DeepChat Provider Integration

What it does

When your agent uses it

• Adding a new OpenAI-compatible provider to DeepChat
• Mapping a provider onto an existing native transport
• Writing a special provider adapter for unusual auth or streaming
• Adding provider auth, model catalog mapping or profile config

Example prompts

• “Add a new OpenAI-compatible provider called acme-ai to DeepChat with a default base URL and API key auth.”
• “Map this provider to the existing Anthropic transport and add the registry entry and tests.”
• “This provider uses OAuth and a custom streaming format; scaffold a special provider adapter.”

Requirements

• A checkout of the DeepChat repository

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Read docs/features/provider-runtime/spec.md when the provider work touches the provider runtime
2. 2Inspect the current provider files before editing
3. 3Classify the request into one supported path.
4. 4Add the smallest explicit source changes for that path.
5. 5After implementation, assess provider creation, auth handling, and model discovery for durable
6. 6Update an active SDD plan.md as coherent implementation slices land, when one exists. For a
7. 7Run

What it can do on your machine

Read from SKILL.md and the folder at commit bfa6d76. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pnpm

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

DeepChat Provider Integration loads about 1.2k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 496 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~69

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ThinkInAIXYZ/deepchat at commit bfa6d76, republished under its Apache-2.0 licence (© ThinkInAIXYZ). 496 words, ~1,169 tokens.

name

add-provider

description

Add a DeepChat LLM provider through explicit reviewed source changes. Use when a developer asks Codex to add a provider, provider profile, upstream provider config, model catalog mapping, provider auth behavior, or a special provider adapter in this repository.

pnpm run format
pnpm run i18n
pnpm run lint
pnpm run typecheck

© ThinkInAIXYZ, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/add-provider of ThinkInAIXYZ/deepchat.

Open the folder on GitHubat commit bfa6d76