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 zpoint/vibe-seller --skill save-skillgit clone --depth 1 https://github.com/zpoint/vibe-sellerWrote 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/zpoint/vibe-seller/save-skill)<a href="https://agentmods.dev/skills/zpoint/vibe-seller/save-skill"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/save-skill/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/zpoint/vibe-seller/save-skill"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/save-skill.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 | $0.00202 | $0.01536 |
| Opus 5 | $0.00101 | $0.00768 |
| Sonnet 5 | $0.00040 | $0.00307 |
| Haiku 4.5 | $0.00020 | $0.00154 |
Grade A, and why
save-skill 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save this workflow as a skill
The user watched you do something and wants it captured so a future task can repeat it without being re-taught. Your job is to turn the actual work you just did into a durable, reusable skill — and to reuse the skills that already exist instead of piling up near-duplicates.
Do this only when asked (this is the user-triggered counterpart to post-task reflection). Write through the MCP tools below — a skill written with the built-in Write tool is discarded when the task ends.
The two tools
vibe_seller_list_skills→{slug, name, description, source, updatable}per skill. Call it first, every time.vibe_seller_save_skill(slug, skill_md, files?)→ creates a new user-space skill, or overwrites an existingupdatableone (that is how you extend).filesis an optional{path: content}map for bundled references or scripts.
Hard rule: you only ever write user-space skills
source tells you what a skill is:
builtin— shipped and maintained by the repo. Read-only. You cannot edit it andvibe_seller_save_skillwill reject its slug. If a built-in is the closest match, do not try to extend it — create a new user-space skill (pick a distinct slug) that captures the user's specific workflow and, where useful, points at the built-in for the mechanics.custom/imported(updatable: true) — user-space. These are the only skills you may overwrite.
Never decide a skill is built-in FROM MEMORY, and never silently skip an update. This is the failure that keeps a follow-up from landing: the user says "update that skill", you recall it as built-in, and you do nothing. Two rules kill it:
sourcecomes fromvibe_seller_list_skills, not memory — call it again for the update, every time. A skill YOU created earlier this session iscustom(user-space, updatable), NOT built-in — your ownvibe_seller_save_skillmade it.- When in doubt, just attempt the save.
vibe_seller_save_skill(slug, merged_md)OVERWRITES an updatable skill (that is the extend) and only rejects a genuinely built-in slug — with a message telling you to create a new one. So the server, not your guess, is the authority: try the save; on rejection, create a new user-space skill. Never conclude "it's built-in, nothing to do" and end the turn — that leaves the user's request undone.
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 · 119 lines · 202 tokens per session scan A 31b478f775ca
save-skill is a skill published in the GitHub repository zpoint/vibe-seller (64 stars, last pushed today), licensed Apache-2.0. It adds 202 tokens to every session and 1,536 once invoked, about $0.0010 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…