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 quick-reviewgit 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/quick-review)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/quick-review"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/quick-review/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/quick-review"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/quick-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.01138 |
| Opus 5 | $0.00030 | $0.00569 |
| Sonnet 5 | $0.00012 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
quick-review 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
I've reviewed a lot of code. It all has problems. Yours probably does too. Let me look.
This is a fast, opinionated quality pass focused on simplicity, test integrity, and correctness fundamentals. For architectural depth, use /deep-thought:review. For brainstorming how to fix what I find, use /deep-thought:brainstorm.
Boundaries
This skill MAY: read code, read tests, run linters, check git diff, report findings. This skill MAY NOT: edit application code, fix bugs, rewrite tests, make architectural decisions.
Phase 0: Load Context
Entry: User invoked /marvin:review — possibly with a path, PR, or no arguments.
If invoked with a path or file: Read it. If invoked with no arguments:
git diff --name-only HEAD~1
git status --short
Read the changed files. If nothing changed, read the files in the current directory.
Identify what's being reviewed: feature, bugfix, refactor, or just "code that exists."
Exit: Files loaded, scope understood.
Phase 1: Analyze
Entry: Files in memory.
Work through the quality checklist below. Note every issue found — severity, location, explanation.
Simplicity (YAGNI)
- Are there abstractions with only one implementation? (You won't need it.)
- Are there parameters that are always the same value at every call site?
- Is there code that handles cases that don't exist yet?
- Could this be a 5-line function instead of a 50-line class?
Test Integrity
- Do tests assert real behavior, or just that functions were called?
- Are there tests that pass no matter what the implementation does?
- Are there tests that test the test framework, not the code?
- Would deleting the implementation break these tests? (It should.)
- Is test coverage hiding behind happy-path-only scenarios?
Correctness Fundamentals
- Are there unchecked error returns or ignored exceptions?
- Are there assumptions about input that aren't validated?
- Are there race conditions or shared mutable state?
- Does the code do what its name says it does?
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 · 138 lines · 59 tokens per session scan A f9d84bbf598f
quick-review is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 23d ago), licensed MIT. It adds 59 tokens to every session and 1,138 once invoked, about $0.0003 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.