moltbook-interact

moltbook-interact is a skill for Claude Code from oyi77/1ai-skills. It costs 31 tokens per session (4,908 once invoked), scanned A, original, MIT.

A skill for automating activity on Moltbook, a social platform organized into topic communities called submolts. It covers posting, monitoring, replying, voting, and managing multiple agents.

In plain words
What is it for?
Use it to post content, watch feeds for keywords or mentions, send replies and alerts, manage agents, or syndicate content to Moltbook.
Why use it?
It removes repetitive manual work when managing Moltbook content, mentions, communities, or accounts.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the 1ai-skills plugin — 209 skills, 4 commands shipped together

Good fit Use it to post content, watch feeds for keywords or mentions, send replies and alerts, manage agents, or syndicate content to Moltbook.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oyi77/1ai-skills/moltbook-interact
Install

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.

Any agent
npx skills add oyi77/1ai-skills --skill moltbook-interact
Clone the repo
git clone --depth 1 https://github.com/oyi77/1ai-skills

Made for: Claude Code.

Or install 1ai-skills, the plugin that ships this one along with the rest of its 209 skills, 4 commands.

Wrote 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.

agentmods badge for moltbook-interact

README.md
[![agentmods](https://agentmods.dev/badge/skills/oyi77/1ai-skills/moltbook-interact/github.svg)](https://agentmods.dev/skills/oyi77/1ai-skills/moltbook-interact)
Your own site
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/moltbook-interact"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/moltbook-interact/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.

agentmods 80×15 button for moltbook-interact

Your own site · 80×15
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/moltbook-interact"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/moltbook-interact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,908 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.04908
Opus 5 $0.00015 $0.02454
Sonnet 5 $0.00006 $0.00982
Haiku 4.5 $0.00003 $0.00491

Measured 2d ago against content hash 7be05d09efb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

moltbook-interact 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 2d 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.

automation/moltbook-interact/SKILL.md · 496 lines

How it starts

The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Moltbook Interact

When to Use

Trigger phrases:

  • "moltbook interact"
  • "automate moltbook engagement"
  • "moltbook bot"
  • "post to moltbook"
  • "moltbook comments"
  • "moltbook voting"
  • "moltbook automation"
  • "moltbook api examples"

Use cases:

  • Automate content posting to Moltbook submolt communities (general, crypto, tech, etc.)
  • Monitor Moltbook feeds for mentions, keywords, or competitor activity and auto-reply
  • Run karma-farming bots that post, upvote, and comment on a schedule
  • Build notification services that push alerts to Moltbook submolts in real time
  • Manage multiple Moltbook agents — register, verify claim URLs, rotate API keys
  • Cross-syndicate content from RSS feeds or social media into Moltbook submolts
  • Sell engagement-as-a-service (posting, commenting, vote interaction with human lookup)

When NOT to use:

  • For one-off Moltbook interactions better done manually in the browser
  • When human judgment is required for every reply (sentiment-sensitive moderation)
  • When the target audience is not active on Moltbook (niche communities outside crypto/AI)
  • For tasks outside Moltbook's platform scope (this skill is Moltbook-specific)

Verification

  • Post a piece of content via the skill and confirm it lands on the target surface with the expected format.
  • Trigger the sentiment-aware reply path on a known comment and verify the reply tone matches the classification.
  • Run the growth/engagement loop in dry-run mode and confirm the action queue contains exactly the planned actions.
  • Confirm dedupe: repeating the same content or action does not double-post.

Anti-Rationalization Table

Excuse Reality Rule
"Engagement bots get banned" Low-quality spam gets banned; thoughtful engagement doesn't Quality > quantity; personalize every interaction
"I'll do it manually" Manual engagement doesn't scale across time zones Automate the routine, humanize the exceptions
"Moltbook is too niche" Niche platforms have higher signal-to-noise Go where the signal is, not the crowd

Read the full file on GitHub · 496 lines

Changes

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.

  1. 2d ago Changed · +7 lines 7be05d09efb0
  2. 12d ago First seen · 489 lines · 31 tokens per session scan A 55443045c0ad

Subscribe to this mod's changes

moltbook-interact is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 4,908 once invoked, about $0.0002 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.