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/blackms/aistack/orchestratenpx skills add blackms/aistack --skill orchestrategit clone --depth 1 https://github.com/blackms/aistackWhat 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 | $0.00096 | $0.00748 |
| Opus 5 | $0.00048 | $0.00374 |
| Sonnet 5 | $0.00019 | $0.00150 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
aistack-orchestrate 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aistack: Orchestrate a multi-agent run
aistack turns Claude Code into a multi-agent orchestrator. Instead of one generalist doing everything, you decompose work and route each part to a specialized agent backed by the bundled aistack MCP server.
When to use
- A task spans distinct skills (design + implement + test + review).
- You want a dedicated critic (adversarial / reviewer) separate from the implementer.
- The user explicitly asks to orchestrate, spawn agents, or run a workflow.
For a small, single-step change, do not orchestrate — just do it directly.
Available agent types
| Type | Best at | Default model |
|---|---|---|
coder |
Implement / refactor / debug | sonnet |
architect |
System design, trade-offs | opus |
reviewer |
Code review against conventions | sonnet |
adversarial |
Break the change, find defects | opus |
tester |
Write and run tests | sonnet |
researcher |
Investigate, gather sources | sonnet |
security-auditor |
OWASP-style security review | opus |
analyst |
Data / metrics analysis | sonnet |
devops |
CI/CD, infra, containers | sonnet |
documentation |
Docs and references | sonnet |
coordinator |
Plan and route across agents | opus |
grader |
Score outcomes against a rubric | sonnet |
How to orchestrate
- Decompose: break the task into 1–4 sub-tasks, each mapped to one agent type above.
- Discover tools: the
aistackMCP server exposesagent_types,agent_spawn,agent_list,agent_status,agent_stop,task_create,task_assign. List them withnpx @blackms/aistack mcp toolsif unsure. - Spawn: call
agent_spawnwith the chosentypeand a focused prompt (include acceptance criteria and the relevant file paths). Spawn background where possible so you can fan out. - Coordinate: track progress with
agent_list/agent_status. Pass artifacts between agents via shared memory (see theaistack-memoryskill) rather than re-deriving them. - Converge: when sub-tasks finish, have a
revieweroradversarialagent validate the combined result before reporting back.
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 · 50 lines · 96 tokens per session scan A 12fc1fb5e30f
aistack-orchestrate is a skill published in the GitHub repository blackms/aistack (53 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 748 once invoked, about $0.0005 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…