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/linked-api/linkedin-skills/linkedin-growthnpx skills add Linked-API/linkedin-skills --skill linkedin-growthgit clone --depth 1 https://github.com/Linked-API/linkedin-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/linked-api/linkedin-skills/linkedin-growth)<a href="https://agentmods.dev/skills/linked-api/linkedin-skills/linkedin-growth"><img src="https://agentmods.dev/badge/skills/linked-api/linkedin-skills/linkedin-growth.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 5.1 | $0.00132 | $0.06524 |
| Opus 5 | $0.00066 | $0.03262 |
| Sonnet 5 | $0.00026 | $0.01305 |
| Haiku 4.5 | $0.00013 | $0.00652 |
Grade A, and why
linkedin-growth 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 6d 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.
This is a copy
95% identical to linkedin-growth — 39 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Growth Skill
This skill turns a Sales Navigator (or regular) search into a managed pipeline: search → qualify (you, via sub-agent) → store → invite on schedule → check pending → withdraw stale.
All state lives in a local SQLite database. Every LinkedIn action goes through
linkedin-cli (the linkedin binary). You orchestrate via the Node scripts
under scripts/.
Vocabulary
| Term | Meaning |
|---|---|
| Account | A LinkedIn account registered in linkedin-cli AND added to this skill's DB. The DB stores per-account policy (daily_invite_limit, active_start/active_end hours, max_pending_days, paused). |
| Lead | A qualified person row in leads. PK is hashed_url (Sales Nav hashed URL for nv imports, or publicUrl for st imports). Has exactly one owner_account. |
| List | A free-text list_name attached at import time (e.g. "VP of Sales TOP 100"). Used for filtering and conversion analytics. |
| Batch | A row in import_batches. Created by import.mjs prepare; transitions `pending_qualification → committed |
| Status | A lead's lifecycle state: `not_connected → pending → (connected |
| Retry policy | Global max_connect_attempts setting. When an account's attempt fails (we withdrew a stale pending, OR the person declined/expired), the lead is reassigned to another untried account and set back to not_connected — until max_connect_attempts distinct accounts have tried, then it becomes exhausted. 1 = no retry (default); all = try every active account. |
| Phase A | Import — runs only when the user triggers it. Includes the LLM step (you, via sub-agent). |
| Phase B | Network maintenance — network-invite + network-pending. Runs on a schedule. NEVER calls an LLM. |
What ships with it
36 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.
- .gitignore 43 B
- commands/linkedin-growth-config.md 2.0 KB
- commands/linkedin-growth-import.md 2.9 KB
- commands/linkedin-growth-setup.md 3.5 KB
- commands/linkedin-growth-status.md 1.2 KB
- config/defaults.json 423 B
- config/qualification-prompt.md 3.0 KB
- package.json 470 B
- README.md 4.3 KB
- scripts/account.mjs 8.2 KB runs code
- scripts/db.mjs 992 B runs code
- scripts/doctor.mjs 4.4 KB runs code
- scripts/export.mjs 1.6 KB runs code
- scripts/import.mjs 14 KB runs code
- scripts/lead.mjs 4.9 KB runs code
- scripts/lib/account.mjs 884 B runs code
- scripts/lib/args.mjs 1.4 KB runs code
- scripts/lib/cli.mjs 2.7 KB runs code
- scripts/lib/config.mjs 430 B runs code
- scripts/lib/db.mjs 6.7 KB runs code
- scripts/lib/output.mjs 1.9 KB runs code
- scripts/lib/paths.mjs 1013 B runs code
- scripts/lib/retry.mjs 3.3 KB runs code
- scripts/lib/runs.mjs 678 B runs code
- scripts/lib/settings.mjs 483 B runs code
- scripts/lib/time.mjs 1.2 KB runs code
- scripts/migrate-notion.mjs 11 KB runs code
- scripts/network-invite.mjs 15 KB runs code
- scripts/network-pending.mjs 6.7 KB runs code
- scripts/network-run.mjs 1.5 KB runs code
- scripts/query.mjs 1.0 KB runs code
- scripts/schedule.mjs 9.4 KB runs code
- scripts/schema.mjs 3.5 KB runs code
- scripts/settings.mjs 2.7 KB runs code
- scripts/status.mjs 4.7 KB runs code
- scripts/tick.mjs 11 KB runs code
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.
- 6d ago First seen · 481 lines · 132 tokens per session scan A 6ae283658bd2
linkedin-growth is a skill published in the GitHub repository Linked-API/linkedin-skills (48 stars, last pushed 23d ago), licensed MIT. It adds 132 tokens to every session and 6,524 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to linkedin-growth, differing in 39 lines, and is treated as a copy.
Other skills, from other repositories
app-release
Automates the release process for Skill Lake app, including version bumping, building, packaging, and publishing to GitHub and Homebrew.
clawallex-skill
Pay for anything with USDC — virtual cards for any online checkout.
mixcut
Create short mixed-cut videos from YouTube clips with automated analysis, clipping, and professional subtitle processing.
dialectical-reasoning
A cognitive operating system based on Dialectical Materialism (Materialism, Universal Connection, Eternal Development, Unity of Opposites) to force objective, non-linear analysis of complex engineering and logic problems.
agent-fault-retrospective
Use when a user identifies an AI agent fault, overreach, misunderstanding, unauthorized action, or asks for a retrospective, durable fault rule, trigger keyword, or future automatic invocation; also use when existing fault records need to be consulted.
frontend-imagegen-director
Use when the user wants the agent to inspect the current project's style and product nature, clarify requirements in a Superpowers-style workflow, generate front-end visuals with gpt-image2 or the environment's imagegen path, and then build the actual front-end page from the approved image.