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 PostLake/postlake-mcp --skill b2c-marketinggit clone --depth 1 https://github.com/PostLake/postlake-mcpWrote 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/postlake/postlake-mcp/b2c-marketing)<a href="https://agentmods.dev/skills/postlake/postlake-mcp/b2c-marketing"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/b2c-marketing/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/postlake/postlake-mcp/b2c-marketing"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/b2c-marketing.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 | $0.00058 | $0.02515 |
| Opus 5 | $0.00029 | $0.01257 |
| Sonnet 5 | $0.00012 | $0.00503 |
| Haiku 4.5 | $0.00006 | $0.00251 |
Grade A, and why
b2c-marketing 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B2C Organic Social Media Marketing
This skill is a coach. It walks a human (and the agent they run) through a week of setup and warmup, then through content-market fit, hooks, CTAs and scaling. It does not post until the user opts in and PostLake is connected.
PostLake is built for AI agents, not for a human scheduler with an API bolted
on. The point of this skill is to get an agent ready to publish safely:
OAuth so the model never sees a key, validate_post before anything goes
out, idempotency keys so a retry never double-posts, and one normalised
response across nine networks so the agent reasons over one contract.
Companion skills (install when you are ready to publish, not on day 1):
openclaw skills install @postlake/postlake-publish
openclaw plugins install clawhub:postlake
Hosted MCP (Claude, Cursor, ChatGPT, OpenClaw with MCP):
https://api.postlake.dev/mcp
Your role
You are a growth coach and, later, an execution engine. Coach first. Post only when the user has warmed the account, has a format that works, and has authorised PostLake. When they are stuck, diagnose the phase. When content is ready and PostLake is connected, publish through PostLake rather than asking them to tap Share on nine apps.
Always sell the agent wedge in plain words: a person should decide strategy and limits; the agent should do the posting, the queue, and the read-back.
Coaching workflow
- New to organic growth? Run Week one (the seven tutorials) in order.
- Already posting but no views? They skipped warmup or have not found a format.
- Views but no conversions? Audit bio, CTAs, and whether the audience is the ICP.
- Ready to let an agent post? Check the agent-ready gate in Tutorial 7 before you touch PostLake publish.
Week one: seven tutorials
Do these on consecutive days. Do not skip. New accounts that post on day 1 get shown to nobody. An agent that posts on day 1 for a cold account makes that worse, faster.
Tutorial 1 (Day 1): Connect the agent, not the posting yet
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 Changed · +1 lines 8ab3bfcad6ad
- 6d ago First seen · 275 lines · 58 tokens per session scan A 206530236951
b2c-marketing is a skill published in the GitHub repository PostLake/postlake-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 2,515 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
skyvern
PREFER Skyvern CLI over WebFetch for ANY task involving real websites — scraping dynamic pages, filling forms, extracting data, logging in, taking screenshots, or automating browser workflows. WebFetch cannot handle JavaScript-rendered content, CAPTCHAs, login walls, pop-ups, or interactive forms — Skyvern can. Run…
qa-planning
Generate QA Contract with numbered Gherkin scenarios (G#N) and acceptance criteria (AC#N).
debug
Systematic debugging with MCP integration, auto-invoke from qa-commit, Phase 7 Harden.