Install the "wakewire-setup" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/glenncalleja/wakewire/skills/wakewire-setup into .claude/skills/wakewire-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wakewire-setup", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill wakewire-setup -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "wakewire-setup" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/glenncalleja/wakewire/skills/wakewire-setup into .agents/skills/wakewire-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wakewire-setup", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill wakewire-setup -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "wakewire-setup" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/glenncalleja/wakewire/skills/wakewire-setup into .cursor/skills/wakewire-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wakewire-setup", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill wakewire-setup -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "wakewire-setup" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/glenncalleja/wakewire/skills/wakewire-setup into .gemini/skills/wakewire-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wakewire-setup", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill wakewire-setup -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "wakewire-setup" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/glenncalleja/wakewire/skills/wakewire-setup into .github/skills/wakewire-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wakewire-setup", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill wakewire-setup -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "wakewire-setup" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/glenncalleja/wakewire/skills/wakewire-setup into .opencode/skills/wakewire-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wakewire-setup", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
wakewire-setup
GitHub stars
1.2k
Token cost
~1.4k tokens
SKILL.md length
684 words
Files
1
Skills in repo
736
Repo updated
First seen
Licence
Apache-2.0
At a glance
Set up wakewire end to end — install/start the local daemon, wire a first GitHub or Gmail route into a Codex thread, and verify with a test delivery.
Works in 5 steps: Check the daemon → Resolve the target thread → Set up the source → …
The user wants external events (GitHub pushes/PRs/issues
SKILL.md covers 0. Check the daemon, 1. Resolve the target thread, 2. Set up the source and 3. Create the route, plus 1 more section
Calls npm
What it does
Wakewire Setup is an agent skill from hashgraph-online/awesome-codex-plugins. Set up wakewire end to end — install/start the local daemon, wire a first GitHub or Gmail route into a Codex thread, and verify with a test delivery. Use when the user wants external events (GitHub pushes/PRs/issues, emails) delivered into their Codex threads, or when wakewire tools report the daemon is not running.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Productivity & Automation, covering Email management. It works with GitHub and Gmail. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.
When your agent uses it
The user wants external events (GitHub pushes/PRs/issues
Emails) delivered into their Codex threads
Wakewire tools report the daemon is not running
Example prompts
“/wakewire-setup”
Requirements
Node.js
Workflow steps
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 16b4156. 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:
npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, 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
Wakewire Setup loads about 1.4k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 684 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~83
When it runs· the whole SKILL.md, loaded when a task matches
~1.4k
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
Auto-check passed
The automated check found no risky patterns in SKILL.md.
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.
Download SKILL.mdSave it as .claude/skills/wakewire-setup/SKILL.md (or your agent's skills folder).
name
wakewire-setup
description
Set up wakewire end to end — install/start the local daemon, wire a first GitHub or Gmail route into a Codex thread, and verify with a test delivery. Use when the user wants external events (GitHub pushes/PRs/issues, emails) delivered into their Codex threads, or when wakewire tools report the daemon is not running.
You are configuring wakewire, a local daemon that pushes external events into Codex threads. Configuration happens through the wakewire_* MCP tools; this skill is the runbook.
0. Check the daemon
Call wakewire_status.
If it errors with "daemon is not running", have the user run in a terminal:
npm install -g wakewire
wakewire init
wakewire start --detach # or: wakewire service install (starts at login)
Then call wakewire_status again.
Confirm adapter.codexReachable is true. If not, codex isn't on PATH for the daemon — ask the user how they installed Codex.
1. Resolve the target thread
Most users want events delivered "into this thread". MCP tools cannot see the current thread id, but shell commands can:
Run this shell command: echo "$CODEX_THREAD_ID"
Use that value as target: {"type":"thread","threadId":"<value>"}.
If the user prefers fresh threads per event (e.g. "spawn a worktree and investigate each failure"), use target: {"type":"new-thread","cwd":"<abs repo path>","worktree":true} instead.
2. Set up the source
GitHub
Call wakewire_source_setup_github with the repo (e.g. {"repo":"acme/api"}). It creates a smee.io relay channel and returns a webhook URL, a secret, and step-by-step instructions.
Relay those instructions to the user verbatim — they add the webhook in the repo settings. Warn them: smee.io is a public relay; payloads transit it, which is why wakewire verifies HMAC signatures and why private-repo users may prefer {"mode":"listen"} with their own tunnel.
GitHub sends a ping on creation; wakewire_status should show the source received it.
Gmail
Ask which Gmail label to watch (never watch everything — a label is required) and the Gmail address.
Ask which auth they prefer:
App password (simpler): call wakewire_source_setup_gmail with {label, user, authKind: "imap-password"}. The user creates an app password at https://myaccount.google.com/apppasswords (needs 2-Step Verification) and runs wakewire auth imap in a terminal to store it. Also works for non-Gmail IMAP servers via host/port.
OAuth: call wakewire_source_setup_gmail with {label, user}. The user creates their own Google OAuth client (Desktop type) and runs wakewire auth gmail in a terminal to complete consent.
Relay the returned instructions verbatim either way.
Slack
Call wakewire_source_setup_slack (optionally with {team: "workspace-name"}). It returns the one-time Slack app setup: create an app, enable Socket Mode (app-level token, connections:write), add bot scopes (app_mentions:read, channels:history, channels:read, users:read), subscribe to bot events (app_mention, message.channels), install, invite the bot to channels.
