What is add-provider?

A step-by-step guide for adding a maintained Connecta provider in its own source folder. A provider is a connector to an external service, and the guide covers its factory, documentation, fixtures, and records of the vendor's interface.

It is for creating provider connectors, documenting how they connect, adding test fixtures, and recording vendor-contract drift.

It turns a provider addition into a repeatable process and preserves evidence when the external service changes. This helps prevent broken imports, undocumented behavior, and unreviewed size or contract changes.

How zackbart/connecta configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zackbart/connecta. 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/zackbart/connecta/main/.claude/skills/add-provider/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/zackbart/connecta

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/zackbart/connecta/add-provider/github.svg)](https://agentmods.dev/skills/zackbart/connecta/add-provider)

Your own site

<a href="https://agentmods.dev/skills/zackbart/connecta/add-provider"><img src="https://agentmods.dev/badge/skills/zackbart/connecta/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/zackbart/connecta/add-provider"><img src="https://agentmods.dev/badge/skills/zackbart/connecta/add-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,972 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	$0.00051	$0.08972
Opus 5.5	$0.00020	$0.03589
Sonnet 5.5	$0.00010	$0.01794
Haiku 4.5	$0.00005	$0.00897

Measured yesterday against content hash b886a9d88427, 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 · 615 lines

How it starts

The opening of the file, as written. The whole thing — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add or change a maintained provider

Read PRINCIPLES.md, documentation/architecture.md (Providers and reviewed classification; Contributor provider kit), and documentation/providers.md. This skill describes the current provider workflow. Decisions 0010, 0011 and 0012 record its design history.

test/provider-standard.node.test.ts enforces layout (L), evidence (E), drift (D), guide (G) and surface (S) rules on every provider folder; test/provider-conventions.test.ts applies the tool conventions on Node. The generator refuses D or G violations before writing any output.

Workflow

Use the standard folder below and defineApiProvider from src/http/provider.ts for an API implementation. It builds on defineProvider, validates construction and derives generation facts. Import internal kit modules by explicit source path. Deployment factories return ordinary Connectors; published declarations name no Effect type.
Review the vendor contract, classification, credential withholding and paging before implementing tools. Declare publicIdentifierHeaders only for a header the vendor's contract shows names the account rather than proving it, and cite that in evidence/review.md; a header's name is never evidence. Reviewed path calls need an indexed safety resolver; caller-supplied templates never establish policy. An explicit global review applies only where unindexed paths are permitted.
Reuse compact stateful provider outcomes through published deployment adapters. Grade independent fake state, physical requests, final answers, identity and secrecy; prove no-op and fabricated answers fail. Cover native Workers boundaries where applicable and keep focused vendor fault probes. Do not add characterization goldens or migration exemptions.
Generate indexes, evidence and guides, run the verification below, and record changed outcomes for each affected provider. For breaking tool, argument, envelope or guide changes, map the changes in a fragment following AGENTS.md and update installed migration instructions.

Read the full file on GitHub · 615 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.

yesterday Changed · +7 lines b886a9d88427
2d ago Changed · +3 lines 4111b54a2f31
6d ago Changed · +10 lines a921e23ae200
8d ago Changed · +50 lines · -4 tokens per session 03f8134753a0
9d ago Changed · -66 lines · -3 tokens per session 711613c13dd1
10d ago Changed · +8 lines 284dc9a82e86
12d ago Changed · +47 lines 06da3e08aba6
13d ago Changed · +80 lines 9b10655c9dac
15d ago Changed · -28 lines · -2 tokens per session 57e98667aab8
16d ago First seen · 504 lines · 60 tokens per session scan A 5b4f0ed468e8

Subscribe to this mod's changes

add-provider is a skill published in the GitHub repository zackbart/connecta (0 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 8,972 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 2026-10-08.

Backend and APIs Testing

add-provider next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
add-providerzackbart/connecta	Skill	0	yesterday	MIT	A	51	Claude Code
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code
fastapi-router-pymicrosoft/skills	Skill	3.2k	yesterday	MIT	A	46	Claude Code
dev-runtimelangwatch/langwatch	Skill	5.0k	yesterday	Apache-2.0	A	172	Claude Code
api-designericrisco/rsc-harness	Skill	503	2d ago	MIT	A	105	Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1	Skill	252	yesterday	MIT	A	106	Claude Code

connecta: Skill for Claude Code