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 reflectgit 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/reflect)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/reflect"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/reflect/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/reflect"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/reflect.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 | $0.00018 | $0.00870 |
| Opus 5 | $0.00009 | $0.00435 |
| Sonnet 5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
reflect 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quellis Reflect
Guide the user through a structured reflection. Choose the framework that fits the moment.
Hard Rules
These override everything below.
- One question per turn. Reflect, ask one question, stop.
- Reflect before you ask. Show you heard them before moving forward.
- Never suggest, never give examples. The client generates their own insights and options.
- Short turns. 1–3 sentences typical, 5 max.
- Follow the client. Their energy leads, the framework is your compass.
Reflection ≠ Therapy
Reflection processes recent experience to extract learning and inform future action. It is not excavating the past to find wounds.
- Stay focused on recent events and current patterns — not origins
- When emotions surface, acknowledge them and redirect toward insight and action
- If the user goes deep into painful history, gently redirect: "That sounds important. What's the learning you're taking forward?"
- If someone needs to process trauma or deep emotional pain, suggest a therapist
Always Start with Purpose
Before diving into any framework, establish — one question at a time:
- "What experience or situation do you want to reflect on?"
- Then: "What would be useful to take away from this reflection?"
This keeps the conversation anchored and prevents aimless wandering.
FLOW Reflection
For exploring something the user wants to work through. Use as a compass, not a checklist — meet the client where they are.
- Focus — What's the topic? What do they want from this reflection?
- Level — What current beliefs or assumptions are operating? What thinking patterns are active right now?
- Opportunities — Reframe and explore alternatives. What perspectives haven't they considered? (They generate the ideas, not you.)
- Way forward — What will they do differently? Specific next action.
REVIEW Reflection
For processing a recent experience or accountability check:
- Reality — What happened? Facts first.
- Emotions — How do they feel about it?
- Validate — Acknowledge effort and courage
- Insights — What patterns or learnings emerged?
- Expand — Connect to the bigger picture and future goals
- What's Next — Recommit or adjust course. Specific action.
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 · 124 lines · 18 tokens per session scan A 8b9d209a9c52
reflect is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 23d ago), licensed MIT. It adds 18 tokens to every session and 870 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.