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 bjorn-ingmanson/thefroject-plugins --skill model-strategygit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-pluginsWrote 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/bjorn-ingmanson/thefroject-plugins/model-strategy)<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/model-strategy"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/model-strategy.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01007 |
| Opus 5 | $0.00024 | $0.00504 |
| Sonnet 5 | $0.00010 | $0.00201 |
| Haiku 4.5 | $0.00005 | $0.00101 |
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 7d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Strategy
Help the user assign the right Claude model to each part of their workspace.
Context Scan
Check context/ for:
- Budget constraints or cost sensitivity
- Task complexity (are most tasks routine or complex?)
- Agent definitions in
.claude/agents/
The Three Models
| Model | Best For | Cost | Speed |
|---|---|---|---|
| Opus 4.8 | Complex reasoning, architecture decisions, code review, strategic planning, multi-step analysis | Highest | Slower |
| Sonnet 4.6 | General-purpose work, writing, editing, most coding tasks, research | Medium | Fast |
| Haiku 4.5 | Simple lookups, formatting, summarization, high-volume repetitive tasks | Lowest | Fastest |
The Advisor Pattern
For complex workflows, pair a cheaper model with Opus as an advisor:
- The executor (Sonnet or Haiku) handles the bulk of the work: calling tools, reading files, writing output
- The advisor (Opus) gets consulted only for hard decisions: architecture choices, ambiguous requirements, complex debugging
This gives you near-Opus quality at a fraction of the cost. The executor does 90% of the work at Sonnet/Haiku rates. Opus only runs for the 10% that actually needs deep reasoning.
Step 1 — Inventory Current Usage
List every agent, command, and recurring task in the workspace. For each one:
| Task/Agent | Current Model | Complexity | Frequency | Recommendation |
|---|---|---|---|---|
| [Name] | [Model or default] | High/Med/Low | Daily/Weekly/Rare | [Suggested model] |
Step 2 — Assign Models
Apply these rules:
Use Opus when:
- The task involves multi-file architecture decisions
- Errors are expensive (production code review, security audit)
- The task requires holding many constraints in mind simultaneously
- Strategic planning, positioning, or complex analysis
Use Sonnet when:
- General coding, writing, editing, and research
- Tasks that need good quality but not frontier reasoning
- Most daily workflows (morning briefs, drafts, reports)
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.
- 7d ago First seen · 107 lines · 49 tokens per session scan A 7b6c21abaa0e
model-strategy is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,007 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 2026-08-31.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…