Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yogasw/wick --skill wick-custom-connectorsgit clone --depth 1 https://github.com/yogasw/wickWrote 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/yogasw/wick/wick-custom-connectors)<a href="https://agentmods.dev/skills/yogasw/wick/wick-custom-connectors"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-custom-connectors/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/yogasw/wick/wick-custom-connectors"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-custom-connectors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00124 | $0.01831 |
| Opus 5 | $0.00062 | $0.00915 |
| Sonnet 5 | $0.00025 | $0.00366 |
| Haiku 4.5 | $0.00012 | $0.00183 |
Grade A, and why
wick-custom-connectors 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 9d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building a custom connector
A custom connector wraps one external API without Go code, a rebuild, or a
redeploy. It is a definition stored in the database that wick replays into the
same registry as built-in connectors, so afterwards the two are
indistinguishable: same tool_id shape, same encrypted fields, same audit
trail, same tag-based access control.
Use wick-connectors for CALLING connectors. This skill is about creating one.
You can build it from chat
The custom-connector connector exposes the whole lifecycle as operations,
so no one has to open the dashboard. Reach it the usual way — wick_list /
wick_search to find its instance, then wick_get for an operation's schema.
| Operation | Does |
|---|---|
def_schema |
the full draft contract — read this first |
def_validate |
dry-run a draft; persists nothing |
def_create |
create from a manual draft |
def_list / def_get |
what exists, and one definition's current shape |
def_update |
replace a definition wholesale (key is immutable) |
def_resync |
re-fetch an MCP server's tool list |
def_set_disabled / def_delete |
serve zero ops, or remove entirely |
mcp_register |
register an external MCP server as a connector |
mcp_set_excluded |
change which of its tools are exposed |
instance_list / instance_create |
the rows that hold credentials |
instance_delete / instance_set_disabled |
remove or park a row |
There is deliberately no cURL-parse operation. Converting a cURL command,
a fetch() snippet, or API docs into the draft shape is your job — that is
what an LLM is for, and it keeps the surface small.
The workflow is not optional
def_create and mcp_register both state it in their own descriptions, and
they mean it:
def_schema— read the contract. Widgets, template syntax, limits, validation rules, categories, a worked example. Do not draft from memory; this skill deliberately does not copy that reference, because a stale copy is worse than a lookup.- Build the draft from whatever the user gave you.
def_validate— same validationdef_createruns, plus a key-availability check. Free, persists nothing.- Present the plan and wait. Name, key, icon, description; every config field with its widget and its secret/required flags; every operation with its description, inputs, and request recipe; and the decisions you made for them — single vs multi-instance, which ops you marked destructive, which fields you made secret, the category.
def_createonly after they say yes.instance_create— a definition serves nothing without a row. Config values go in afterwards, via the dashboard or thewickmanagerconnector'sconnector_set_config.
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.
- 9d ago First seen · 151 lines · 124 tokens per session scan A 2dae2c95ccfd
wick-custom-connectors is a skill published in the GitHub repository yogasw/wick (5 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 1,831 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
omh-code-review
This is a Hermes-native code-review workflow skill.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
workflow-builder
Load before calling build-workflow. Default path for all single-workflow work: new one-off workflows, existing-workflow edits, verification repairs, and workflow-local data tables. Write or edit a workspace source file, run workflow-sdk validate via workspaceexecutecommand, then call build-workflow with filePath. When…
jikegongyuan-perspective
A writing guide based on GeekPark, a Chinese technology publication and entrepreneur community focused on AI, products, startups, and innovation.