pick-model SKILL.md skillA

pick-model from pantheon-org/tekhne is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pantheon-org/tekhne/pick-model@git:20261007.83cf275

Pins git:20261007.83cf275 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pantheon-org/tekhne
Path
skills/agentic-harness/pick-model/SKILL.md
Versions recorded
3
Latest version
git:20261007.83cf275, committed Oct 7, 2026
First version recorded
Apr 11, 2026
Size
8,254 bytes
Repository stars
10
License
MIT

Recommend the cheapest Claude model tier (Haiku, Sonnet, Opus) that still meets a task's quality bar, using a task-type matrix plus complexity escalators (scope, stakes, ambiguity, stakeholders). Use when asked "which model", "pick model", "model for", or before starting a costly task. Covers technical, business, creative work.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Pick Model

Classify the task, apply the escalators, then recommend the cheapest Claude tier that meets the quality requirement.

## Mindset

- Right-size and do not default up. Keep to the cheapest tier that meets the quality bar. Escalating after a failed attempt costs one retry; an Opus habit costs every call.
- Judge reasoning demand, not volume. Pass a long document to a summariser at the same tier as a short one.
- Name tiers (fast, balanced, reasoning) before model names. Model names are retired and renamed; tier meaning lasts.
- Escalate with a stated reason. Always name the signal that moved the tier.

## When to Use

- Use it when a user asks which model fits a task, before the work starts.
- Use it when an agent must assign a model to a sub-task without a human in the loop.
- Use it when a pipeline or batch job overspends on a frontier model for simple work.
- Use it when the cost against capability trade-off must be explicit, for example in production routing.

## When Not to Use

- Do not use it when infrastructure or an explicit user instruction already fixes the model.
- Do not use it once the task is finished, because the choice is moot.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add pantheon-org/tekhne/pick-model@sha256:c679ebce6c2630c1

The line at the top of this page pins the label git:20261007.83cf275, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ilz5xy54cgrvm74k.svg)](https://markdownregistry.com/a/art_ilz5xy54cgrvm74k)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Apr 11, 2026 and Oct 7, 2026, about one every 89 days.

versioncommittedcommitsizeaudit
git:20261007.83cf275 latest2026-10-07 83cf275 8,254 BA view · diff
git:20260923.7852cb42026-09-23 7852cb4 13,385 BA view · diff
git:20260411.33e05462026-04-11 33e0546 12,572 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8254 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

GitHub

pantheon-org/tekhne · 10 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ilz5xy54cgrvm74k
GET https://markdownregistry.com/api/v1/resolve?ref=pantheon-org/tekhne/pick-model
GET https://markdownregistry.com/api/v1/blob/c679ebce6c2630c1851cbf1727892bfa5dac0d27a91ec3cc4107fc66bdf63bb8

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from pantheon-org/tekhne

AGENTS.md AGENTS.md file
pantheon-org/tekhne · AGENTS.md
git:20261021.d128b5f · audit A · 10 stars
CLAUDE.md CLAUDE.md file
pantheon-org/tekhne · CLAUDE.md
git:20261007.fce3c8c · audit B · 10 stars
agents-md SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/agents-md/SKILL.md · Create and maintain AGENTS.md documentation for simple projects, complex monorepos, deterministic discovery, scoped…
git:20261004.cc33b37 · audit A · 10 stars
cache-audit SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/cache-audit/SKILL.md · Audit your Claude Code setup against prompt caching best practices. Checks ordering, tool stability, dynamic content…
git:20260710.a38941a · audit A · 10 stars
context-radar-audit SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/context-radar-audit/SKILL.md
git:20260928.242d7c2 · audit B · 10 stars
create-context SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/create-context/SKILL.md · Create the baseline session context from the in-folder of raw project documents, classifying each file by priority…
git:20261007.83cf275 · audit A · 10 stars
guided-interview SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/guided-interview/SKILL.md · Conduct a structured, one-question-at-a-time interview to explore a specific topic or decision — each question offers…
git:20260824.4a8d48e · audit A · 10 stars
handover-document-creator SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/handover-document-creator/SKILL.md
git:20261007.1762166 · audit B · 10 stars
load-context SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/load-context/SKILL.md · Resume session from CONTEXT-llm.md. Use when resuming work, loading saved context, continuing a previous session…
git:20261007.83cf275 · audit A · 10 stars
opencode-build-plugins SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/opencode-toolkit/build-plugins/SKILL.md · Create OpenCode plugins using the opencode-ai/plugin SDK. Use when user wants to build a plugin, extend OpenCode…
git:20260314.95ea1b2 · audit A · 10 stars
opencode-build-tool SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/opencode-toolkit/build-tool/SKILL.md · Build custom tools and plugins using the OpenCode SDK packages. Use when creating custom tools, implementing tool…
git:20260314.95ea1b2 · audit A · 10 stars
opencode-configure SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/opencode-toolkit/configure/SKILL.md · Configure OpenCode via opencode.json and AGENTS.md with deterministic provider setup, model selection, permission…
git:20261004.cc33b37 · audit A · 10 stars

Every file in pantheon-org/tekhne

Browse by kind, by grade A, or by owner.