heyreach

heyreach is a skill for Claude Code, Codex from anthroos/heyreach-claude-skill. It costs 63 tokens per session (2,569 once invoked), scanned A, original, MIT.

An integration for running LinkedIn outreach through HeyReach, a cloud service that manages lead lists, campaigns, messages, inbox replies, and webhooks. Campaigns continue running in the cloud when your computer is off.

In plain words
What is it for?
Use it to create lead lists, build connection and message sequences, add personalized leads, read or send inbox replies, and manage webhooks.
Why use it?
It removes the need to operate browser automation yourself and keeps outreach running remotely. It also provides one workflow for researching leads, sending messages, and handling replies.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create lead lists, build connection and message sequences, add personalized leads, read or send inbox replies, and manage webhooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthroos/heyreach-claude-skill/heyreach-claude-skill
Install

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.

Any agent
npx skills add anthroos/heyreach-claude-skill --skill heyreach-claude-skill
Clone the repo
git clone --depth 1 https://github.com/anthroos/heyreach-claude-skill

Made for: Claude Code, Codex.

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.

agentmods badge for heyreach

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthroos/heyreach-claude-skill/heyreach-claude-skill/github.svg)](https://agentmods.dev/skills/anthroos/heyreach-claude-skill/heyreach-claude-skill)
Your own site
<a href="https://agentmods.dev/skills/anthroos/heyreach-claude-skill/heyreach-claude-skill"><img src="https://agentmods.dev/badge/skills/anthroos/heyreach-claude-skill/heyreach-claude-skill/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.

agentmods 80×15 button for heyreach

Your own site · 80×15
<a href="https://agentmods.dev/skills/anthroos/heyreach-claude-skill/heyreach-claude-skill"><img src="https://agentmods.dev/badge/skills/anthroos/heyreach-claude-skill/heyreach-claude-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,569 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.02569
Opus 5 $0.00032 $0.01285
Sonnet 5 $0.00013 $0.00514
Haiku 4.5 $0.00006 $0.00257

Measured 12d ago against content hash 001ab75888d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

heyreach scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> connected, ALWAYS call the `heyreach.*` MCP tools. Do **not** curl the REST API. Reach for REST only
SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HeyReach LinkedIn Automation (Claude skill)

Drive HeyReach entirely from Claude. HeyReach is API-first, so you never babysit browser automation or VM queues — campaigns run in HeyReach's cloud with built-in warmup.

Setup

  1. HeyReach account: https://heyreach.io/?via=ivanrx
  2. Pick ONE transport. MCP and REST use different credentials from different sub-sections of Settings → Integrations — do not mix them up:
    • MCP (recommended): Settings → Integrations → MCP ServerGet MCP key → copy the MCP Connection URL (the key is already baked into the URL). Then: claude mcp add --scope user --transport http heyreach '<MCP Connection URL>' Restart Claude so the heyreach.* tools load. Verify: claude mcp listheyreach … connected.
    • REST (fallback): Settings → Integrations → API → copy the API key (a SEPARATE key from the MCP key). Base https://api.heyreach.io/api/public/, header X-API-KEY: <key>.

Transport decision — check this first, every session. If claude mcp list shows heyreach connected, ALWAYS call the heyreach.* MCP tools. Do not curl the REST API. Reach for REST only when no MCP server is connected and you actually have an X-API-KEY. Hitting REST without a key returns 401 Unauthorized — that means "wrong transport / missing key", not "service is down".

Core model

The API drives CAMPAIGNS (sequences), not individual clicks. You don't "send a connect to X" ad-hoc. You create a campaign with a sequence (connection request → wait → message → follow-up) and push leads into it; HeyReach executes from the cloud with warmup and rate limits.

Sourcing leads — the API does NOT search LinkedIn

There is no "find people" tool. HeyReach ingests leads you already have (add_leads_to_list / add_leads_to_campaign take profileUrl / navigatorProfileId); it does not run a LinkedIn people-search for you. So "find 10 X" is a research step you do first, then push the results in.

Read the full file on GitHub · 147 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.

  1. 12d ago First seen · 147 lines · 63 tokens per session scan A 001ab75888d9

Subscribe to this mod's changes

heyreach is a skill published in the GitHub repository anthroos/heyreach-claude-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 2,569 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens