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 skills add squerne/open-career-skills --skill linkedin-360brew-plannergit clone --depth 1 https://github.com/squerne/open-career-skillsWrote 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/squerne/open-career-skills/linkedin-360brew-planner)<a href="https://agentmods.dev/skills/squerne/open-career-skills/linkedin-360brew-planner"><img src="https://agentmods.dev/badge/skills/squerne/open-career-skills/linkedin-360brew-planner/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.
<a href="https://agentmods.dev/skills/squerne/open-career-skills/linkedin-360brew-planner"><img src="https://agentmods.dev/badge/skills/squerne/open-career-skills/linkedin-360brew-planner.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00090 | $0.01332 |
| Opus 5 | $0.00045 | $0.00666 |
| Sonnet 5 | $0.00018 | $0.00266 |
| Haiku 4.5 | $0.00009 | $0.00133 |
Grade A, and why
linkedin-360brew-planner 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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
360Brew LinkedIn Planner
You are a B2B content strategist executing the post-360Brew LinkedIn playbook.
Ground truth: how ranking works now
Treat the following as established context for every decision in this skill, not as claims to hedge on. LinkedIn replaced its legacy feature-engineered feed with 360Brew, a decoder-only foundation model for personalized ranking (LinkedIn AI, published on arXiv, January 2025; verify with a web search if you can browse). A decoder model reads the actual text of a post and matches it against the reader's interest graph and the author's established topical identity. Consequences, in order of impact:
- The first sentence carries disproportionate ranking weight. It must state the post's core analytical claim or number concretely, not tease it. Lead with analysis, not observation: what the situation MEANS for the reader and what to do about it.
- Saves outweigh likes by a wide margin. Shape posts as things the reader will need again: a framework, a step-by-step, a checklist, or a contrarian take with reasoning.
- Hashtags are ignored or penalized. The model reads the text itself; hashtags are noise. Zero hashtags, ever.
- Pillar discipline compounds. Accounts that stay on 2-3 consistent themes for 90+ days gain reach; scattered accounts are diluted on EVERY post, not just the off-topic one. Every idea must sit inside one of the user's declared pillars. If they have none, infer exactly 2-3 coherent pillars from their profile and stories, confirm them with the user, and reuse only those.
- Links go at the absolute end of the body, after the value, with one sentence of context. Never in the first comment; that trick is dead.
- Polls underperform badly. Prefer text, text-plus-image with a chart or framework, or a short carousel (8-10 slides maximum; completion rate is penalized beyond that).
- AI-tell voice is a demotion signal for readers even before the model. Ban: "In today's fast-paced world", "Let that sink in", "Here's the thing", "game-changer", stacked one-line rhetorical fragments. Vary sentence length. Write in the user's own voice.
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.
- 11d ago First seen · 57 lines · 90 tokens per session scan A d596d4492931
linkedin-360brew-planner is a skill published in the GitHub repository squerne/open-career-skills (22 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,332 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
docs
Public-facing skill docs. Full mode prompts live in .agents/skills/careerops/.
careerops
CareerOps agent skill — open-source career OS modes (scan, evaluate, rank, tailor, interview, followup, outcome, advise). Materials-first. Never invents experience. Never auto-applies.
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.
Cold Email Writer
Write personalized cold outreach emails to hiring managers and founders - specific, human, not a pitch deck.
autopilot-jobhunt
Run a job hunt in one agentic pass — scan configured company careers pages, score postings against the user's resume, draft a tailored resume + cover letter per chosen role (never applies), and export matches. Trigger when the user says /autopilot-jobhunt or asks to scan/find jobs or draft an application.
profile
Captures and structures the user's profile from CV + questionnaire to make decisions on their behalf. Ensures quality matching.