Claude Code Thinking Skills is a catalogue of 28 portable skills that give coding agents structured procedures for reasoning about decisions, diagnosis, risk, strategy, and related problems. It is intended for Claude Code, GitHub Copilot, Codex, Cursor, and other tools that support Agent Skills.
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 tjboudreaux/cc-thinking-skills --skill thinking-model-combinationgit clone --depth 1 https://github.com/tjboudreaux/cc-thinking-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/tjboudreaux/cc-thinking-skills/thinking-model-combination)<a href="https://agentmods.dev/skills/tjboudreaux/cc-thinking-skills/thinking-model-combination"><img src="https://agentmods.dev/badge/skills/tjboudreaux/cc-thinking-skills/thinking-model-combination/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/tjboudreaux/cc-thinking-skills/thinking-model-combination"><img src="https://agentmods.dev/badge/skills/tjboudreaux/cc-thinking-skills/thinking-model-combination.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00763 |
| Opus 5 | $0.00017 | $0.00381 |
| Sonnet 5 | $0.00007 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
thinking-model-combination 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Combination
Core rule: Combine only when each model answers a different named question. Cap at three, name the conflict rule before applying, then synthesize once.
When to Use
- One model already applied (or clearly primary) still leaves a material blind spot that another mechanism covers.
- Problem spans domains (e.g. risk + choice + system structure) and stakes justify multi-lens work.
- You need independent checks, not confirmation of the same conclusion.
- You can name a distinct role per model before running them.
When NOT to Use
- A single catalog skill fully answers the unknown — apply that skill alone.
- Routine, local, or fully reversible work where multi-lens cost exceeds upside.
- You cannot state what unique question each extra model answers (checkbox / model soup).
- Near-duplicate mechanisms (two diagnosis skills that ask the same causal question).
- Time budget cannot support genuine synthesis — prefer one honest model over contradictory partials.
Procedure
- State the unknown and the gap. Write the decision question. If one model already covers it, stop and use that model alone. Otherwise name the specific blind spot (e.g. "failure modes unexamined", "displaced alternative unknown").
- Pick 2–3 models with distinct roles. For each, record: model id, role (narrow / decide / stress / cost / …), and the unique question it answers. Drop any model that only rephrases another. Prefer sequential pipeline (narrow → stress → decide) over parallel unless independent concurrent checks are required.
- Lock the relation and conflict rule before applying. Choose pattern: sequential, parallel, nested (macro→meso→micro), or adversarial (for/against). Predeclare the tiebreaker (e.g. reversibility class, evidence strength, ruin constraint, primary decision owner). Incompatible worldviews run sequential or adversarial — never blended.
- Apply each model fully for its role only. Capture one key insight per model plus what only that model revealed. Do not re-run a model that adds no new insight.
- Synthesize once. Record convergence, divergence, how the conflict rule resolves divergence, and a single combined recommendation with residual uncertainty. Stop when the recommendation is decision-ready or when further models would only reconfirm.
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 · 56 lines · 35 tokens per session scan A 8c37407d77d1
thinking-model-combination is a skill published in the GitHub repository tjboudreaux/cc-thinking-skills (1,293 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 763 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 2026-08-30.
Other skills, from other repositories
forensic-read
Read any document the way a detective reads a witness statement — surface what it is NOT saying. Unlike a summarizer (which tells you what a text says), this skill exposes the subtext: hedging and weasel words, conspicuous omissions, buried leads, frequency tells, tone shifts, and non-answers. Use it on earnings…
pre-mortem
Find what will kill a plan before it's committed to — by assuming it already failed and working backwards to the causes. Based on Gary Klein's pre-mortem technique. Unlike generic "what are the risks?" brainstorming, this skill imagines a specific, vivid failure six months out, reasons back to the most likely causes…
second-order
Reason past the obvious, first-order consequence to the second-, third-, and long-tail effects everyone else stops short of. Where most analysis says "X causes Y", this skill asks "and then what?" — mapping the cascade, surfacing the non-obvious winners and losers, the reflexive responses, and the effects that only…
foundation-models
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.
analytics-interpretation
Interpret app metrics and make data-driven decisions. Covers DAU/MAU, retention, LTV, ARPU, App Store Connect analytics, AARRR funnel analysis, cohort analysis, and diagnostic decision trees. Use when user wants to understand their metrics, diagnose problems, or build a data-driven growth plan.
app-namer
Turn an app idea into validated, App-Store-ready name candidates. Use when the user says "name my app", "what should I call it", "app name ideas", "help me name this app", "is this name available", or needs to pick a brandable, ownable name before reserving it in App Store Connect.