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 wdavidturner/product-skills --skill radical-candorgit clone --depth 1 https://github.com/wdavidturner/product-skillsWrote 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/wdavidturner/product-skills/radical-candor)<a href="https://agentmods.dev/skills/wdavidturner/product-skills/radical-candor"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/radical-candor/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/wdavidturner/product-skills/radical-candor"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/radical-candor.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 | $0.00073 | $0.01069 |
| Opus 5 | $0.00036 | $0.00535 |
| Sonnet 5 | $0.00015 | $0.00214 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
radical-candor 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Radical Candor
What It Is
Radical Candor is a framework for giving feedback that builds trust and drives results. The core insight: great feedback happens when you Care Personally AND Challenge Directly at the same time.
Most people fail at feedback because they choose one or the other. They're either so focused on being nice that they don't say what needs to be said (ruinous empathy), or they're so focused on being direct that they forget to show they care (obnoxious aggression). Radical Candor isn't about finding a middle ground—it's about doing both fully.
The key shift: Move from "How do I deliver this feedback?" to "How do I help this person succeed?"
When to Use It
Use Radical Candor when you need to:
- Give feedback (both praise and criticism) that actually lands
- Have difficult performance conversations with direct reports
- Build a culture of honest communication on your team
- Solicit feedback from others about your own performance
- Coach employees through growth and development
- Address problems before they become crises
- Build trust in professional relationships
When Not to Use It
- When you don't actually care — if you just want to vent or hurt someone, that's obnoxious aggression with extra steps
- When the feedback is about unchangeable personal traits — focus on behavior, not personality
- When you haven't solicited feedback first — always start by asking for feedback before giving it
- When you're saving it for a performance review — Radical Candor happens in the moment, not quarterly
- When you haven't built any relationship — you need some foundation of care before challenging directly
Patterns
Detailed examples showing how to apply Radical Candor correctly. Each pattern shows a common mistake and the correct approach.
Critical (get these wrong and you've wasted your time)
| Pattern | What It Teaches |
|---|---|
| ruinous-empathy | Being "nice" by withholding feedback isn't kind—it's harmful |
| obnoxious-aggression | Challenging without caring puts people in fight-or-flight |
| manipulative-insincerity | Saying what people want to hear destroys trust |
| soliciting-before-giving | Always ask for feedback before you give it |
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- patterns/_template.md 460 B
- patterns/accepting-no-answer.md 1.5 KB
- patterns/asking-why.md 1.5 KB
- patterns/feedback-sandwich.md 1.6 KB
- patterns/feedback-via-text.md 1.4 KB
- patterns/gauging-how-it-lands.md 1.8 KB
- patterns/manipulative-insincerity.md 1.7 KB
- patterns/obnoxious-aggression.md 1.6 KB
- patterns/people-pleasing-trap.md 1.5 KB
- patterns/personality-not-behavior.md 1.3 KB
- patterns/public-criticism.md 1.7 KB
- patterns/ruinous-empathy.md 1.8 KB
- patterns/soliciting-before-giving.md 1.6 KB
- patterns/vague-praise.md 1.3 KB
- patterns/waiting-for-better-moment.md 1.3 KB
- references/radical-candor-playbook.md 12 KB
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 · 86 lines · 73 tokens per session scan A 9996f0b854fe
radical-candor is a skill published in the GitHub repository wdavidturner/product-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 73 tokens to every session and 1,069 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…