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 agentmods add skills/agentproto/ts/linkedinnpx skills add agentproto/ts --skill linkedingit clone --depth 1 https://github.com/agentproto/tsWhat 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 | $0.00161 | $0.01616 |
| Opus 5 | $0.00081 | $0.00808 |
| Sonnet 5 | $0.00032 | $0.00323 |
| Haiku 4.5 | $0.00016 | $0.00162 |
Grade A, and why
linkedin 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn skill
The browser is just an authenticated transport. The data lives in LinkedIn's own internal API (Voyager). Read from source, not the DOM. (DOM selectors returned 0 reliably; a Voyager fetch returned 217 KB of structured truth.)
Golden rules
- API-first — every read is a Voyager fetch; DOM only for the few write buttons.
- Fail fast — ~8 s timeouts, not 60 s. After 5-6 s it's ~90 % a hard hang.
- Prefer direct navigation to URLs over clicking links/buttons that navigate (they hang).
- Tab/focus discipline —
list_pagesbefore acting;new_pageto isolate. - queryIds + selectors DRIFT — capture live each session; never hardcode.
- Gate every write — acts as the user; explicit per-send confirmation.
Read this in order
reference/transport.md— chain, lifecycle, tab/focus, timeouts, tool gotchas.reference/voyager.md— the data layer: the fetch primitive + query library + capture method + entity model.reference/recipes.md— read recipes (feed, profile, activity, who-reacted/commented, connections, search + the identification scorer).reference/write-actions.md— message + attachment (✅ proven, API-first) + the relationship graph (invite ±note / withdraw, ✅ viasocial_network/ the trusted-input ladder; connect+withdraw are SDUI, not a fetch), gated, safety rails.reference/playbooks.md— the 100x layer: persona dossiers, the engagement/relationship graph, discover→dossier→outreach.
Quickstart (once the browser is free)
1. health: api 3040 · tunnel 3600 · daemon 18790 (else: agentproto serve --connect ws://localhost:3600/connect)
2. navigate any linkedin.com page → liFetch(voyagerFeedDashMainFeed, …) → structured feed
3. for a person: search + score → persona.build → (gated) reach out
Harnesses: projects/guilde/apps/api/scripts/linkedin-explore.ts
(feed/profile/search/req) and linkedin-message.ts (--send gated).
Connect-with-note flow in write-actions.md.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 124 lines · 161 tokens per session scan A c60aa4819cee
linkedin is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 161 tokens to every session and 1,616 once invoked, about $0.0008 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
browser-qa
Validate web applications through the embedded browser with responsive, interaction, console, and screenshot checks.
goplaces
Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.
ai-browser-use
业务诊断助手适合市场营销、运营、产品、销售在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。.
docs-planner
Identify documentation gaps and prioritize the docs backlog. Use when planning a docs improvement sprint, after signals surface repeated friction, when new SDK features ship without docs, or for periodic health assessment. Also triggers on "plan docs work", "what docs need writing", "prioritize the backlog", "docs…
pr-feedback
Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…