Agent Skills is a collection and marketplace of reusable instruction sets that teach AI agents specific workflows, tasks, or domain knowledge, with supporting files such as scripts, templates, and examples. It is for people who want to install, browse, create, or contribute portable skills for compatible agents. The catalogue entries are individual skills from this collection.
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 agentmods add skills/block/agent-skills/rp-whynpx skills add block/agent-skills --skill rp-whygit clone --depth 1 https://github.com/block/agent-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/block/agent-skills/rp-why)<a href="https://agentmods.dev/skills/block/agent-skills/rp-why"><img src="https://agentmods.dev/badge/skills/block/agent-skills/rp-why.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.03861 |
| Opus 5 | $0.00026 | $0.01930 |
| Sonnet 5 | $0.00011 | $0.00772 |
| Haiku 4.5 | $0.00005 | $0.00386 |
Grade A, and why
rp-why 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 6d 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 — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rp-why: Three Dimensions of AI Collaboration
Overview
The rp-why skill is a self-reflection framework that helps AI practitioners measure and improve their collaboration practice. It tracks three dimensions:
- DOK (Depth of Knowledge) - Cognitive complexity of human prompts, scored 1.0-4.0 using Webb's framework. "Adjusted" accounts for compression of intent.
- TM (Tool Maturity) - Intentional orchestration of AI tools, tracked through the Orchestra Model (Tiers 1-6).
- ADT (Agentic Delegation Trust) - The relationship between tool sophistication and cognitive depth. Derived from the TM x DOK matrix.
The intersection of these dimensions produces diagnostic zones that reveal the health of the collaboration practice.
How to Use This Skill
Installation
npx skills add https://github.com/block/agent-skills --skill rp-why
Available Commands
| Command | What It Does |
|---|---|
/rp-why init |
Generate a baseline from your session history |
/rp-why baseline |
Same as init |
/rp-why current |
Analyze the current session |
/rp-why compare |
Compare current session to your baseline |
/rp-why overall |
Full longitudinal analysis across all sessions |
/rp-why token-spend |
Daily token spend breakdown across all sessions |
Alternative: Natural Language
You can also ask naturally:
You: Analyze my AI collaboration patterns
You: What's my DOK distribution for this session?
You: How does this session compare to my baseline?
You: Give me the full rp-why longitudinal report
When to Use
- First time: Run
/rp-why init(or/rp-why baseline) to establish your starting point - End of session: Run
/rp-why currentto reflect on your work - Weekly: Run
/rp-why compareto track progress against baseline - Monthly: Run
/rp-why overallfor the full growth picture
The Three Dimensions
Dimension 1: DOK (Depth of Knowledge)
Measures the cognitive complexity of human prompts. Scored 1.0-4.0 using Webb's Depth of Knowledge framework.
What ships with it
13 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.
- .gitignore 19 B
- example-baseline.json 1.1 KB
- README.md 10 KB
- references/dok-levels.md 2.9 KB
- references/growth-zones.md 2.7 KB
- references/intent-compression-impact.md 2.2 KB
- references/intent-compression.md 2.2 KB
- references/nudges-by-zone.md 2.4 KB
- references/orchestra-model.md 1.7 KB
- scripts/goose_skill.py 12 KB runs code
- scripts/growth_nudge.py 2.9 KB runs code
- scripts/rp_why_baseline.py 59 KB runs code
- scripts/rp_why_core.py 17 KB runs code
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.
- 6d ago First seen · 434 lines · 53 tokens per session scan A 231175f5c7d3
rp-why is a skill published in the GitHub repository block/agent-skills (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,861 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
sillytavern-antifragile
从压力中成长，从失败中学习，越挫越勇.
single-point-rubric-designer
Design a single-point rubric with one criterion and open columns for evidence. Use for student self-assessment, peer feedback, teacher formative feedback, or pre-task planning. Works with any learning target, with or without a band system.
reflection-facilitator
Supports personal reflection, journaling, and periodic growth reviews.
side-quests
Full creative synthesis — combine song, visual concept, and TED talk from a single technical insight.
insight-song
Transform technical insights into Suno-ready songs with lyrics, style tags, and emotional arc.
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…