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 siarhei-belavus/agent-public --skill atelier-orchestratorgit clone --depth 1 https://github.com/siarhei-belavus/agent-publicWrote 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/siarhei-belavus/agent-public/atelier-orchestrator)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/atelier-orchestrator"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/atelier-orchestrator/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/siarhei-belavus/agent-public/atelier-orchestrator"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/atelier-orchestrator.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 | $0.00086 | $0.04136 |
| Opus 5 | $0.00043 | $0.02068 |
| Sonnet 5 | $0.00017 | $0.00827 |
| Haiku 4.5 | $0.00009 | $0.00414 |
Grade A, and why
atelier-orchestrator 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 11d 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
atelier-orchestrator
Run atelier as a task-centric control loop:
- one task window
- one lead/orchestrator pane
- ephemeral right-side worker panes only while active
- pi teams runtime teams plus predefined agent definitions for worker prompts/model
Use this skill as the lead. Do not implement or review directly unless the human explicitly asks.
Read first
../references/task-packet-contract.md../references/persistent-artifacts-contract.md../references/review-phases-contract.md../references/compatibility-policy.md../references/ownership-and-reuse-policy.md../references/initiative-packet-contract.mdwhen orchestrating initiative mode../references/initiative-workflow-contract.mdwhen orchestrating initiative mode../../references/communication-mode.md- relevant tracked
AGENTS.mdchain - applicable
AGENTS.override.mdonly if local execution constraints matter REFERENCE.md
Agent definitions
Use predefined agent definitions from ~/.pi/agent/agents/ as the source of truth for worker prompts/model:
atelier-planneratelier-plan-revieweratelier-implementeratelier-plan-sat-revieweratelier-maint-revieweratelier-distiller
Do not rely on predefined full teams for normal orchestration. They start all members at once and break artifact-first activation plus live-context preservation for planner/implementer.
Quick start
- Confirm task slug, repo cwd, and desired outcome.
- Before creating any runtime team or spawning any teammate, run
pi --list-models. - Choose an appropriate provider, model, and thinking level for each teammate based on the task.
- Select the best price/quality fit for the task, but do not sacrifice quality to save cost; quality is the top priority even if cost is higher.
- Prefer providers in this order when suitable:
openai-codex,zai,github-copilot,anthropic. - Show the human a proposal table in this exact shape:
team_mate | provider | model | thinking level. - Ask for approval or refinement. Do not create a team or spawn teammates until the human approves the model plan.
- Keep only the lead alive at start.
- Run discovery yourself with
grill-mestyle questioning. - Create only the runtime team needed for the current phase.
- Spawn workers incrementally as artifacts become reviewable.
- Preserve planner/implementer live context across their whole phase.
- Shut down the current phase team before moving to the next phase.
- End with distillation and orderly cleanup.
What ships with it
1 file 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.
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.
- 11d ago First seen · 391 lines · 86 tokens per session scan A 1311b95f2714
atelier-orchestrator is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 4,136 once invoked, about $0.0004 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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…