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/mudrii/golink/golink-clinpx skills add mudrii/golink --skill golink-cligit clone --depth 1 https://github.com/mudrii/golinkWrote 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/mudrii/golink/golink-cli)<a href="https://agentmods.dev/skills/mudrii/golink/golink-cli"><img src="https://agentmods.dev/badge/skills/mudrii/golink/golink-cli.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 | $0.00109 | $0.00852 |
| Opus 5 | $0.00055 | $0.00426 |
| Sonnet 5 | $0.00022 | $0.00170 |
| Haiku 4.5 | $0.00011 | $0.00085 |
Grade A, and why
golink-cli 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
golink CLI
Use golink as the source of truth for LinkedIn automation. Prefer CLI commands
over editing local state files directly. Default to non-destructive inspection
and dry-runs until the user explicitly asks to publish, delete, approve, or run a
queued mutation.
For command examples and troubleshooting, read references/cli-reference.md.
Operating Rules
- Verify the binary first:
golink version. - Prefer
--jsonfor single results and--output=jsonlfor streams. - Run
golink doctorbefore diagnosing auth, scope, redirect, or API support issues. - Use
--dry-runfor mutating commands unless the user clearly wants live LinkedIn changes. - Use
--require-approvalfor agent-driven publishing workflows. - Use
--idempotency-keyfor retryable mutations. - Never print or store access tokens, refresh tokens, client secrets, PKCE codes, or OAuth callback URLs containing
code=. - Never edit keyring, audit, approval, idempotency, schedule, or cassette files by hand unless the user explicitly asks for repair.
- Treat
unsupportedas an expected LinkedIn entitlement/scope result, not necessarily a CLI bug.
Setup Workflow
- Check local readiness:
golink version golink doctor - If unauthenticated, confirm required env vars without revealing values:
test -n "$GOLINK_CLIENT_ID" && echo GOLINK_CLIENT_ID=set || echo GOLINK_CLIENT_ID=missing test -n "$GOLINK_REDIRECT_PORT" && echo GOLINK_REDIRECT_PORT=set || echo GOLINK_REDIRECT_PORT=missing - Authenticate only when user expects an interactive browser flow:
golink auth login golink --json auth status golink doctor - If the user needs LinkedIn app setup instructions, point them to
LINKEDIN_SETUP.mdin this repo.
Mutation Workflow
- Inspect state:
golink --json auth statusandgolink doctor. - Build the command with explicit flags; do not rely on prompts in agent mode.
- Dry-run:
golink --json --dry-run post create --text "..." --visibility PUBLIC - For reviewable work, create a plan or approval entry:
golink --json plan post create --text "..." --visibility PUBLIC > plan.json golink --json execute plan.json --dry-run - Execute live only after user confirmation or an existing approved plan:
golink --json execute plan.json
What ships with it
4 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.
- 5d ago First seen · 87 lines · 109 tokens per session scan A a89ab6bee9b0
golink-cli is a skill published in the GitHub repository mudrii/golink (5 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 852 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 2026-08-31.
Other skills, from other repositories
linkedin-api
Use when composing LinkedIn posts - writes post text and carousel/image assets to a local directory for manual review and publishing. Optimized for the 2026 LinkedIn algorithm (dwell time, Golden Hour, document carousel format).
linkedctl-mcp
This skill teaches linkedctl MCP workflow patterns, conventions, and error handling for managing LinkedIn content via the LinkedIn API.
triage-reviews
Fetch PR review comments, verify each against real code/docs, fix valid issues, commit and push.
wiki-context-pack
Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "use my vault as context", "context slice for X", "pack the wiki for my agent", or "bounded context for Y".
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.