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 megamen32/LastHumanCommit --skill model-routinggit clone --depth 1 https://github.com/megamen32/LastHumanCommitWrote 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/megamen32/lasthumancommit/model-routing)<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/model-routing"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/model-routing/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/megamen32/lasthumancommit/model-routing"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/model-routing.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 | $0.00029 | $0.01568 |
| Opus 5.5 | $0.00012 | $0.00627 |
| Sonnet 5.5 | $0.00006 | $0.00314 |
| Haiku 4.5 | $0.00003 | $0.00157 |
Grade A, and why
model-routing 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 today.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model allocation is a feedback loop
Use for initial allocation, material re-decomposition, a capability failure or reviewing which model assignments actually worked. Do not perform a full model market survey before every task.
Existing Herder is the execution path
Use the already connected Agent Herder MCP: no new tool, delegation wrapper,
router agent or role×model profile matrix. Role, model and harness are separate
choices. Before a multi-model dispatch read the current Herder tool schema; use
new_or_resume to launch/deliver once, or create_session then its existing
message transport. Pass explicit model, absolute canonical cwd and a stable
assignment name; reuse the same inputId on delivery retries. Never change
the parent's or global model merely to set a child's model.
Source/parent identity comes from the native current-session context, never from
a guessed last-active session. Supply sourceSessionId/sourceHarness for a
real continuation/replacement when the schema calls for it; do not invent them
or treat source metadata as proof of an OpenCode-native child relationship.
Respect manual Stop. A fresh independent assignment has a unique stable name;
new_or_resume must not reuse a previous tester's discussion as Zero Knowledge.
Do not set humanRequested=true for autonomous retries or delegation.
The message contains the current canonical role, bounded task, tangible result, needed inputs, scope/permissions and the actual acceptance check. Worker and technical Reviewer can read the relevant source. A fresh Zero Knowledge tester receives only a realistic persona/goal, product entrypoint and permitted demo access: no parent chat, implementation/task-card answers or prior verdicts. A different model alone is not an independent context. All children remain parts of the original goal and budget; dispatch does not reset the parent clock.
For this user's server-100 installation the desired model routes are:
| Model | Harness | Model selection |
|---|---|---|
| GPT-6.1 Sol | codex | gpt-6.1-sol (existing native ChatGPT login) |
| GPT-6 Luna | opencode | omniroute/cx/gpt-6-luna |
| MiniMax 3.1 Preview | opencode | omniroute/minimax/MiniMax-M3.1-Flash-Preview |
| GLM 5.3 Flash | opencode | omniroute/zc/glm-5.3-flash |
| GLM 5.3 | opencode | omniroute/zc/glm-5.3 |
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.
- today Changed · +53 lines 31058d67ebd7
- 1mo ago Changed · +16 lines 2f6ebce5fb75
- 1mo ago Changed 6535ce2aee8c
- 1mo ago First seen · 64 lines · 29 tokens per session scan A c38ca3e98083
model-routing is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,568 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…