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/jared833/claude-code-hooks/linkedin-engagenpx skills add jared833/claude-code-hooks --skill linkedin-engagegit clone --depth 1 https://github.com/jared833/claude-code-hooksWrote 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/jared833/claude-code-hooks/linkedin-engage)<a href="https://agentmods.dev/skills/jared833/claude-code-hooks/linkedin-engage"><img src="https://agentmods.dev/badge/skills/jared833/claude-code-hooks/linkedin-engage.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.01796 |
| Opus 5 | $0.00044 | $0.00898 |
| Sonnet 5 | $0.00018 | $0.00359 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
linkedin-engage 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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn engagement session
Goal: grow Jared's LinkedIn presence (linkedin.com/in/jaredhebb) by commenting with substance, not broadcasting. Claude drafts; Jared posts by hand. This is the LinkedIn twin of the x-engage skill and uses the same Engage app; the only API difference is platform: "linkedin" in the session payload.
NO BROWSER AUTOMATION ON LINKEDIN (hard rule, 2026-07-19)
Never drive Jared's logged-in LinkedIn account through Claude in Chrome (or any browser tool): no opening his feed, no scrolling/harvesting, no auto-posting comments, no clicking Follow/Connect. LinkedIn is even more aggressive than X about automation detection, and browser-driven sessions put his reach at risk. Every outward action is Jared's hands only; Claude's job here is draft-and-hand-off. Holds until we pay for a compliant LinkedIn API path (first revenue spend). Do not reintroduce browser control before then; if a session seems to need it, stop and ask.
Session flow
-
Start the Engage app (
<HOME>\projects\engage). Checkhttp://localhost:3220/api/health; if it is not up, runnpm run devthere in the background and wait for the health check to pass. -
Get the raw material from Jared. He pastes the post URLs (or screenshots) he wants to comment on, and his current follower/following counts if he wants them tracked. Claude does not open LinkedIn to find posts. Topic lanes he can search himself: Claude Code / AI coding agents, build in public, IT leadership + AI adoption, network operations, indie products. WebFetch on a public post URL for context is fine; driving his account is not.
-
Vet what he brought. Draft only for posts worth a comment: real author with real engagement, a post where Jared can add something concrete, not buried under 200+ comments, not engagement-bait. Skip the rest and say why in one line.
-
Draft a comment for each following the voice rules below, then present them in the Engage review page (Jared approves in a browser, never in the terminal):
- POST the session JSON to
http://localhost:3220/api/sessionwithplatform: "linkedin"(shape otherwise identical to x-engage:{platform:"linkedin", title, replies:[{id,author,age,context,draft}], follows:[{handle,reason}]}, with nopostfield, see "This session does not draft posts" below;handle= the person's/in/vanity slug). The response returnsreviewUrl; open it for him. - He marks each item Drafted/Skip/Redraft, edits inline, hits "Approve and send to Claude" (means approved-to-copy, not auto-sent). Poll
GET http://localhost:3220/api/session/<id>/decisionsuntilsaved:true. The decisions tell you which drafts he approved; nothing is posted by Claude. - Redraft loop: same as x-engage - POST fresh drafts to
/api/session/<id>/redraft, repeat until nothing is marked redraft.
- POST the session JSON to
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.
- 4d ago First seen · 63 lines · 88 tokens per session scan A 610ff741a8b9
linkedin-engage is a skill published in the GitHub repository jared833/claude-code-hooks (2 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 1,796 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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.
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…