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 marcos-sponton/frameworks-as-skills --skill radical-candorgit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/radical-candor)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/radical-candor"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/radical-candor"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-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 | $0.00360 | $0.02922 |
| Opus 5 | $0.00180 | $0.01461 |
| Sonnet 5 | $0.00072 | $0.00584 |
| Haiku 4.5 | $0.00036 | $0.00292 |
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 11d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Radical Candor
Kim Scott's operating system for feedback, hard conversations, and building teams that trust each other enough to challenge each other. Distilled from Radical Candor (St. Martin's Press, 2017; revised 2019), Just Work (2021), Radical Respect (2024), the weekly Radical Candor: Communication at Work podcast with Jason Rosoff and Amy Sandler (2017–present), and Kim's Medium essays.
This skill helps the assistant think in Kim's method — not just recite the 2×2. It's opinionated because Kim is opinionated: Care Personally is load-bearing. Strip it out and you have Obnoxious Aggression with better PR, which is exactly the thing Kim spends most of her airtime warning against.
When this skill activates
Use this skill when the user is:
- Preparing to give hard feedback ("how do I tell my report that…", "how do I bring up…").
- Preparing to ask for feedback ("how do I get real feedback from my team?").
- Diagnosing why their team isn't pushing back on them.
- Running or redesigning 1:1s.
- Doing a performance review or thinking about a promotion/no-promotion decision.
- Deciding whether to hire, fire, put someone on a PIP, or tolerate a "brilliant jerk".
- Thinking about a report's career trajectory — especially the Rock Star vs. Superstar question.
- Managing up: challenging their own boss, or peers.
- Facing a moment of bias, prejudice, or bullying — theirs, someone else's, or on their team.
- Redesigning a broken decision-making process (candidate for the GSD wheel).
- Reading their own team's dynamic and asking "why are people going quiet?"
Do NOT use this skill when:
- The user just wants a summary of the book. Point them at the book and don't run the 2×2 on them.
- The user is asking a pure operational question with no interpersonal / feedback / manager dimension.
- The user is asking for legal or HR-compliance guidance about harassment/discrimination — this skill informs, it doesn't replace HR/legal counsel.
- The user is looking for a rhetorical weapon to "win" against a coworker they dislike. Name it and redirect (see the voice guard below).
What ships with it
11 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.
- evals/evals.json 9.0 KB
- README.md 7.4 KB
- references/applications.md 11 KB
- references/author-live-sources.md 8.7 KB
- references/examples.md 9.0 KB
- references/heuristics.md 18 KB
- references/method.md 14 KB
- references/post-book.md 11 KB
- references/prompts.md 9.7 KB
- references/sources.md 8.1 KB
- references/voice-and-tone.md 15 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.
- 11d ago First seen · 113 lines · 360 tokens per session scan A 53f76a6b5352
radical-candor is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 360 tokens to every session and 2,922 once invoked, about $0.0018 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 2026-08-31.
Other skills, from other repositories
acquire-skills
Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
endpoint-discovery
Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.
param-miner
Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.