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 synthesisengineering/synthesis-skills --skill synthesis-model-tiersgit clone --depth 1 https://github.com/synthesisengineering/synthesis-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/synthesisengineering/synthesis-skills/synthesis-model-tiers)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-model-tiers"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-model-tiers/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/synthesisengineering/synthesis-skills/synthesis-model-tiers"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-model-tiers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00154 | $0.02077 |
| Opus 5 | $0.00077 | $0.01038 |
| Sonnet 5 | $0.00031 | $0.00415 |
| Haiku 4.5 | $0.00015 | $0.00208 |
Grade A, and why
synthesis-model-tiers 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 12d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Model Tiers
A tiny convention that keeps model names out of everything except one file.
Skills, project context files, agent memory, and standing instructions reference role labels; the labels resolve to current model identifiers in tiers.yaml. When a vendor ships a new generation, one file changes and every consumer is current.
The three roles
| Role | Use for | Character |
|---|---|---|
| judgment | Judgment calls, novel patterns, skill/script authorship, cross-system changes — anywhere being wrong is expensive | The most capable model you can afford |
| routine | Routine rule-following execution: daily sweeps, mechanical runs, well-templated work | The balanced default |
| bulk | High-volume, low-stakes work: classification at scale, summarization drips | The cheapest adequate option |
Three roles, deliberately — even when a vendor's ladder has four or five rungs. Roles describe the work, not the vendor's catalog.
Choosing a role: diagnostic difficulty, not apparent size
The most common misroute is sending a small-sounding task to a cheap tier. Size is not the variable. Whether the cause is known is the variable.
- Cause known → the specification is settled and the work is execution: apply this rename, run this suite, add this row, reformat these files. This is
routineorbulk. - Cause unknown → the work is diagnosis, whatever its apparent size. Anything phrased as a symptom — "X isn't working," "this broke," "why is it doing that," "the file won't open" — is a differential over a chain of candidate causes. Cost scales with the search, not with the fix. This is
judgmenteven when the subject is one file.
Cheap reasoning on a diagnosis does not return a smaller correct answer. It takes the first plausible branch and commits — and the confidence is what gets the wrong answer written, committed, and pushed.
Three properties force judgment regardless of how small the request sounds. Any one is sufficient:
What ships with it
3 files 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.
- 12d ago First seen · 93 lines · 154 tokens per session scan A 9fe259788452
synthesis-model-tiers is a skill published in the GitHub repository synthesisengineering/synthesis-skills (19 stars, last pushed today), licensed Apache-2.0. It adds 154 tokens to every session and 2,077 once invoked, about $0.0008 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.
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…
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.
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…
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…