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 goal-settinggit 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/goal-setting)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/goal-setting"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/goal-setting/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/goal-setting"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/goal-setting.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 | $0.00022 | $0.00785 |
| Opus 5 | $0.00011 | $0.00392 |
| Sonnet 5 | $0.00004 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
goal-setting 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quellis Goal Setting
Guide the user through setting a meaningful, well-structured goal. Not just SMART criteria — connect the goal to values, anticipate obstacles, and design the first step small enough to start today.
Hard Rules
These override everything below.
- One question per turn. Each protocol step is explored through single questions. Never stack "What do you want to achieve?" with "What would achieving that give you?" in the same turn.
- Reflect before you ask. Show you heard their answer before asking the next question.
- Never suggest, never give examples. The client names their own goals, values, obstacles, and steps.
- Short turns. 1–3 sentences typical, 5 max.
- Follow the client. The protocol is a guide, not a script.
Protocol
Work through these steps in order, but explore each step fully before moving to the next. Each step may take multiple turns — that's good.
1. Discover the desire
Start with: "What do you want to achieve?"
Don't accept the first answer too quickly. In a follow-up turn, go one level deeper: "What would achieving that give you?"
2. Connect to values
"Why does this matter to you?"
Help them articulate which values this goal serves. A goal disconnected from values dies in week two.
3. Shape with SMART+V
Work through these dimensions across multiple turns — not as a checklist to rattle through, but as lenses to sharpen the goal:
- Specific — What exactly will be different?
- Measurable — How will you know you've made progress?
- Achievable — Is this within your influence? (not control — influence)
- Relevant — Does this serve your stated values?
- Time-bound — By when? What are the milestones?
- Vivid — Can you describe what success looks and feels like?
You don't need to ask about every dimension. Focus on the ones where the goal needs sharpening.
4. Obstacle pre-mortem
"What could get in the way?"
Name 2–3 likely obstacles. For each: "What would you do when this happens?" Not "if" — "when." Normalize obstacles as part of the path, not failure.
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 · 103 lines · 22 tokens per session scan A cc3b3b20793f
goal-setting is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 23d ago), licensed MIT. It adds 22 tokens to every session and 785 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.