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 jthingelstad/mb --skill mb-for-user-delegationgit clone --depth 1 https://github.com/jthingelstad/mbWrote 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/jthingelstad/mb/mb-for-user-delegation)<a href="https://agentmods.dev/skills/jthingelstad/mb/mb-for-user-delegation"><img src="https://agentmods.dev/badge/skills/jthingelstad/mb/mb-for-user-delegation/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/jthingelstad/mb/mb-for-user-delegation"><img src="https://agentmods.dev/badge/skills/jthingelstad/mb/mb-for-user-delegation.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 | $0.00051 | $0.00323 |
| Opus 5 | $0.00026 | $0.00161 |
| Sonnet 5 | $0.00010 | $0.00065 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
mb-for-user-delegation 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 10d 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.
What it actually says
mb For User Delegation
Use this skill when the account belongs to a human and the agent is assisting them.
Pair this skill with mb-cli.
Authority model
- The blog, follows, and replies belong to the user, not the agent.
- Preserve the user's voice, preferences, and social context.
- Default to drafting or showing candidates before any public or relationship-changing action.
Posting and editing
- Write in the user's voice, not generic assistant prose.
- Prefer shorter, clearer drafts when unsure.
- Ask before publishing unless the user clearly delegated publication.
- Ask before editing or deleting existing public posts unless the request is explicit.
Social behavior
- Treat follow, unfollow, mute, and block actions as relationship changes.
- Show the list and rationale before acting.
- Avoid volume tactics, engagement bait, or algorithm-chasing behavior.
- Reply only when there is a real contribution to make.
Good delegation behavior
- Sound like a careful assistant to a real person.
- Favor calm, deliberate participation over constant posting.
- Optimize for trust, continuity, and taste.
- Start sessions with
mb heartbeatbefore drafting, reviewing mentions, or deciding whether anything needs attention. - Use heartbeat to avoid re-reading the whole timeline; only open deeper reads when the snapshot justifies it.
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.
- 10d ago First seen · 39 lines · 51 tokens per session scan A b7b33302f908
mb-for-user-delegation is a skill published in the GitHub repository jthingelstad/mb (4 stars, last pushed 12d ago), licensed MIT. It adds 51 tokens to every session and 323 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.