reasoning-models skillA
reasoning-models is agent-read markdown (skill) from jnpiyush/agentx: Use reasoning / thinking models (OpenAI o-series, Anthropic extended thinking, DeepSeek R1, Gemini Thinking) effectively. Covers when to choose reasoning vs fast models, prompt patterns for reasoners, reasoning_effort / thinking budget controls, structured outputs with reasoning, cost/latency trade-offs, and combining reasoners with fast models..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Reasoning Models
> **Purpose**: Get reliable answers from reasoning models without overspending or stalling on tasks that do not need them.
---
## When to Use This Skill
- Choosing between a reasoning model (o3, GPT-5 thinking, Claude extended thinking, DeepSeek R1, Gemini Thinking) and a fast model
- Setting `reasoning_effort` (low / medium / high) or thinking-token budgets
- Designing prompts for reasoning models (different from chat models)
- Combining reasoners (planner) with fast models (executor)
- Diagnosing high cost or latency on reasoning calls
## When NOT to Use a Reasoning Model
- Routine extraction, summarization, classification -- a fast model is cheaper and faster
- Strict latency budget (<2s end-to-end) -- reasoning models add seconds
- Tool-use-heavy loops where each turn is short -- fast model + scaffolding is usually better
---
## Decision Tree
```
Is the task hard? (multi-step reasoning, math, planning, code refactor across files,
ambiguous spec, agent strategy)
+- No -> Fast model (gpt-5, claude-haiku-4.5, gemini-2.5-flash)
+- Yes -> Reasoning model
+- Need fast feedback loop? -> Reasoning effort = low / medium
…Read the whole file at its exact version.
How to install
mdr add jnpiyush/agentx/reasoning-models@v1.0.0mdr add jnpiyush/agentx/reasoning-models@sha256:0ae532f95ca05622Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_247als2qv3izkklp)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-15 | f17c505 | 5,092 B | A | view · diff |
| v1.0.0 | 2026-06-23 | bab3a1b | 5,090 B | A | view · diff |
| v1.0.0 | 2026-04-30 | 4f38ce8 | 5,091 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5092 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jnpiyush/agentx · 16 stars · license Apache-2.0 · pushed 2026-09-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_247als2qv3izkklp GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/reasoning-models GET https://markdownregistry.com/api/v1/blob/0ae532f95ca056224357ce99f03361618af62e6a13431f5fe98b6a5443351eb9
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.