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 wardawgmalvicious/agent-config --skill linkedin-highlightsgit clone --depth 1 https://github.com/wardawgmalvicious/agent-configWrote 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/wardawgmalvicious/agent-config/linkedin-highlights)<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/linkedin-highlights"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/linkedin-highlights/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/wardawgmalvicious/agent-config/linkedin-highlights"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/linkedin-highlights.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 | $0.00169 | $0.04659 |
| Opus 5 | $0.00084 | $0.02329 |
| Sonnet 5 | $0.00034 | $0.00932 |
| Haiku 4.5 | $0.00017 | $0.00466 |
Grade A, and why
linkedin-highlights 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 yesterday.
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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Highlights
Produce the prose for one LinkedIn Experience role's Highlights field, from a git repo the user worked in.
The field is a single plain textarea — no formatting toolbar — capped at 2,000 characters and prompting "Projects, problems you solved, or results you achieved". Both facts come from the user's own screenshot of the Edit-role dialog, 2026-09-10, which is the primary source for this skill. Field mechanics and the format spec live in references/highlights-format.md; the extraction procedure in references/repo-evidence.md.
The scrub in step 7 is why this is a skill and not a prompt. Every
other step is careful writing an unaided model does reasonably well. The
scrub encodes something no unaided run would reconstruct: the
identity-guard hook gates git commit and git push only, and skips
exempt repo roots wholesale — so text carried out of a work repo onto a
public profile passes no gate at all.
Scope and stop conditions
This skill writes one field. Stop and say so if:
- The target is a resume, a CV, a cover letter, or a LinkedIn post.
Different length, different register, different conventions, and none
of them were drilled. A resume skill may exist later and will read
references/repo-evidence.md; it does not exist now. - The target is not a git repo. The evidence method is git history plus committed docs. Without both there is nothing to extract from, and inventing the content is the failure this skill exists to prevent.
- Authorship cannot be established (step 1). Writing someone else's work into the user's profile is worse than writing nothing.
Multiple roles means multiple runs. Do not batch them: the character budget is per role and the evidence boundary is per role.
1. Fix the role boundary
Settle four things before reading anything: which repo, which role, which date range, and whether the work is live. Ask if any is unclear — the answers bound everything downstream. Deployment state is the one easily skipped, and it decides how step 5 handles outcome figures: a system still in Test has no adoption number to ask for.
What ships with it
3 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.
- yesterday First seen · 385 lines · 169 tokens per session scan A 94e081ae7a9d
linkedin-highlights is a skill published in the GitHub repository wardawgmalvicious/agent-config (1 stars, last pushed yesterday), licensed MIT. It adds 169 tokens to every session and 4,659 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 2026-09-11.
Other skills, from other repositories
drawio
WORKFLOW SKILL — Generate Azure architecture diagrams in .drawio via simonkurtz-MSFT MCP server (full Azure icon set, batch creation, transactional mode). Covers architecture, dependency, runtime-flow, and as-built diagrams. WHEN: 'draw.io diagram', 'Azure architecture diagram', 'as-built diagram', 'runtime flow…
azure-artifacts
UTILITY SKILL — Artifact template structures, H2 compliance rules, and documentation styling for agent outputs (Steps 1-7). WHEN: "generate artifact", "check H2 structure", "artifact template", "step 7 as-built". USE FOR: generating any agent artifact, checking H2 structure compliance. DO NOT USE FOR: Azure resource…
azure-bicep-patterns
UTILITY SKILL — Reusable Azure Bicep patterns: hub-spoke, private endpoints, diagnostics, AVM composition. WHEN: "hub-spoke Bicep", "private endpoint module", "diagnostic settings", "AVM Bicep composition". USE FOR: Bicep template design, hub-spoke networking, private endpoint patterns, AVM modules. DO NOT USE FOR…
azure-governance-discovery
ANALYSIS SKILL — Azure Policy discovery: effective assignments (incl. MG-inherited), definitions/exemptions, effect classification, emits governance-constraints JSON. WHEN: 'Azure policy discovery', 'effective policy assignments', 'governance constraints', '04g-Governance Phase 1', 'refresh governance JSON'. DO NOT…
vendor-prompting
ANALYSIS SKILL — Audit-grade reference for Anthropic Claude and OpenAI GPT-5.6 prompting best practices. WHEN: "claude prompting", "gpt-5.6 prompting", "audit agent", "review prompt", "vendor best practices", "anthropic best practices", "openai prompting". DO NOT USE FOR: routine prompt edits where rules are already…
copilot-customization
Authoritative reference for VS Code Copilot customization mechanisms: instructions, prompt files, custom agents, agent skills, MCP servers, hooks, and plugins. Use when deciding which customization type to use, creating new .instructions.md/.prompt.md/.agent.md/SKILL.md/mcp.json files from scratch, or debugging why a…