Borrowing it
Nothing to install: this file belongs to crystal-autobot/autobot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/crystal-autobot/autobot/main/.claude/skills/autobot-provider/SKILL.mdgit clone --depth 1 https://github.com/crystal-autobot/autobotWrote 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/crystal-autobot/autobot/autobot-provider)<a href="https://agentmods.dev/skills/crystal-autobot/autobot/autobot-provider"><img src="https://agentmods.dev/badge/skills/crystal-autobot/autobot/autobot-provider/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/crystal-autobot/autobot/autobot-provider"><img src="https://agentmods.dev/badge/skills/crystal-autobot/autobot/autobot-provider.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 | $0.00015 | $0.00793 |
| Opus 5 | $0.00008 | $0.00396 |
| Sonnet 5 | $0.00003 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
autobot-provider 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a New LLM Provider
Files to Create/Modify
-
Create provider implementation:
src/autobot/providers/<name>_provider.cr- Inherit from
HttpProvideror implementProviderinterface
-
Register provider:
- Add a new
ProviderSpecto thePROVIDERSlist insrc/autobot/providers/registry.cr. - Ensure keywords and API URL are correctly specified.
- Add a new
-
Add configuration schema:
- Update
src/autobot/config/schema.crwith provider config if needed. - Most HTTP providers work automatically if they follow OpenAI compatibility.
- Update
-
Create tests:
spec/autobot/providers/<name>_provider_spec.cr- Test provider registration in
registry_spec.cr. - Test API integration (mocked).
-
Add documentation:
docs/<name>.md- Provider setup guide.- Update
docs/providers.md- Add to provider comparison.
Provider Implementation Template
# src/autobot/providers/<name>_provider.cr
module Autobot
module Providers
class <Name>Provider < HttpProvider
def initialize(
api_key : String,
api_base : String? = nil,
@model : String = "default-model",
@extra_headers = {} of String => String,
provider_name : String? = nil,
)
super(api_key, api_base)
@gateway = Providers.find_gateway(provider_name, api_key, api_base)
end
def chat(
messages : Array(Hash(String, JSON::Any)),
tools : Array(Hash(String, JSON::Any))? = nil,
model : String? = nil,
max_tokens : Int32 = DEFAULT_MAX_TOKENS,
temperature : Float64 = DEFAULT_TEMPERATURE,
) : Response
# Implement API-specific logic here
# Or call super for OpenAI-compatible APIs
super
end
def default_model : String
@model
end
end
end
end
Alternative: Non-HTTP Provider
For providers with non-standard APIs (like AWS Bedrock), inherit directly from Provider:
class BedrockProvider < Provider
# Implement abstract methods directly
# See src/autobot/providers/bedrock_provider.cr for full example
end
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 · 126 lines · 15 tokens per session scan A 90e4fad5314d
autobot-provider is a skill published in the GitHub repository crystal-autobot/autobot (45 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 793 once invoked, about $0.0001 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
agentfield
Design and ship a multi-agent system on AgentField. Use when the user asks to build, scaffold, design, or run an agent, reasoner network, multi-agent backend, or 'an agent that does X' — whenever the work would otherwise be a single LLM call or a flat LangChain/CrewAI/AutoGen chain. The skill produces composite…
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.
routing-card-authoring
Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.
hephaestus-upload
Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.
hep-storm
Run a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion.
hep-network
Staff a task from registered Local, owner Cloud, and public Hub agents.