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 fatihguner/foreman --skill radical-candorgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/radical-candor)<a href="https://agentmods.dev/skills/fatihguner/foreman/radical-candor"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/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/fatihguner/foreman/radical-candor"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/radical-candor.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 | $0.00090 | $0.03212 |
| Opus 5 | $0.00045 | $0.01606 |
| Sonnet 5 | $0.00018 | $0.00642 |
| Haiku 4.5 | $0.00009 | $0.00321 |
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 4d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Radical Candor
When Kim Scott joined Google and later became a director at Apple, she thought she was a good manager. Then Sheryl Sandberg pulled her aside after a presentation. "You said 'um' a lot," Sandberg told her. Scott brushed it off -- she had nailed the content, after all. Sandberg pressed: "I can see I'm going to have to be more direct with you. When you say 'um' every third word, it makes you sound stupid." Scott was stunned. And then she was grateful. No one had ever cared enough to be that blunt. She had given hundreds of presentations with that verbal tic, and every previous manager had been too "nice" to mention it. Sandberg's willingness to combine genuine personal concern with unfiltered directness became the seed of what Scott later formalised as Radical Candor -- a framework that has since reshaped how a generation of managers thinks about the relationship between kindness and honesty.
The insight is deceptively simple: most management failures are failures of feedback, and most feedback failures stem from a false choice between being caring and being honest. Radical Candor rejects the choice entirely.
The Framework
The 2x2 Matrix
Radical Candor maps management behaviour along two dimensions:
- Care Personally (vertical axis): The degree to which you give a damn about the person as a human being -- not just as a producer of output. This is not about being friends; it is about acknowledging that work is performed by people with lives, fears, ambitions, and dignity.
- Challenge Directly (horizontal axis): The degree to which you tell people what you actually think -- especially when your assessment is unfavourable. Direct challenge means sharing your honest perspective, not softening it into meaninglessness.
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.
- 4d ago First seen · 199 lines · 90 tokens per session scan A ce93dd50cd52
radical-candor is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 3,212 once invoked, about $0.0005 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 2026-09-06.
Other skills, from other repositories
run-difficult-conversation
Use when preparing for or facilitating a high-stakes conversation involving conflict, feedback, performance issues, or sensitive interpersonal topics.
apply-solicited-advice-discipline
Use when someone asks you a specific question, or when you're tempted to offer advice, opinion, or evaluation nobody asked for — answer exactly the scope of what was asked and no more, and don't volunteer advice or judgment unprompted, because unsolicited or over-scoped advice is systematically discounted and can…
run-one-on-one
Use when preparing for or improving weekly one-on-one meetings between a manager and a direct report.
weekly-stop-item
A weekly feedback method in which a senior leader asks one employee what the organisation should start, stop, and keep doing. It focuses especially on removing actions that create friction.
zapier-demo
Walk a new user through setting up their first Zapier action and running it live — the smallest possible win. Asks what app they use, recommends one read action to enable, guides them to mcp.zapier.com to add it, then demonstrates it working in the same chat. Use when the user asks "show me how Zapier works", "set up…
research-proposal
A guide for creating academic research proposals for PhD applications. A research proposal explains the question, plan, and expected contribution of a future research project.