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 ShaftHQ/SHAFT_ENGINE --skill local-runtimesgit clone --depth 1 https://github.com/ShaftHQ/SHAFT_ENGINEWrote 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/shafthq/shaft_engine/local-runtimes)<a href="https://agentmods.dev/skills/shafthq/shaft_engine/local-runtimes"><img src="https://agentmods.dev/badge/skills/shafthq/shaft_engine/local-runtimes/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/shafthq/shaft_engine/local-runtimes"><img src="https://agentmods.dev/badge/skills/shafthq/shaft_engine/local-runtimes.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 | $0.00044 | $0.00426 |
| Opus 5.5 | $0.00018 | $0.00170 |
| Sonnet 5.5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
local-runtimes 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 15d 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.
What it actually says
Local runtimes
Cloud implementers write code directly. A local runtime is optional and only pays for narrow mechanical or offline jobs; never let it review its own diff. Pick one row, then open only that route.
| Need | Route | Open |
|---|---|---|
| Which model size fits this machine | hardware probe | local-coding-delegate |
| Already READY loopback server (Ollama, LM Studio, llamacpp) | loopback | local-openai-compat |
| Standalone FreeToken process | FreeToken | freetoken |
| Frontier MoE through disk/RAM/VRAM tiers | Colibri | colibri |
| OmniRoute runner with delegate continuity | OmniRoute | omniroute |
| Local agents (OpenCode / OSS agency) | agency | local-agency |
FreeToken and Colibri share the loopback runtime contract.
Rules:
- A runtime is used only when its READY probe passes; otherwise stay on the
cloud implementer and record
local: skipped(<reason>)once. - One-shot jobs only: one short spec in, one digest out. No parent relay.
- Avoided-spend metering and USD/EGP lines are required only when a local inference channel was actually used (process owner).
- Descriptions, paths and host exposure live in the catalog.
What ships with it
6 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.
- 15d ago Changed · +2 lines 03b8ea714f42
- 21d ago First seen · 35 lines · 44 tokens per session scan A 1cc5e582af42
local-runtimes is a skill published in the GitHub repository ShaftHQ/SHAFT_ENGINE (414 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 426 once invoked, about $0.0002 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 2026-09-26.
Other skills, from other repositories
azure-ai-vision-imageanalysis-java
Build image analysis applications with Azure AI Vision SDK for Java. Use when implementing image captioning, OCR text extraction, object detection, tagging, or smart cropping.
tsp-type-override
Override TypeSpec types with Java-native types (e.g. OffsetDateTime, DayOfWeek) using @@alternateType in a client.java.tsp file. Use when a TypeSpec model field has an incorrect or too-generic type that should map to a specific Java type.
tsp-naming-collision
Fix Java codegen parameter names that end with a numeric suffix (e.g. createAgentRequest1) caused by TypeSpec model names colliding with synthetic body type names. Use when generated Java client methods have parameter names ending in '1'.
dup-classes
Verify whether generated Java classes duplicate openai-java models by comparing fields/types (names may differ). Use when checking for duplicate model coverage.
ax-java-gen
Use when writing Java code with dev.axllm:ax for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
rag-assistant
Knowledge base assistant that retrieves and cites documents from a curated index. Use when answering questions that must be grounded in specific source material with citations.