agentmods.dev

hecate-providers

hecate-providers is a skill for Claude Code, Codex from hecatehq/hecate. It costs 55 tokens per session (2,411 once invoked), scanned A, original, MIT.

A development skill for the internal provider layer of Hecate, a Go backend that connects to AI services. It covers outbound adapters for OpenAI-compatible services and Anthropic, plus changes that pass data between the API and providers.

In plain words
What is it for?
It is for modifying provider adapters, model discovery and caching, provider health checks, registries, streaming interfaces, and API-to-provider data fields.
Why use it?
It helps keep provider integrations consistent when adding fields, capabilities, health checks, discovery, or runtime routing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Plan first.** Wire-field additions cross `pkg/types/`, `internal/api/`, `internal/providers/`, and tests at every layer — exactly the cross-package ripple tha.

not rated 24repo +1 yesterday A scan SkillSpector: pass 55 tokens original MIT

Good fit It is for modifying provider adapters, model discovery and caching, provider health checks, registries, streaming interfaces, and API-to-provider data fields.

Compare 6 skills from other repositories ↓
View source ↗ hecatehq/hecate hecate.sh
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/hecatehq/hecate
agentmods
npx agentmods add skills/hecatehq/hecate/providers

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for hecate-providers

README.md
[![agentmods](https://agentmods.dev/badge/skills/hecatehq/hecate/providers/github.svg)](https://agentmods.dev/skills/hecatehq/hecate/providers)
Your own site
<a href="https://agentmods.dev/skills/hecatehq/hecate/providers"><img src="https://agentmods.dev/badge/skills/hecatehq/hecate/providers/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.

agentmods 80×15 button for hecate-providers

Your own site · 80×15
<a href="https://agentmods.dev/skills/hecatehq/hecate/providers"><img src="https://agentmods.dev/badge/skills/hecatehq/hecate/providers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.02411
Opus 5.5 $0.00022 $0.00964
Sonnet 5.5 $0.00011 $0.00482
Haiku 4.5 $0.00006 $0.00241

Measured 2mo ago against content hash 430ed50ceb37, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hecate-providers 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 2mo 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.

docs-ai/skills/providers/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hecate providers skill

Use this skill for work in internal/providers/ and any change that crosses the api↔providers boundary. Backend-wide rules are in ../backend/SKILL.md; field-shape rules in ../../core/engineering-standards.md; the race-suite floor in ../../core/verification.md.

Layout

provider.go               Provider / Streamer / Capabilities interfaces
openai.go                 OpenAI-compat adapter (real OpenAI, Together, Groq, Ollama, vLLM)
openai_transcription.go   Explicit OpenAI-compatible audio transcription adapter
anthropic.go              Native Anthropic Messages API adapter
runtime_manager.go        provider catalog + protocol → adapter dispatch
capabilities_cache.go     /v1/models discovery + TTL cache
discovery_policy.go       when to discover, when to use static caps
health.go                 provider health probe + circuit
mutable_registry.go       control-plane mutation surface

Test helpers live in provider_test_helpers_test.go and tooluse_test.go (the newAnthropicTestProvider helper is there, not in anthropic_test.go).

The capital/lowercase parallel-struct rule

internal/api/openai.go defines OpenAIChatMessage, OpenAIMessageContent, OpenAIContentBlock (capital). This package defines openAIChatMessage, openAIMessageContent, openAIContentBlock (lowercase).

Same JSON shape, two packages, intentional. Keeps internal/providers/ free of internal/api/ imports — the wire shapes evolve independently. When you add a field on one side, mirror it on the other.

The polymorphic content type (UnmarshalJSON / MarshalJSON for string-or-array-or-null) is duplicated for the same reason. Don't try to share — the duplication is the contract. Sharing would re-introduce the import.

The seven-step chain

Adding a passthrough wire field. This is the most-redone task in the providers package; the chain is canonical and lives here.

Read the full file on GitHub · 128 lines

Changes

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.

  1. 2mo ago First seen · 128 lines · 55 tokens per session scan A 430ed50ceb37

Subscribe to this mod's changes

hecate-providers is a skill published in the GitHub repository hecatehq/hecate (24 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,411 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 2026-08-30.

Backend and APIsGoLLMLanguagesaiai-gatewayai-runtimemcp-clientopentelemetry
Related

hecate-providers compared with skills from other repositories

hecate-providers next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hecate-providershecatehq/hecateSkill24yesterdayMITA55Claude Code, Codex
rust-gatewayBerriAI/litellmSkill63kyesterdaynoneA70Claude Code, Codex
go-programming-expertroedyrustam/vibes-plugSkill121yesterdayMITA45Cursor
go-expertpersonamanagmentlayer/pclSkill4411d agoApache-2.0A65Claude Code
go-functional-optionscxuu/golang-skillsSkill1904mo agoApache-2.0A65Claude Code
go-contextcxuu/golang-skillsSkill1904mo agoApache-2.0A73Claude Code
pn-go-scaffoldingperniemann/pnCoreSkill05d agoMITA51Cursor