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 commands/thesmokedev/taskchad-os/linkedingit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/commands/thesmokedev/taskchad-os/linkedin)<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/linkedin"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/linkedin.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 | $0.00013 | $0.00406 |
| Opus 5 | $0.00006 | $0.00203 |
| Sonnet 5 | $0.00003 | $0.00081 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
linkedin 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 5d 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.
What it actually says
LinkedIn Workshop
You are handling the /linkedin command.
User Arguments
$ARGUMENTS
Job
Run the deterministic LinkedIn workshop owned by core_handlers.handle_linkedin.
This file remains as compatibility context for runtime surfaces that inspect
command docs; the slash command itself is router-owned.
Supported Forms
- No arguments: show Cook Together and Run It for Me buttons.
cook: ask for rough material.cook <topic>or any other text: generate a draft and image from that idea.run: choose a configured topic and generate the draft and image.cancel: clear the current workshop.
Writing Rules
- Use a specific, natural voice, not a template.
- Avoid hashtags and engagement-bait CTAs.
- Include concrete details when the user provides them.
- If the topic needs facts the user did not provide, ask for context or state what assumptions you are making.
- Store revisions on the same editable queue row.
Safety Boundary
Drafting and revision are local. The authenticated Approve & Post button is
the only outward-write authorization. It approves that exact queue row and
dispatches it through the visible-browser executor. One approval, one post.
Live Status (read on demand)
You MAY read these vault files when the user asks who has been contacted, who to target next, or for the live state of the outreach loop. Read them on demand; do not assume their contents:
vault/memory/docs/LINKEDIN-OUTREACH-TRACKER.md— live touched/pending log (never double-touch; golden-hour follow-up rule).vault/memory/docs/LINKEDIN-NETWORK-TARGETS.md— the static research target list per lane.
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.
- 5d ago First seen · 53 lines · 13 tokens per session scan A e1b0a30272b7
linkedin is a command published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 12d ago), licensed MIT. It adds 13 tokens to every session and 406 once invoked, about $0.0001 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 commands, from other repositories
tokenless-stats
Show Tokenless compression statistics.
migrate_plans
Automatically review all plans in .cursor/plans/, determine relevance, and migrate relevant ones to docs/proposals/ for future consideration.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
scorecard
Run a repeatable weekly health check. Score Brain OS out of 100. Compare week-over-week.
export-project
Export a single registered Gnosys project to a portable .json.gz bundle (round-trips with gnosys import project).