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 agentmods add skills/giang6283623/minimal-vibe-coding-kit/claimnpx skills add giang6283623/minimal-vibe-coding-kit --skill claimgit clone --depth 1 https://github.com/giang6283623/minimal-vibe-coding-kitWrote 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/giang6283623/minimal-vibe-coding-kit/claim)<a href="https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/claim"><img src="https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/claim.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 | $0.00050 | $0.01774 |
| Opus 5 | $0.00025 | $0.00887 |
| Sonnet 5 | $0.00010 | $0.00355 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
claim 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 5d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claim
The text after the invocation is the claim - a request to bring something new into this repo: a skill, rule, convention, workflow, concept, or tool, possibly referenced by URL or document. Vet it before any edit; integrate only what survives vetting. No text after the invocation → ask what the user wants to integrate and stop.
Step 1 - Understand the claim
- Restate the request in one sentence: what should exist in the repo after integration.
- Classify the integration target: new skill / new rule / convention entry (
backbone.ymlcustom_rules) / command / doc reference / config change. - List every URL, package name, tool name, and document the claim references.
Done when: the claim has one clear outcome sentence, a target type, and a complete reference list.
Step 2 - Validate references and sources
Process each reference from Step 1 through these stages in order; an earlier stage gates every later one.
- Lexical triage - no network. Judge the reference as text before opening anything. Reject: any scheme other than
https(http:,file:,ftp:,data:,javascript:); URLs carrying user-info (user@host); URL shorteners; IP-literal, localhost, or private-network hosts; lookalike, typosquat, or punycode/Unicode-confusable domains; raw paste sites; and direct download links to executables or scripts. A rejected reference is never opened or "resolved to see where it goes" - report it with the official alternative instead. - Sanitize before any display or record. Strip user-info; replace the values of sensitive query keys (
token,key,secret,password,auth,signature,code, and their case or encoding variants) with[REDACTED]; drop fragments. Every later mention of the reference - ledger, questions, plans, logs, saved notes - uses only the sanitized form; the raw secret-bearing URL is never printed or persisted. - Discover the official source independently. Never follow a suspicious link to find its destination. Locate the vendor's documentation domain, the project's own repository, or the package-registry entry through official indexes, documentation MCP tools (for example Context7), or restricted search - then open only that already-verified official HTTPS destination. If a redirect chain cannot be observed safely, record final-domain verification as unavailable instead of guessing.
- Verify the content. Cross-check factual claims (API names, flags, config formats, install commands) against the official docs; mark anything unverifiable as an assumption.
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.
- 5d ago First seen · 83 lines · 50 tokens per session scan A e0561b592b4a
claim is a skill published in the GitHub repository giang6283623/minimal-vibe-coding-kit (21 stars, last pushed 8d ago), licensed MIT. It adds 50 tokens to every session and 1,774 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…