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/openpi-dev/openpi/background-terminalsnpx skills add openpi-dev/openpi --skill background-terminalsgit clone --depth 1 https://github.com/openpi-dev/openpiWhat 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 | $0.00038 | $0.00292 |
| Opus 5 | $0.00019 | $0.00146 |
| Sonnet 5 | $0.00008 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
background-terminals 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.
What it actually says
Background Terminals
Use bg_start for long-running commands; use regular bash for quick commands.
Start
Call bg_start with:
command: shell command to runtitle: short recognizable labelworking_dir: project directory when different from the current directorytimeout_seconds: optional deadline for finite work such as builds, tests, or migrations; omit for servers and watchers
Background commands receive no stdin. Never use them for interactive prompts.
After starting, continue useful work instead of polling. The terminal sends one completion message when it exits or times out.
Inspect and stop
- Use
bg_statusonly when current output or status is needed. - Use
bg_listto inventory all tracked terminals. - Use
bg_killwhen a process is no longer needed or is stuck; termination continues even if the tool wait is aborted. - Tell the user they can open
/psto inspect live output and kill terminals interactively.
Prefer meaningful titles and avoid starting duplicate servers or watchers. Full output is captured to spill files; tool and completion output shows a concise tail. Terminals are session-scoped and are stopped during shutdown or reload.
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 · 31 lines · 38 tokens per session scan A b872a26df974
background-terminals is a skill published in the GitHub repository openpi-dev/openpi (100 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 292 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.
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.