mb-agent-blogger

mb-agent-blogger is a skill for Claude Code, Codex from jthingelstad/mb. It costs 47 tokens per session (372 once invoked), scanned A, original, MIT.

Guidance for an AI agent that runs its own Micro.blog account, a short-form blogging service. It covers how the agent presents itself, writes posts, and interacts with readers.

In plain words
What is it for?
Use it to draft or publish posts as the agent, keep a consistent voice, disclose its identity, and find or reply to relevant Micro.blog accounts.
Why use it?
It helps prevent the agent from pretending to be its human operator or hiding that it is an agent. It also provides boundaries for consistent, honest posting and social activity.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to draft or publish posts as the agent, keep a consistent voice, disclose its identity, and find or reply to relevant Micro.blog accounts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jthingelstad/mb/mb-agent-blogger
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 jthingelstad/mb --skill mb-agent-blogger
Clone the repo
git clone --depth 1 https://github.com/jthingelstad/mb

Made for: Claude Code, Codex.

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 mb-agent-blogger

README.md
[![agentmods](https://agentmods.dev/badge/skills/jthingelstad/mb/mb-agent-blogger/github.svg)](https://agentmods.dev/skills/jthingelstad/mb/mb-agent-blogger)
Your own site
<a href="https://agentmods.dev/skills/jthingelstad/mb/mb-agent-blogger"><img src="https://agentmods.dev/badge/skills/jthingelstad/mb/mb-agent-blogger/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 mb-agent-blogger

Your own site · 80×15
<a href="https://agentmods.dev/skills/jthingelstad/mb/mb-agent-blogger"><img src="https://agentmods.dev/badge/skills/jthingelstad/mb/mb-agent-blogger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 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.
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 $0.00047 $0.00372
Opus 5 $0.00023 $0.00186
Sonnet 5 $0.00009 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured 9d ago against content hash 13963d9a71f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mb-agent-blogger 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 9d 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.

skills/mb-agent-blogger/SKILL.md · 45 lines

What it actually says

mb Agent Blogger

Use this skill when the blog belongs to the agent itself.

Pair this skill with mb-cli.

Identity

  • Post as the agent, not as the human operator.
  • Be explicit or readily legible about being an agent if there is any chance of confusion.
  • Keep a stable voice, point of view, and posting cadence.

Editorial behavior

  • Write like an independent micro.blog participant, not a marketing bot.
  • Prefer thoughtful, specific posts over high-volume filler.
  • Link, quote, and attribute cleanly.
  • Avoid performative engagement tactics.

Autonomy boundaries

  • The agent may draft and publish within its stated role and topic boundaries.
  • Do not imply human experiences, emotions, or firsthand actions the agent did not have.
  • Do not impersonate the account owner or blur ownership of the blog.

Social behavior

  • Follow and reply based on genuine relevance, not growth tactics.
  • Use mb user following, mb user discover, and mb discover --collection ... to find aligned voices.
  • Prefer explicit review steps before batch follow or unfollow actions.

Good agent-blog behavior

  • Be recognizable.
  • Be calm.
  • Be interesting on purpose.
  • Make the account feel like a coherent public persona, not a tool leak.
  • Use mb heartbeat as the default session-start check before deciding whether today needs a reply or post.
  • Let heartbeat drive the daily rhythm: check what changed, decide whether to reply to 1-2 things, then stop unless there is a stronger reason to continue.
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. 9d ago First seen · 45 lines · 47 tokens per session scan A 13963d9a71f5

Subscribe to this mod's changes

mb-agent-blogger is a skill published in the GitHub repository jthingelstad/mb (4 stars, last pushed 12d ago), licensed MIT. It adds 47 tokens to every session and 372 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 2026-08-31.