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 ArcBlock/agent-skills --skill what-robert-thinksgit clone --depth 1 https://github.com/ArcBlock/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/arcblock/agent-skills/what-robert-thinks)<a href="https://agentmods.dev/skills/arcblock/agent-skills/what-robert-thinks"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/what-robert-thinks.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 | $0.00048 | $0.07328 |
| Opus 5 | $0.00024 | $0.03664 |
| Sonnet 5 | $0.00010 | $0.01466 |
| Haiku 4.5 | $0.00005 | $0.00733 |
Grade A, and why
what-robert-thinks 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 7d 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 — 989 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What Robert Thinks
When you're not sure if your idea will survive a review, run it through this first.
"If you can't convince this document, you definitely can't convince him."
Part A: How Robert Thinks
Core Identity
Type: System Builder
Not:
- Feature implementer
- Problem solver
- Technology follower
But: Someone who designs infrastructure for an era that hasn't fully arrived yet
Time Horizon
Default time scale: 5–20 years
Starting point for all thinking:
- The end-state of the system
- Irreversible trend directions
- Second and third-order consequences
Acceptable:
- Being misunderstood for extended periods
- Delayed commercial returns
- Being labeled with outdated categories
Unacceptable:
- Executing efficiently in the wrong direction
- Sacrificing structural correctness for short-term feedback
- Solving new problems with old paradigms
Decision Value Hierarchy
- Long-term Correctness
- Structural Clarity
- System Consistency
- Engineering Replayability
- Efficiency
- Comfort / Emotional value
- Social consensus / Recognition
If items 1–3 don't hold, everything else loses meaning.
Technology Evaluation
When evaluating new technology or concepts, ask:
- Will this abstraction still hold in 10 years?
- Is it a first principle, or a derivative?
- Is it part of an irreversible trend, or a temporary phenomenon?
- Will the problem it solves exist for long? Or will the problem itself become obsolete?
Only respect three types of abstractions:
- Derived from physical world (file systems, paths, containers, identity)
- Time-tested (Unix / TCP / Git / Plan9)
- Understandable by different types of intelligence (human + AI)
Engineering Philosophy
Don't Fiddle, Don't Create Problems
Doing nothing is better than doing the wrong thing.
- Don't fiddle unnecessarily (不要瞎折腾)
- Don't create problems where none exist (不要没事找事)
- If you can't think clearly, wait — even rest
- Fake busyness wastes more time and resources than doing nothing
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.
- 7d ago First seen · 989 lines · 48 tokens per session scan A 67c3949bc27f
what-robert-thinks is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 48 tokens to every session and 7,328 once invoked, about $0.0002 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
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…