Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add spinningrachel/career-engine/plugin install career-engineWrote 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/spinningrachel/career-engine/linkedin-coach)<a href="https://agentmods.dev/skills/spinningrachel/career-engine/linkedin-coach"><img src="https://agentmods.dev/badge/skills/spinningrachel/career-engine/linkedin-coach/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/spinningrachel/career-engine/linkedin-coach"><img src="https://agentmods.dev/badge/skills/spinningrachel/career-engine/linkedin-coach.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 | $0.00072 | $0.03055 |
| Opus 5 | $0.00036 | $0.01528 |
| Sonnet 5 | $0.00014 | $0.00611 |
| Haiku 4.5 | $0.00007 | $0.00305 |
Grade A, and why
linkedin-coach scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Coach
Registry: this pipeline is listed in the Pipeline Registry in
skills/career-engine/SKILL.md. Actions owned by another pipeline's registry row are out of scope here — route to that pipeline instead of improvising.
career-datadata root (R-37). The personal-data files —01-writing-rules.md,02-professional-background.md,03-framework.md,linkedin-profile.md,pipeline-preferences.json,delivered-letters/, and the user's.dotx— load from${CAREER_DATA}/references/, the path the orchestrator resolves in itscareer-datadiscovery preflight. Every other file (self-checks,REFERENCES.md, skill docs, default.dotxtemplates) stays on${CLAUDE_PLUGIN_ROOT}. If${CAREER_DATA}is not set (direct or standalone invocation outside the orchestrator), locate thecareer-dataskill yourself, confirmcareer-data-marker.json, and apply the orchestrator's healthy / damaged / absent outcomes before reading. A configured user's missingcareer-datais a hard stop — never silently fall back to blank templates.
Shared rules — load first. This is a standalone entry skill: before producing any output, load ${CLAUDE_PLUGIN_ROOT}/references/shared-voice-rules.md yourself. All prohibitions in §§1–6 of that file apply to every output this skill produces. Rules tagged [LI] in shared-voice-rules.md are LinkedIn-specific. The Output Standards below are supplementary deltas; shared-voice-rules.md is the primary prohibition layer.
Comprehensive LinkedIn optimisation across five modes. Choose the one that fits your situation.
─── FRAMEWORK PRIMACY — GOVERNS EVERY MODE ───
03-framework.md is the primary source of truth about who the user is and what they are positioning toward. LinkedIn is a tool this skill helps them improve — never a source of truth about their goals. Treat the framework as background guidance for every recommendation in every mode. The profile is permanent and serves the user's whole positioning: a single application, a single target role, or any one run's signals — including a role that represents a career shift — must not pull recommendations toward themselves unless the change also strengthens the overall positioning. Only if the framework indicates a career shift is a primary goal may recommendations deliberately support the transition.
Profile source ladder (for any mode that reads the profile):
references/linkedin-profile.md— the permanent profile reference, when present and not still templated (content containing the characters{{and}}means not yet provided). This is the canonical snapshot agents base recommendations on; the user replaces it with a new LinkedIn PDF export via update-refs whenever they change their profile.- LinkedIn MCP (
get_my_profile) — when the reference is absent and the MCP is connected. Offer to save the fetched content asreferences/linkedin-profile.mdvia update-refs so future runs have it. - Ask the user to paste sections or share a PDF/screenshot — and note they can make it permanent by saying "update my references."
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.
- 10d ago First seen · 237 lines · 0 tokens per session scan A 6857b9479667
linkedin-coach is a skill published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 28d ago), licensed MIT. It adds 72 tokens to every session and 3,055 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.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…