caliber

caliber is a skill for Claude Code, Codex from AnkitClassicVision/ankit_shared_skills. It costs 61 tokens per session (671 once invoked), scanned A, original, MIT.

A model-routing skill that matches a task with a suitable combination of AI model, tools, context, retrieval, checks, and human review.

In plain words
What is it for?
Use it to choose an approach for coding, long-context work, local or private models, media tasks, compliance, agents, or high-stakes results.
Why use it?
It helps avoid choosing a model by reputation alone and instead considers the task's difficulty, risk, data, and need for verification.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/ankitclassicvision/ankit_shared_skills/caliber
Any agent
npx skills add AnkitClassicVision/ankit_shared_skills --skill caliber
Clone the repo
git clone --depth 1 https://github.com/AnkitClassicVision/ankit_shared_skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for caliber

README.md
[![agentmods](https://agentmods.dev/badge/skills/ankitclassicvision/ankit_shared_skills/caliber.svg)](https://agentmods.dev/skills/ankitclassicvision/ankit_shared_skills/caliber)
Your own site
<a href="https://agentmods.dev/skills/ankitclassicvision/ankit_shared_skills/caliber"><img src="https://agentmods.dev/badge/skills/ankitclassicvision/ankit_shared_skills/caliber.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00671
Opus 5 $0.00030 $0.00336
Sonnet 5 $0.00012 $0.00134
Haiku 4.5 $0.00006 $0.00067

Measured 6d ago against content hash 3748a9750be3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

caliber 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 6d 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.

caliber/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CALIBER

CALIBER is a model-routing skill. It turns a request into a task-surface demand vector, compares that vector against a model capability matrix, and returns the cheapest constructor that can clear the task with the right defender.

A constructor is:

model + deployment path + context + retrieval + tools + verifier + human gate

Core rule

Do not ask “what is the best model?” Ask:

What is the cheapest allowed constructor whose proven capabilities clear this task's required surfaces and whose defender can verify the result?

Demand levels

Level Name Meaning
-1 deterministic No model; use SQL/rules/regex/script/API directly.
0 tiny Simple classify/extract/rewrite/routing.
1 small Simple reasoning, short summaries, low-stakes drafts.
2 workhorse Normal professional work, routine code/specs, common RAG.
3 strong specialist Harder domain work, repo work, complex synthesis, multimodal reasoning.
4 frontier Expensive-to-fail planning, novel architecture, high-reliability synthesis.
5 orchestrated frontier Decomposition + tools + defenders + human gates.
6 reserved future Future super-frontier/research-grade tier.

Workflow

  1. Gate the deployment pool: regulated/private data, local-only requirements, secrets, production writes, or external sends may restrict allowed models.
  2. Break the task into surfaces such as reasoning, coding, long context, tool use, media, structured output, local/private, or compliance.
  3. Assign required level per surface.
  4. Filter candidate models/deployments from references/model-capability-matrix.yaml.
  5. Attach defenders from references/defender-registry.md.
  6. Pick the cheapest viable constructor.
  7. If the defender fails, escalate one tier or switch specialist lane.

Output shape

Task surfaces:
- <surface>: required level <n> — <why>

Gate pool:
- allowed deployments:
- excluded deployments:

Candidate comparison:
- cheapest viable:
- strongest reliable:
- local/private option:
- specialist option:

Defenders:
- required verifier(s):
- human gate:

Recommendation:
- primary constructor:
- fallback constructor:
- escalation rule:
- evidence confidence:

Read the full file on GitHub · 90 lines

Changes

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.

  1. 6d ago First seen · 90 lines · 61 tokens per session scan A 3748a9750be3

Subscribe to this mod's changes

caliber is a skill published in the GitHub repository AnkitClassicVision/ankit_shared_skills (11 stars, last pushed 25d ago), licensed MIT. It adds 61 tokens to every session and 671 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens