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 skyf0xx/better-thinking --skill better-thinking-recipesgit clone --depth 1 https://github.com/skyf0xx/better-thinkingWrote 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/skyf0xx/better-thinking/better-thinking-recipes)<a href="https://agentmods.dev/skills/skyf0xx/better-thinking/better-thinking-recipes"><img src="https://agentmods.dev/badge/skills/skyf0xx/better-thinking/better-thinking-recipes/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/skyf0xx/better-thinking/better-thinking-recipes"><img src="https://agentmods.dev/badge/skills/skyf0xx/better-thinking/better-thinking-recipes.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 | $0.00123 | $0.02163 |
| Opus 5 | $0.00062 | $0.01081 |
| Sonnet 5 | $0.00025 | $0.00433 |
| Haiku 4.5 | $0.00012 | $0.00216 |
Grade A, and why
better-thinking-recipes 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recipes
Given a named external framework — or a request to browse what's available — load its mapping from recipes/ and run the mapped skill sequence as one continuous, orchestrated pass.
Why
A recipe doc under recipes/ states which skills implement each stage of a framework like Design Thinking, but a doc sitting unread doesn't run itself — without an orchestrator, it's reference material a human has to manually walk. This skill is the bridge: it makes a named framework actually executable, the same way a composite skill makes its own procedure executable. A user who doesn't yet know this collection's recipe names, or the frameworks' jargon, also needs a way to discover them without reading recipes/README.md directly — so browsing and running live in one place.
Use when / Don't use when
- Use when: the user names a known external framework explicitly, describes its stages without naming it, asks what recipes/frameworks exist, or wants to browse options before committing to one.
- Don't use when: no matching recipe exists in
recipes/— fall back tobetter-thinking's normal routing instead of forcing an ill-fitting framework onto the task. Don't use for a task that's already better served by a single atomic or composite skill directly.
Inputs → Outputs
- Inputs: either a named framework (or a description matching one's stages) and the task to run it on, or no framework at all — just a request to see what's available.
- Outputs: if browsing, a numbered menu of recipes with one-line descriptions and a prompt for a pick; either way, the framework's stages executed in order via their mapped skills, plus the residual-gap notes from the recipe doc (what the framework covers that this collection deliberately doesn't).
Principles
- A recipe names a combination of existing skills — it introduces no new cognition. If a stage seems to need a new move, that belongs in a skill, not patched into the recipe.
- The recipe list must come from
recipes/README.md's index, not from memory — that file is the source of truth and gains new rows over time. - Stage order in the recipe doc is load-bearing — later stages consume earlier stages' outputs, so skip-ahead isn't valid.
- The recipe's "Residual gap" section is not an implementation failure — some stages (building, prototyping) are outside this collection's scope by design and should be named as gaps, not silently dropped or faked.
- Prefer the recipe's own stage-to-skill mapping over improvising a similar-sounding skill sequence from memory — the doc encodes deliberate choices (e.g. why
problem-framingover a plain brainstorm).
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.
- 10d ago First seen · 85 lines · 123 tokens per session scan A f8533e025e5d
better-thinking-recipes is a skill published in the GitHub repository skyf0xx/better-thinking (3 stars, last pushed 29d ago), licensed MIT. It adds 123 tokens to every session and 2,163 once invoked, about $0.0006 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
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.