radical-candor

radical-candor is a skill for Claude Code, Codex from guia-matthieu/clawfu-skills. It costs 82 tokens per session (5,456 once invoked), scanned A, original, MIT.

A framework for giving clear feedback while showing that you care about the person receiving it. It combines personal concern with direct challenges instead of avoiding difficult conversations or being needlessly harsh.

In plain words
What is it for?
Use it for positive or corrective feedback, performance discussions, trust-building with direct reports, and developing a more direct team culture.
Why use it?
Managers often soften feedback so much that problems remain unresolved, or deliver it so harshly that trust suffers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it for positive or corrective feedback, performance discussions, trust-building with direct reports, and developing a more direct team culture.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guia-matthieu/clawfu-skills/radical-candor
Install

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.

Any agent
npx skills add guia-matthieu/clawfu-skills --skill radical-candor
Clone the repo
git clone --depth 1 https://github.com/guia-matthieu/clawfu-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for radical-candor

README.md
[![agentmods](https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/radical-candor/github.svg)](https://agentmods.dev/skills/guia-matthieu/clawfu-skills/radical-candor)
Your own site
<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/radical-candor"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-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.

agentmods 80×15 button for radical-candor

Your own site · 80×15
<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/radical-candor"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/radical-candor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.05456
Opus 5 $0.00041 $0.02728
Sonnet 5 $0.00016 $0.01091
Haiku 4.5 $0.00008 $0.00546

Measured 9d ago against content hash 15f9bb4dfb29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 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.

skills/leadership/radical-candor/SKILL.md · 866 lines

How it starts

The opening of the file, as written. The whole thing — 866 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Radical Candor

Stop being a "nice" manager. Learn Kim Scott's framework for caring personally while challenging directly—the combination that builds trust and drives performance.

When to Use This Skill

  • Giving feedback (positive or constructive)
  • Building trust with direct reports
  • Performance conversations that need to happen
  • Team culture building for high performance
  • New manager development learning to have hard conversations
  • Preventing ruinous empathy in yourself or your organization

Methodology Foundation

Aspect Details
Source Kim Scott - Radical Candor (2017)
Core Principle "Radical Candor = Care Personally + Challenge Directly. You need both. Neither alone is enough."
Background Scott was a senior leader at Google and Apple, advised Twitter, Dropbox, and many others
Why This Matters Most managers fail by being too nice (Ruinous Empathy) or too harsh (Obnoxious Aggression). Radical Candor is the sweet spot that builds both trust and results.

What Claude Does vs What You Decide

Claude Does You Decide
Structures production workflow Final creative direction
Suggests technical approaches Equipment and tool choices
Creates templates and checklists Quality standards
Identifies best practices Brand/voice decisions
Generates script outlines Final script approval

What This Skill Does

  1. Defines the four quadrants - Radical Candor, Ruinous Empathy, Obnoxious Aggression, Manipulative Insincerity
  2. Teaches caring personally - Building genuine relationships
  3. Develops challenging directly - Having necessary hard conversations
  4. Provides feedback frameworks - How to give effective criticism and praise
  5. Builds a feedback culture - Teams that can handle candor
  6. Avoids management traps - Especially "ruinous empathy"

How to Use

Give Difficult Feedback

I need to give feedback to [person] about [issue].
Help me structure this using Radical Candor principles.
Context: [relationship, situation]

Read the full file on GitHub · 866 lines

Changes

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.

  1. 9d ago First seen · 866 lines · 82 tokens per session scan A 15f9bb4dfb29

Subscribe to this mod's changes

radical-candor is a skill published in the GitHub repository guia-matthieu/clawfu-skills (149 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 5,456 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 2026-09-03.

Related

Other skills, from other repositories

team-onboarding-playbook

Design a structured onboarding experience that gets new team members productive in 30, 60, and 90 days. Use when a new hire is joining, when contractors or agency partners need to ramp up, when an existing team is restructuring and members are switching focus, or when current onboarding feels chaotic and slow. Also…

rampstackco/claude-skills · 124 tokens

developer-onboarding-builder

Création de processus d'onboarding pour nouveaux développeurs. Se déclenche avec "onboarding", "nouveau développeur", "intégration équipe", "setup poste", "getting started guide", "accueil développeur". Also triggers on "onboard a new developer", "developer setup guide", "first week checklist".

khalilbenaz/claude-skills-collection · 72 tokens

azure-devops

Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…

sanjay3290/ai-skills · 105 tokens

ads-performance-analytics

How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media…

rampstackco/claude-skills · 147 tokens

paid-media-strategy

A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media…

rampstackco/claude-skills · 142 tokens

prd-to-issues

Splits a PRD into vertical-slice GitHub issues with HITL/AFK tagging and dependencies. Triggers: PRD to issues, create tickets, break down PRD, work items.

softspark/ai-toolkit · 46 tokens