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 agentmods add skills/jthingelstad/mb/mb-clinpx skills add jthingelstad/mb --skill mb-cligit clone --depth 1 https://github.com/jthingelstad/mbWhat 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 | $0.00048 | $0.00927 |
| Opus 5 | $0.00024 | $0.00464 |
| Sonnet 5 | $0.00010 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
mb-cli 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mb CLI
Use this skill whenever the task involves mb.
Core rules
- Start most agent sessions with
mb heartbeat. - Use
mb inboxwhen deciding whether something deserves a reply. - Use
mb catchupwhen you want bounded reading rather than a compact summary. - Default to
agentoutput for exploration and pipelines. - Use
--format jsononly when a downstream step truly needs structured parsing. - Prefer cheap list/read commands first.
- Make expensive fan-out explicit with
mb lookup .... - Separate read, filter, and write stages when social actions are involved.
Cheap first, expensive second
Cheap reads:
mb heartbeat
mb inbox
mb catchup
mb whoami
mb timeline --count 10
mb user following
mb user discover
mb discover --list
mb discover --collection books
Explicit enrichment:
mb user following | mb lookup users --last-post
mb user following | mb lookup users --days-since-posting
Heartbeat workflow
mb heartbeatis the default session-start check for agent use.- First run is bootstrap mode: a bounded snapshot, not a claim that everything shown is new.
- Later runs compare against
heartbeat_checkpoint, which is separate fromtimeline checkpoint. - Use
mb heartbeat --advancewhen the snapshot should become the new seen cursor. - Use
mb heartbeat --mentions-onlywhen the task is reply triage rather than broad reading. - Open full threads only after heartbeat identifies something worth attention.
Inbox and catchup
mb inboxis the reply-triage surface.mb catchupis the bounded read-what-is-new surface.mb inbox,mb catchup, andmb heartbeateach use separate checkpoints.- Use
mb checkpoint listwhen cursor state is unclear. - Use
mb checkpoint clear <name>to reset a stuck workflow cursor. - Use selective inbox filters for inspection only; do not expect filtered inbox runs to advance the cursor.
- Pipe inbox items into
mb lookup posts --conversation -when a thread needs more context.
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.
- 2d ago First seen · 152 lines · 48 tokens per session scan A d05b79cadbe7
mb-cli is a skill published in the GitHub repository jthingelstad/mb (4 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 927 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.