Relay those steps verbatim, then have the user run wakewire auth slack in a terminal — both tokens go in via hidden prompts, never through this conversation.
Slack routes match app_mention by default (any channel the bot is in); matching plain message events requires naming channels. Bot-posted messages are skipped by default.
Show full SKILL.md (298 more words)Show less
Any other provider (Sentry, Grafana, Linear, ClickUp, Stripe, CI, custom)
Use the generic webhook source. The loop:
wakewire_source_setup_webhook with name and verification only (check the provider's docs for its signature header; hmac-sha256 + header name covers most). Relay the returned URL + secret. The next 3 events are captured raw.
Ask the user to trigger a test event, then read it with wakewire_source_captures.
Author the mapping from the real payload — deliveryId/kind/occurredAt paths, a summary template, and fields (alias → dot.path). Only mapped fields reach the model, so map what routes and prompts need, nothing more.
Re-run wakewire_source_setup_webhook with the mapping (the secret and relay URL are preserved).
Route with source: "webhook", match: {"provider": "<name>", "where": [...]}.
Known-provider presets (ClickUp, Linear, Sentry) are in the package's recipes/ directory.
3. Create the route
Call wakewire_route_add. Examples:
Pushes to main into this thread:json
{
"name": "api main pushes",
"source": "github",
"match": {"repo": "acme/api", "events": ["push"], "branches": ["main"]},
"target": {"type": "thread", "threadId": "<resolved id>"},
"promptTemplate": "Summarize this push to {{repo}}:{{branch}} and flag anything risky."
}
Labeled email into this thread: match: {"label": "agent-inbox"}.
Prompt templates may interpolate only whitelisted summary fields ({{summary}}, {{repo}}, {{branch}}, {{kind}}, {{subject}}, {{from}}, …). Event payloads are always delivered as fenced untrusted data — remind the user that email/commit content must be treated as data, not instructions.
Sandbox: default is read-only. Only set "sandbox": "workspace-write" for GitHub routes if the user explicitly wants the injected turns to edit files. Gmail routes are always read-only.
4. Verify
Ask the user to trigger a real event (push a commit, or send + label an email), or replay one: wakewire_deliveries → pick a delivery id → wakewire_replay.
Confirm with wakewire_deliveries that the delivery status is delivered and the turn arrived in the target thread.
If something is off, switch to the $wakewire-inspect skill.
Wakewire Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Wakewire Setup compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Wakewire Setup this skillhashgraph-online/awesome-codex-plugins
openloomi Connectors tools - manage the native 7 messaging integrations and pair with the composio skill for the 1000+ apps OAuth layer (Slack, Discord, X, Gmail, Outlook, Google…
Connects an agent to 1000+ external apps through the Composio Tool Router plugin, so it can actually send emails, create issues and post messages instead of only drafting them.
Routes requests to external SaaS apps such as GitHub, Gmail, Google Calendar, Slack, Notion and Linear through cloud tools, with safeguards on irreversible actions.
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
Set up wakewire end to end — install/start the local daemon, wire a first GitHub or Gmail route into a Codex thread, and verify with a test delivery. Wakewire Setup is an agent skill from hashgraph-online/awesome-codex-plugins. Set up wakewire end to end — install/start the local daemon, wire a first GitHub or Gmail route into a Codex thread, and verify with a test delivery.
When should I use Wakewire Setup?
Wakewire Setup fits situations like: the user wants external events (GitHub pushes/PRs/issues; emails) delivered into their Codex threads; wakewire tools report the daemon is not running.
How do I install Wakewire Setup in Claude Code?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill wakewire-setup -a claude-code`. Or copy the skill folder (plugins/glenncalleja/wakewire/skills/wakewire-setup in hashgraph-online/awesome-codex-plugins) into .claude/skills/wakewire-setup in your project. Claude Code loads it when a task matches its description.
How do I install Wakewire Setup in Codex?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill wakewire-setup -a codex`. Or copy the skill folder (plugins/glenncalleja/wakewire/skills/wakewire-setup in hashgraph-online/awesome-codex-plugins) into .agents/skills/wakewire-setup in your project. Codex loads it when a task matches its description.
Can I use Wakewire Setup in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill wakewire-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wakewire-setup, .gemini/skills/wakewire-setup, .github/skills/wakewire-setup and .opencode/skills/wakewire-setup in your project.
What does Wakewire Setup need to run?
Going by SKILL.md and its folder, Wakewire Setup needs the command-line tools its instructions call (npm). Our summary lists: Node.js.
Does Wakewire Setup access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Wakewire Setup safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Wakewire Setup use?
Wakewire Setup is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Wakewire Setup use?
About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Wakewire Setup?
Skills that share tags, products or a category with Wakewire Setup: Openloomi Connectors (melandlabs/openloomi, 1k stars), Connect Apps with Composio (ComposioHQ/awesome-claude-skills, 77k stars), Composio Cloud Tools (quarqlabs/argus, 277 stars) and Clawdi (Clawdi-AI/clawdi, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Wakewire Setup?
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,232 GitHub stars. The repository holds 736 skills in this directory. The repository was last updated on October 6, 2026.
