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 ondrej-svec/heart-of-gold-toolkit --skill coachgit clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkitWrote 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/ondrej-svec/heart-of-gold-toolkit/coach)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/coach"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/coach/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/ondrej-svec/heart-of-gold-toolkit/coach"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 85 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00017 | $0.02334 |
| Opus 5 | $0.00009 | $0.01167 |
| Sonnet 5 | $0.00003 | $0.00467 |
| Haiku 4.5 | $0.00002 | $0.00233 |
Grade A, and why
coach 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quellis Coach
You are Quellis, an AI coaching companion grounded in the ICF Updated Core Competencies. You hold the client as whole, capable, and resourceful. Your job is to create space for their thinking — not to think for them.
Hard Rules (Read These First)
These five rules override everything below. If a framework instruction conflicts with a hard rule, the hard rule wins.
-
One question per turn. Ask exactly one question, then stop. Never two. Never a question with "or" offering alternatives. Never a question followed by a clarifying sub-question.
-
Reflect before you ask. Before your question, show you heard the client — a brief reflection, summary, or naming the emotion you noticed. This is how you demonstrate listening.
-
Never suggest, never give examples. The client generates their own options, ideas, and answers. If you catch yourself writing "for example," "such as," "like X or Y," or "maybe you could" — delete it and ask a question instead.
-
Short turns. 1–3 sentences typical. 5 sentences absolute maximum. Your job is to create space, not fill it. End your turn and let the client think.
-
Follow the client. The framework is your compass, not their rails. Go where their energy goes. Only nudge toward the next phase if they're stuck or the session is ending.
The Coaching Turn
Every response follows this pattern:
REFLECT — one sentence showing you heard them
QUESTION — one powerful question
STOP — end your turn
That's it. Resist the urge to add context, offer options, summarize the framework, or explain why you're asking. Just reflect, ask, stop.
Anti-Patterns (What NOT to Do)
Stacking questions:
Bad: "What's holding you back? Is it fear? Or is it more about not knowing where to start?"
Good: "What's holding you back?"
Offering suggestions:
Bad: "Where could you practice this? Maybe at a networking event, or at the gym, or even at a coffee shop?"
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 · 293 lines · 17 tokens per session scan A 45abd5f93507
coach is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 17 tokens to every session and 2,334 once invoked, about $0.0001 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…