agentmods.dev

linkednav

linkednav is a skill for Claude Code from linglistack/linkednav-mcp. It costs 70 tokens per session (1,126 once invoked), scanned A, original, MIT.

A set of assistant actions for managing LinkedNav outreach on the user's own account. It covers lead discovery, campaigns, messages, replies, contact details, and results, with approval required before sending or changing things.

In plain words
What is it for?
It is for auditing campaigns, finding leads, writing or answering messages, enriching contacts, and reviewing outreach performance.
Why use it?
It removes repeated manual work across outreach tasks while keeping sending and account changes under the user's control.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the linkednav plugin — 1 skill, 2 MCP servers shipped together

not rated 0repo 14d ago A scan 70 tokens original MIT

Good fit It is for auditing campaigns, finding leads, writing or answering messages, enriching contacts, and reviewing outreach performance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linglistack/linkednav-mcp/linkednav
View source ↗ linglistack/linkednav-mcp linkednav.com
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 linglistack/linkednav-mcp --skill linkednav
Clone the repo
git clone --depth 1 https://github.com/linglistack/linkednav-mcp

Made for: Claude Code.

Or install linkednav, the plugin that ships this one along with the rest of its 1 skill, 2 MCP servers.

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 linkednav

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/linglistack/linkednav-mcp/linkednav"><img src="https://agentmods.dev/badge/skills/linglistack/linkednav-mcp/linkednav.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,126 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01126
Opus 5.5 $0.00028 $0.00450
Sonnet 5.5 $0.00014 $0.00225
Haiku 4.5 $0.00007 $0.00113

Measured 14d ago against content hash 3b0b482b58c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

linkednav 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 14d 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.

skills/linkednav/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LinkedNav: LinkedIn outreach on the user's own account

The tools come from the MCP server linkednav at https://mcp.linkednav.com/. They run inside the user's own LinkedNav account and respect their active AI setup. LinkedNav is an independent service; it is not made by or affiliated with LinkedIn.

Before the first call

  • If the tools are missing or a call says a key is required, ask the user to sign in to the linkednav server from their app's MCP or plugin settings. The sign-in opens LinkedNav's connect page, where they paste their API key (made at https://www.linkednav.com/app/api-keys). Never ask for a key, a password or a LinkedIn cookie in the chat.
  • get_account_status checks the connection and shows the plan, credits, limits and LinkedIn senders.
  • No LinkedIn account connected: run start_linkedin_connect and give the user the private link it returns. Prefer it over the cookie and credentials tools.

Ask before anything is sent or changed

Reading needs no permission: the get_*, analyze_*, audit_*, diagnose_campaign, full_audit and preview_* tools. Read the real state with them before you change anything.

Before any call that sends something on LinkedIn or changes the account, show the user exactly what will happen and to whom, and wait for a yes. That covers:

  • Sending. activate_campaign, send_unibox_reply, approve_pending_reply, approve_pending_comment.
  • Changing. Every create_*, update_* and set_* tool, pause_campaign, duplicate_campaign, adding or removing campaign leads, track_* and untrack_*, and running a signal agent.
  • Spending credits. The enrich_* tools. For enrich_profiles, call it with confirm: false first, tell the user the estimate, then call it with confirm: true.
  • Things that cannot be undone. Every delete_* tool, bulk_delete_contacts, clear_signal_agent_results and withdraw_connections (run preview_withdraw_connections first). Say that it cannot be undone when you ask.

Read the full file on GitHub · 54 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. 14d ago First seen · 54 lines · 70 tokens per session scan A 3b0b482b58c9

Subscribe to this mod's changes

linkednav is a skill published in the GitHub repository linglistack/linkednav-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 70 tokens to every session and 1,126 once invoked, about $0.0003 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 2026-10-11.

Marketing and SEOai-agentsclaudelead-generationlinkedinmcpmodel-context-protocol
Related

Other skills, from other repositories

b2b-marketing-playbook

Complete B2B marketing pipeline combining LinkedIn content, cold email sequences, and webinar funnels. Designed for SaaS founders doing $0–$1M ARR who need predictable lead generation. By @WeiYipei.

Gingiris-1031/gingiris-skills · 53 tokens

migrate-waniwani-sdk-0.24-to-0.25

Migrate a project from @waniwani/sdk 0.24.x, or straight from 0.23.x, to 0.25.x. 0.25 removes the asked-only gate: the first question or widget lists every state field in fields, and any call writes a declared field whose value fits its Zod schema, so the flow skips the questions it fills. Computed values (price…

WaniWani-AI/sdk · 248 tokens

migrate-waniwani-sdk-0.23-to-0.24

Migrate a project from @waniwani/sdk 0.23.x to 0.24.x and auto-apply its breaking change to flows: the tool listing no longer names state fields under stateUpdates, start merges no stateUpdates, and continue and reset merge only fields the run has asked through an interrupt question or a widget's field. A field the…

WaniWani-AI/sdk · 352 tokens

audit-tracking

Audit Waniwani event tracking across an MCP project. Does an in-depth overview check of the whole app (server, flows, tools, widgets, chat embed), verifies that only events defined in the Waniwani taxonomy are sent, and identifies missing events worth adding at each funnel stage (identify, leadqualified, priceshown…

WaniWani-AI/sdk · 118 tokens

migrate-waniwani-sdk-0.19-to-0.20

Migrate a project from @waniwani/sdk 0.19.x to 0.20.x and auto-apply its breaking change: the entire legacy tier is deleted. The entry points @waniwani/sdk/legacy, /legacy/react, /legacy/next-js, /legacy/express-js, /next-js, /express-js and /chat/server no longer exist, ChatCard is gone from @waniwani/sdk/chat, and…

WaniWani-AI/sdk · 250 tokens

waniwani-sdk

MCP distribution SDK: build sales funnels, lead generation, booking flows, insurance quote flows, pricing quote flows, and any multi-step conversational MCP app with @waniwani/sdk. Open source createFlow engine (no API key required) with pluggable state backends (in-memory, Redis, Upstash, Cloudflare KV, DynamoDB, or…

WaniWani-AI/sdk · 199 tokens