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 jkomyno/.dotfiles --skill jk-buildgit clone --depth 1 https://github.com/jkomyno/.dotfilesWrote 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/jkomyno/.dotfiles/jk-build)<a href="https://agentmods.dev/skills/jkomyno/.dotfiles/jk-build"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/jk-build/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/jkomyno/.dotfiles/jk-build"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/jk-build.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 | $0.00034 | $0.00539 |
| Opus 5 | $0.00017 | $0.00269 |
| Sonnet 5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
jk-build 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 11d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jk-build
A four-phase build loop. Each phase has a contract: what it takes in, what it produces, when it's done. Pick the phase that matches your starting point and run it to completion before moving to the next.
| Phase | Input | Output | Done when |
|---|---|---|---|
| spec | A rough idea | A written spec the human has reviewed | Constraints, scope, and success criteria are all named |
| plan | A stable spec | A commit list with dependencies | Every commit is self-contained and leaves the build green |
| work | An approved plan | Code + green tests + commits on the branch | Plan is fully checked off and tests pass |
| safe-change | A scoped edit request | The edit applied, verified, and documented | Tests green, docs updated, no regressions |
Running a phase
The invocation argument, when present, names the phase. When absent, infer it: fresh work starts at spec, an approved PLAN.md in the repo means work, a single scoped edit means safe-change. When in doubt, default to spec.
Before doing anything else, read the file for the active phase and follow it exactly:
Read only the active phase's file; the others load when their turn comes.
Cross-phase principles
- Honesty about uncertainty. If you guessed a name, a default, or a structure, say so when reporting. The human can correct cheaply now; expensively later.
- Match the work to the phase. Don't draft a spec while in work phase. Don't start coding while in plan phase. The phase boundary is the value.
- Working documents stay local. SPEC.md and PLAN.md are working artifacts. Don't commit them unless the repo's convention says to.
- Tests are part of the deliverable. A feature without tests is a feature with a deferred bill. The bill comes due.
- Stop and re-spec when the ground shifts. If a plan-phase decision turns out wrong during work, that's a signal to update the plan, not to hack around it.
What ships with it
5 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.
- 11d ago First seen · 38 lines · 34 tokens per session scan A 575e42134b78
jk-build is a skill published in the GitHub repository jkomyno/.dotfiles (5 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 539 once invoked, about $0.0002 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 2026-08-31.
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…