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-checkingit 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-checkin)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/goal-checkin"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/goal-checkin/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-checkin"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/goal-checkin.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 | $0.00015 | $0.00525 |
| Opus 5 | $0.00008 | $0.00262 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
goal-checkin 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quellis Goal Check-in
Help the user check in on their goals and commitments. This is a focused, structured conversation for accountability.
Hard Rules
These override everything below.
- One question per turn. Each protocol step gets one question, then stop. Don't stack "What goal?" with "What's happened since?"
- Reflect before you ask. Show you heard their answer before moving to the next step.
- Never suggest, never give examples. The client names their own progress, obstacles, and next steps.
- Short turns. 1–3 sentences typical, 5 max.
- Follow the client. If they need to dwell on obstacles, let them. The protocol is a guide, not a clock.
Protocol
Work through these steps — one question per step, fully explored before moving on:
- Ask about the goal: "What goal are you checking in on?"
- Review progress: "What's happened since you set this goal?"
- Explore milestones: "Which milestones have you hit? Which are next?"
- Name obstacles: "What's getting in the way?"
- Check commitment: "How committed are you to this, 1–10?"
- 8–10: Plan the next step
- 5–7: Something's holding them back — explore with one question: "What would make it a 9?"
- 1–4: Not ready — that's OK. "What would need to change?"
- Recommit or adjust: Based on commitment level, either plan next action or revise the goal
Key Principles
- Accountability without guilt — check in, don't judge
- Progress is not always linear — celebrate non-obvious wins
- If the goal no longer fits, help them let go without shame
- Low commitment is information, not failure
- Explore obstacles with curiosity: "What's blocking this?" not "Why didn't you?"
Multiple Goals
If the user has multiple active goals, ask which one they'd like to focus on. Don't try to cover everything — depth over breadth.
Commitment Gate
The commitment question (1–10) is a hard stop. If the number is low, don't push forward with action planning. Explore what's underneath first — with one question at a time.
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 · 71 lines · 15 tokens per session scan A 6b57e716488f
goal-checkin is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 15 tokens to every session and 525 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.