What is add-provider?

A procedure for adding an AI model provider to Synapse's local-build option. It covers provider registration, capability settings, adapters for incompatible APIs, tests, and documentation.

Use it when adding support for a new language-model provider or inference host used by local builds.

It provides a consistent way to support another model service without missing configuration, compatibility code, tests, or user documentation.

How 2ndbrainlabs-ai/synapse-cli-ts configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 2ndbrainlabs-ai/synapse-cli-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/2ndbrainlabs-ai/synapse-cli-ts/main/.claude/skills/add-provider/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/2ndbrainlabs-ai/synapse-cli-ts

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/2ndbrainlabs-ai/synapse-cli-ts/add-provider/github.svg)](https://agentmods.dev/skills/2ndbrainlabs-ai/synapse-cli-ts/add-provider)

Your own site

<a href="https://agentmods.dev/skills/2ndbrainlabs-ai/synapse-cli-ts/add-provider"><img src="https://agentmods.dev/badge/skills/2ndbrainlabs-ai/synapse-cli-ts/add-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/2ndbrainlabs-ai/synapse-cli-ts/add-provider"><img src="https://agentmods.dev/badge/skills/2ndbrainlabs-ai/synapse-cli-ts/add-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 178 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.00178
Opus 5.5	$0.00019	$0.00071
Sonnet 5.5	$0.00010	$0.00036
Haiku 4.5	$0.00005	$0.00018

Measured yesterday against content hash 5290856bc79d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-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 yesterday.

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.

.claude/skills/add-provider/SKILL.md · 15 lines

What it actually says

add-provider

This skill is a thin wrapper. The procedure lives in a shared, agent-agnostic playbook, so Claude Code, Cursor, Codex and the rest follow the same steps.

Read AGENTS.md (hard rules) if it isn't already in context.
Read and follow docs/playbooks/add-provider.md step by step. It links to the reference docs you need.
Input from the user: $ARGUMENTS

If this wrapper and the playbook ever disagree, the playbook wins. Fix the procedure in the playbook, not here.

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.

yesterday First seen · 15 lines · 0 tokens per session scan A 5290856bc79d

Subscribe to this mod's changes

add-provider is a skill published in the GitHub repository 2ndbrainlabs-ai/synapse-cli-ts (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 178 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 2026-11-09.

Building agents Code Generation Data and AI agentic-ai cli mcp model-context-protocol

add-provider next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
add-provider2ndbrainlabs-ai/synapse-cli-ts	Skill	6	yesterday	Apache-2.0	A	48	Claude Code
building-agentsericrisco/rsc-harness	Skill	573	yesterday	MIT	A	85	Claude Code, Codex
open-weightsericrisco/rsc-harness	Skill	573	yesterday	MIT	A	146	Claude Code, Codex
agent-evalericrisco/rsc-harness	Skill	573	yesterday	MIT	A	79	Claude Code, Codex
prompt-engineeringericrisco/rsc-harness	Skill	573	yesterday	MIT	A	83	Claude Code, Codex
llm-runtimeWrongStack/WrongStack	Skill	407	today	MIT	A	97	Claude Code, Codex
ollamaericrisco/rsc-harness	Skill	573	yesterday	MIT	B	93	Claude Code, Codex

synapse-cli-ts: Skill for Claude Code