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/heyayushh/stacc/orchestratenpx skills add heyAyushh/stacc --skill orchestrategit clone --depth 1 https://github.com/heyAyushh/staccWrote 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/heyayushh/stacc/orchestrate)<a href="https://agentmods.dev/skills/heyayushh/stacc/orchestrate"><img src="https://agentmods.dev/badge/skills/heyayushh/stacc/orchestrate.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.00924 |
| Opus 5 | $0.00027 | $0.00462 |
| Sonnet 5 | $0.00011 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
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 4d 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.
Orchestrate
An explicit /orchestrate <goal> fans out a large task across parallel Cursor cloud agents. Workers don't talk to each other; they talk up through structured handoffs. The spawn, wait, and handoff loop lives in scripts/cli.ts. The planner writes plan.json, the script executes it, and the planner reads handoffs to decide what comes next. Long-running agent loops drift; a script with a JSON state file keeps its footing.
Required reading: the cursor-sdk skill (cursor/plugins/cursor-sdk). Spawning, auth, and the error taxonomy live there. Don't reimplement what that skill already documents.
Setup
CURSOR_API_KEYmust be a personal/user key. Create it from Cursor Dashboard > Integrations, then readcursor-sdkAuth before using it.SLACK_BOT_TOKENis optional. When set, pass--slack-channel <id>tokickoffor the firstrun --root, or setSLACK_CHANNEL_ID. The script stores the channel inplan.slackChannel, posts the kickoff thread there, mirrors task status, and reads Andon reactions. When the token is unset, the script logs once and runs without Slack visibility; correctness does not change.
Core principles
These rules make the tree self-converging without global coordination.
- Planners own scopes and publish tasks. They do no coding. Writing
plan.json, reading handoffs, and deciding what's next are planner work. Editing files, runninggit merge, and fixing conflicts inline are not. If a planner feels the urge to code, it publishes a task for a worker instead. - Planners don't know who picks up their tasks. The script routes each task to a cloud agent. The planner's mental model stays at the task level.
- Workers are isolated. One task, one clone of the repo, no channel to any other agent. One handoff when done.
- Subplanners are recursive planners. A planner publishes a "subplan this slice" task; the subplanner fully owns that slice and hands back an aggregated handoff.
- Continuous motion via handoffs. A planner that thought it was done can receive a late handoff and replan. No "finished" state until the planner decides to stop publishing.
- Propagation, not synchronization. No cross-talk between siblings. No shared state between levels. Each level sees only its children's handoffs.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- LICENSE.txt 1.0 KB
- prompts/andon-block.md 665 B
- prompts/empty-error-handoff.md 206 B
- prompts/failure-handoff.md 554 B
- prompts/finished-no-handoff.md 735 B
- prompts/loop-hygiene.md 1.8 KB
- prompts/root.md 670 B
- prompts/slack-block.md 1.5 KB
- prompts/subplanner.md 3.0 KB
- prompts/verifier.md 3.9 KB
- prompts/worker.md 3.0 KB
- references/dispatcher.md 3.2 KB
- references/handoffs.md 11 KB
- references/planner.md 9.2 KB
- references/spawning.md 7.8 KB
- schemas/plan.schema.json 22 KB
- schemas/state.schema.json 7.4 KB
- scripts/__tests__/agent-manager-slack-mirror.test.ts 17 KB runs code
- scripts/__tests__/andon-root-cache.test.ts 12 KB runs code
- scripts/__tests__/checkpoint-restart.test.ts 6.2 KB runs code
- scripts/__tests__/comment-cli.test.ts 7.5 KB runs code
- scripts/__tests__/comment-retry-queue.test.ts 12 KB runs code
- scripts/__tests__/exit-on-error.test.ts 5.0 KB runs code
- scripts/__tests__/failure-handoff.test.ts 6.5 KB runs code
- scripts/__tests__/handoff-branch-parser.test.ts 3.8 KB runs code
- scripts/__tests__/handoff-verification-parser.test.ts 4.1 KB runs code
- scripts/__tests__/handoff-verification-record.test.ts 5.4 KB runs code
- scripts/__tests__/kickoff-dedupe.test.ts 4.6 KB runs code
- scripts/__tests__/measurements-compare.test.ts 6.1 KB runs code
- scripts/__tests__/measurements-mismatch.test.ts 9.1 KB runs code
- scripts/__tests__/measurements-parser.test.ts 3.1 KB runs code
- scripts/__tests__/models-catalog.test.ts 3.6 KB runs code
- scripts/__tests__/operator-boundary.test.ts 3.3 KB runs code
- scripts/__tests__/probe-models.test.ts 1.9 KB runs code
- scripts/__tests__/prompt-plan-validation.test.ts 2.6 KB runs code
- scripts/__tests__/redact-body.test.ts 1.6 KB runs code
- scripts/__tests__/schemas.test.ts 8.5 KB runs code
- scripts/__tests__/slack-adapter.test.ts 9.7 KB runs code
- scripts/__tests__/slack-channel-boundary.test.ts 2.5 KB runs code
- scripts/__tests__/slack-message-format.test.ts 2.6 KB runs code
- scripts/__tests__/slack-prompt-shape.test.ts 6.8 KB runs code
- scripts/__tests__/support/slack-web-api-mock.ts 2.1 KB runs code
- scripts/__tests__/verifier-startingref-reconcile.test.ts 8.6 KB runs code
- scripts/__tests__/wait-handoff-failure.test.ts 9.6 KB runs code
- scripts/__tests__/watchdog-inspect.test.ts 2.8 KB runs code
- scripts/__tests__/worker-branch-discipline.test.ts 3.9 KB runs code
- scripts/adapters/index.ts 366 B runs code
- scripts/adapters/README.md 1.2 KB
- scripts/adapters/slack/client.ts 446 B runs code
- scripts/adapters/slack/index.ts 8.2 KB runs code
- scripts/adapters/types.ts 1.8 KB runs code
- scripts/biome.json 503 B
- scripts/bun.lock 39 KB
- scripts/cli.ts 73 B runs code
- scripts/cli/andon.ts 3.8 KB runs code
- scripts/cli/comments.ts 10.0 KB runs code
- scripts/cli/forensics.ts 5.3 KB runs code
- scripts/cli/index.ts 958 B runs code
- scripts/cli/inspect.ts 7.6 KB runs code
- scripts/cli/task.ts 20 KB runs code
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.
- 4d ago First seen · 50 lines · 54 tokens per session scan A ece33991515f
orchestrate is a skill published in the GitHub repository heyAyushh/stacc (3 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 924 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…