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 yaitio/aichain --skill yait-aichaingit clone --depth 1 https://github.com/yaitio/aichainWrote 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/yaitio/aichain/yait-aichain)<a href="https://agentmods.dev/skills/yaitio/aichain/yait-aichain"><img src="https://agentmods.dev/badge/skills/yaitio/aichain/yait-aichain/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/yaitio/aichain/yait-aichain"><img src="https://agentmods.dev/badge/skills/yaitio/aichain/yait-aichain.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 | $0.00193 | $0.01528 |
| Opus 5.5 | $0.00077 | $0.00611 |
| Sonnet 5.5 | $0.00039 | $0.00306 |
| Haiku 4.5 | $0.00019 | $0.00153 |
Grade A, and why
yait-aichain 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.
This is a copy
95% identical to yait-aichain — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building with yait-aichain
Read llms.txt next to this file before writing code. It holds the real
constructor signatures, one working example per primitive, and the rules that
agents most often get wrong. Names from older tutorials — orchestrator=,
max_steps=, VectorDB, Embedding(...), LocalTools — do not exist and
raise.
Worked programs are in recipes.md next to this file: twenty tasks, each with a
program that solves it. Start from the closest one.
When the package is installed, the documentation of that exact version is
inside it — python -c "import yait_aichain; print(yait_aichain.docs_dir())"
prints the folder, with llms.txt and every page. Prefer it to anything you
remember: it matches the code that will run.
Pick the primitive
| The task | Use |
|---|---|
| One model call — summarise, extract, classify, translate | Skill |
| Known steps in a fixed order, each feeding the next | Chain |
| The same work over many inputs | Pool |
| The next step depends on what the last one returned | Agent with tools |
| A step that is plain code | a function — a chain takes it as a step |
| Something the model may call | @tool on a function; a built-in tool by name |
| An outside API, server or folder | a utility — REST, MCP, Shell, Vectors — and give the agent its tools |
| A picture | image(service, model=…), a tool, not a Skill |
| A run that must stop and continue later, in another process | wait() / gate(tool) and store=FileStore(...) |
Prefer the smallest that fits. A Chain whose steps you can list is cheaper, faster and more predictable than an Agent that rediscovers them.
Tools and utilities
- Built-in tools are made by service name:
search("exa"),fetch("local"),chunk(max_chars=500),embed("openai", model=…),rerank("cohere", model=…),decide("openai", questions=…),speech(…),transcribe(…),image(…). What a tool is goes in the factory; what one call asks goes in.run(input, options). A setting never appears in both. - Your own function is a tool with
@tool; its docstring's first line is the description and its parameters the schema. Call it asfn.run(arg=…). - A utility is an object whose methods your code calls and some of whose
members are tools:
REST(base_url, description=…).endpoint(…),MCP(server).tools,Shell(folder).browse / .read / .write / .run,Vectors(backend, collection=…, description=…).query. Give an agent only the tools it should have —[sh.browse, sh.read]is a read-only agent.
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.
- today Changed · +1 lines abb0135b7c95
- yesterday Changed · +1 lines 053759697d56
- 3d ago Changed · +5 lines 8b4d6c5a84b8
- 4d ago Changed · +23 lines · +21 tokens per session 3329c7f25f60
- 16d ago First seen · 66 lines · 172 tokens per session scan A 310538e5d9f1
yait-aichain is a skill published in the GitHub repository yaitio/aichain (10 stars, last pushed today), licensed MIT. It adds 193 tokens to every session and 1,528 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to yait-aichain, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
data-analyzer
Guidance for analyzing structured data, generating statistics and producing data-driven insights. Use when the user asks to analyze data, compute statistics, find patterns, or generate analytical reports.
unified-llm-api
Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
ape-rsi-toolkit
Reproduce APE (Large Language Models are Human-Level Prompt Engineers, Zhou et al. 2022) on an agent and a frozen Benchmark, or on the house-style brief demo task shipped with this Skill: induce instructions from input/output examples, measure each one, keep the best.
hephaestus-network
Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.
hep-storm
Run a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion.
hep-upload
Publish an Agentlas package to Agent Cloud or the public Hub.