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 vidhunnan/agentic-skills --skill model-strategygit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/model-strategy)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/model-strategy"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/model-strategy/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/vidhunnan/agentic-skills/model-strategy"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/model-strategy.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 | $0.00093 | $0.01526 |
| Opus 5 | $0.00046 | $0.00763 |
| Sonnet 5 | $0.00019 | $0.00305 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
model-strategy 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 9d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
model-strategy
Produces a project-specific docs/MODEL-STRATEGY.md: which Claude model does which kind of work, why, and the review rules that guard the highest-stakes changes. It's a decision aid for both the human directing the work and the agent executing it — so model choice stops being ad-hoc.
Two principles:
- Tailored, not boilerplate. The assignments come from this project's task mix, gathered by a short interview — not a generic template.
- IDs must be current. Model names and IDs change. Confirm the live lineup every run; never emit an ID you didn't verify this session.
Instructions
Step 0 — Detect your surface
Using Bash availability:
- Claude Code — write
docs/MODEL-STRATEGY.mdand register the protocol. - Claude.ai — no filesystem; produce the strategy as a downloadable Markdown artifact and skip CLAUDE.md registration (print the block for the user to paste).
Step 1 — Confirm the current Claude lineup (do NOT hardcode stale IDs)
Model tiers and IDs age fast. Before writing anything, confirm the current lineup:
- If the
claude-apiskill is available, use it as the source of truth for current model names and IDs. - Otherwise, ask the user to confirm the current models, or state clearly which IDs you're using and that they should be verified.
Baseline as of authoring (treat as to be verified, not trusted): Fable 5 = claude-fable-5, Opus 4.8 = claude-opus-4-8, Sonnet 5 = claude-sonnet-5, Haiku 4.5 = claude-haiku-4-5-20251001. Never emit an ID you didn't verify this session.
Step 2 — Create vs. update
- If
docs/MODEL-STRATEGY.mdalready exists: Read it, bump**Version:**, refresh**Last updated:**(date +%Fvia Bash), and update in place with Edit — preserving the tailored assignments unless they've changed. - Otherwise, create it fresh.
Step 3 — Interview the user (tailoring is the whole point)
Ask a short, relevant set (AskUserQuestion on Claude Code; plain text on Claude.ai), then wait for answers:
- What are the project's main task categories? (e.g. UI work, infra/architecture, docs, data migrations, boilerplate.)
- What's the highest-stakes / most review-worthy work — the stuff that must not break?
- How sensitive is this project to latency vs. answer quality?
- Does the app itself ship any AI features? (For the "own AI features" clarity section.)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 118 lines · 93 tokens per session scan A c5d5d0f4dd1f
model-strategy is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 1,526 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…