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/rokyytr2/betterthink/claudenpx skills add RokyYTR2/BetterThink --skill claudegit clone --depth 1 https://github.com/RokyYTR2/BetterThinkWrote 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/rokyytr2/betterthink/claude)<a href="https://agentmods.dev/skills/rokyytr2/betterthink/claude"><img src="https://agentmods.dev/badge/skills/rokyytr2/betterthink/claude.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 | $0.00055 | $0.01217 |
| Opus 5 | $0.00028 | $0.00609 |
| Sonnet 5 | $0.00011 | $0.00243 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
betterthink 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BetterThink — Working Discipline
Apply these rules to every coding task. They override default eagerness to start coding.
1. Clarify before coding
Before writing any code, ask the user targeted questions until you are at least 95% confident you understand exactly what they want. Do not assume scope, stack, naming, edge cases, or "obvious" defaults — ask. If you catch yourself filling a gap with a guess, turn it into a question instead.
2. One to-do at a time
Do not move on to the next to-do item until you are 95% confident the current one is complete and correct. Verify it (run it, read the diff, test the behavior) before advancing. No batched "I'll fix it later" hops between tasks.
3. Prefer subagents, default to Haiku
Delegate work to subagents more often than you naturally would — research, searches, isolated implementation chunks, verification passes. For these subagents, use the Haiku model (claude-haiku-4-5-20251001) unless the task clearly needs Opus/Sonnet reasoning. This keeps the main thread focused and reduces cost.
Use Haiku subagent for:
- File search / glob / locating code
- Reading files and extracting facts
- Grep for symbols, usages, patterns
- Running linters, formatters, type checks
- Taking and inspecting UI screenshots
- Simple verification passes (does X exist, does Y match Z)
Do NOT use Haiku — keep on main model (Opus/Sonnet) for:
- Architecture decisions and design tradeoffs
- Debugging complex / multi-layer bugs
- Security review and threat modeling
- Cross-file refactors needing holistic understanding
- Anything requiring judgment over multiple unknowns
4. Keep CLAUDE.md updated — but lean
Every time you make a meaningful change to the project, update the project's CLAUDE.md at the end of that change.
Update triggers — only update CLAUDE.md when one of these happens:
- New dependency added (production or dev)
- New script added to
package.json(or equivalent:Cargo.toml,pyproject.toml,Makefile) - New top-level folder created
- Build, run, test, or deploy command changed
- New convention introduced (naming, structure, pattern, lint rule)
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 · 81 lines · 55 tokens per session scan A dd00f5606dc3
betterthink is a skill published in the GitHub repository RokyYTR2/BetterThink (1 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 1,217 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 2026-08-31.
Other skills, from other repositories
crisis-catalyst
Reframe a crisis, constraint, or setback as a forcing function for founder-mode decisions that were previously politically blocked. Based on Chesky's pandemic transformation and Andy Grove's "great companies are defined by their crises." Use when facing a serious challenge and want to use it as fuel, not just survive…
founder-quiz
Take a behavioral self-assessment to discover where you sit on the founder mode spectrum. 15 questions that reveal your actual operating mode — not what you think you do, but what you actually do. Use for honest self-reflection.
hiring-scorecard
Score an executive or senior hire using Brian Chesky's 'guilty until proven innocent' framework. Generates a reference check script, identifies red flags, and assesses builder vs. manager fit. Use when evaluating a candidate for a senior role.
org-health
Diagnose organizational health against Brian Chesky's framework. Detects the division → politics → bureaucracy → complacency arc that kills founder-led companies. Use when a founder suspects their org structure is slowing them down.
decision-check
Determine whether a decision is a founder-only move (requires institutional memory, passion, and permission) or a manageable decision that can be delegated. Based on Chesky's framework of what only a founder can do. Use when deciding whether to stay involved in or hand off a decision.
balzac
Balzac is an AI content platform CLI — create workspaces, manage SEO keywords, generate article suggestions, write articles, publish content across integrations, and monitor Google Search Console performance. Supports workspaces, keywords, suggestions, briefings, articles, competitors, links, integrations, search…