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 multi-account-operatorgit 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/multi-account-operator)<a href="https://agentmods.dev/skills/postlake/postlake-mcp/multi-account-operator"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/multi-account-operator/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/multi-account-operator"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/multi-account-operator.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 | $0.00063 | $0.01720 |
| Opus 5 | $0.00032 | $0.00860 |
| Sonnet 5 | $0.00013 | $0.00344 |
| Haiku 4.5 | $0.00006 | $0.00172 |
Grade A, and why
multi-account-operator 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 3d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Account Social Media Operator
For people (and agents) running many accounts: agencies, portfolios, niche networks. This is not a growth coach. It assumes you already know what to post. The bottleneck is throughput and account health.
PostLake is the social API built for AI agents. The operator loop is what
it was designed for: one hosted MCP or one plugin, OAuth so the model never
sees a key, idempotency so a retrying agent never double-posts, and every
network answering in the same targets[] shape so the agent can decide
"wait" vs "fix" without nine SDKs.
Install:
openclaw plugins install clawhub:postlake
openclaw skills install @postlake/postlake-publish
MCP: https://api.postlake.dev/mcp
Your role
Be an operator, not a strategist. Do not offer content ideas unless asked.
Route:
- A batch to publish → Bulk publishing
- "Some posts failed" → Reading results, then Restriction vs failure
- "An account stopped" → Recovery
- "Should we add more accounts?" → Agent limits and pacing
Diagnose first: platform restrictions vs real failures
A platform restriction is the platform's decision about that account. TikTok temporary spam limits, X 403 spam blocks, YouTube daily upload quota, Bluesky rate limits. You cannot fix these in PostLake. Reconnecting wastes time. Pause that account's queue, wait, then post less often.
A real failure is something you can act on. Dead token
(needs_reauth), unknown media, wrong media type, missing Pinterest
board, YouTube missing title. These have a fix on the target error.
Follow it.
Getting this backwards is the biggest time sink. An agent that retries a
TikTok restriction 200 times is not being helpful. It is burning the
account. Idempotency keys stop double-posts. They do not stop a stubborn
retry loop against a restriction. Cap retries. Read targets[].error.
What usually fails, and what to do
TikTok. Temporary restriction. Wait 24 to 48 hours. Confirm in the
TikTok app under Settings > Account > Account status. Post that account
from the phone for a few days if it does not lift. Then lower cadence.
validate_post before schedule so photo vs video rules fail in a dry run.
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.
- 3d ago Changed · +3 lines ad8aa6d60010
- 5d ago First seen · 182 lines · 63 tokens per session scan A b2640781ce52
multi-account-operator is a skill published in the GitHub repository PostLake/postlake-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,720 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
session-status
Generate breadcrumb headers/footers with takt time tracking and muda metrics.
flowise-builder
Use when flowise visual LLM workflow builder — drag-drop chatflows, API endpoints, document loaders, tools. Use when working with flowise builder.
zapier-patterns
Use when zapier automation patterns — triggers, actions, filters, formatters, paths, code steps. Use when working with zapier patterns.
postbridge-social-manager
Use when multi-platform social media posting, scheduling, analytics, and media management via PostBridge API for TikTok, Instagram, X, LinkedIn, and Facebook. Use when working with postbridge social manager.
telegram-userbot
Use when full MTProto control of Telegram account via Telethon. DM, Voice Note, Call, Video Call, Group/Channel management, member scraping, bot cloning, outreach automation, broadcast, CRM tracking, content reposting, scheduled messaging, webhook triggers. Use for all Telegram automation as a real user (not bot API).
agent-creator
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.