Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ondrej-svec/heart-of-gold-toolkit/plugin install deep-thoughtWrote 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/plan)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/plan"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/plan/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/plan"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/plan.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 | $0.00072 | $0.03338 |
| Opus 5 | $0.00036 | $0.01669 |
| Sonnet 5 | $0.00014 | $0.00668 |
| Haiku 4.5 | $0.00007 | $0.00334 |
Grade A, and why
plan 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 — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
Strategic planning that fits the problem. Answers HOW to build what was decided in /brainstorm (or from scratch for clear requirements).
Boundaries
This skill MAY: research (read-only), analyze codebase patterns, write the plan document. This skill MAY NOT: edit code, create files beyond the plan document, run tests, deploy, implement anything.
NEVER write code during this skill. Research and plan only.
Common Rationalizations
| Shortcut | Why It Fails | The Cost |
|---|---|---|
| "Skip research — I already know the codebase" | You know YOUR mental model. The codebase may have changed. | Plan conflicts with existing code → rework |
| "Skip decision rationale — the approach is obvious" | Obvious to you, now. Not to the person executing in 2 weeks. | Decisions get questioned, re-litigated, or silently reversed |
| "Make every task detailed — more detail is better" | Over-specified plans are brittle. They break on first contact with reality. | Plan becomes a constraint instead of a guide |
| "Skip risk analysis — it's low risk" | The risks you don't name are the ones that surprise you. | Unmitigated risk → emergency debugging |
Phase 0: Detect Context
Entry: User has a topic, brainstorm path, or feature description.
If the user provided a brainstorm path:
- Read the brainstorm document
- Extract key decisions, chosen approach, open questions
- Announce: "Using brainstorm: [filename]. Extracting decisions."
- Skip Phase 1 — the brainstorm already answered WHAT to build
If the user provided a topic but no brainstorm:
- Check
docs/brainstorms/(or project override path) for a recent match (last 14 days, semantic match on filename/frontmatter) - If one found: Read it and announce. Skip Phase 1.
- If multiple found: Ask the user which brainstorm to use.
- Prefer the harness's structured choice UI if available
- Otherwise present a short plain-text option list with each matching brainstorm plus
None — proceed without brainstorm context
- If none found: Continue to Phase 1.
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 · 331 lines · 72 tokens per session scan A 3da099597a5b
plan is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 72 tokens to every session and 3,338 once invoked, about $0.0004 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…