What ships with it
4 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.
- 9d ago First seen · 50 lines · 51 tokens per session scan A 8ad2b1eafbfe
how-to-build-software is a skill published in the GitHub repository daniloc/mnemion (22 stars, last pushed 19d ago), licensed MIT. It adds 51 tokens to every session and 590 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…