Atelier
A personal development toolkit for AI agents. It covers spec-driven development, code quality, and deep thinking.
Atelier gives coding agents a disciplined way to move from an idea to reviewed, verified code without taking control away from the developer.
npx skills add martinffx/atelier
npx @martinffx/atelier@latest init --harness <claude|opencode|codex|cursor>
For OpenCode, installing skills first also creates slash commands for every installed skill
marked user-invocable: true. If you initialize first, run npx @martinffx/atelier@latest update --harness opencode
after installing skills.
How Atelier works
Atelier uses as much process as each request needs. Bounded work gets a concise plan in the conversation. Substantial work gets a durable spec, an implementation plan, and tracked execution. The developer approves the plan before implementation begins.
flowchart TD
R[Request] --> O[atelier-orchestrator]
O -->|Bounded work| IP[spec-plan: Inline Plan]
IP --> IA{Developer approval}
IA -->|Approved| I[Implement directly]
IA -.->|Revise| IP
I --> V[Validate]
V -.->|Issues found| I
IP -.->|Needs brainstorming| B
I -.->|Needs brainstorming| B
O -->|Substantial work| B[spec-brainstorm]
B --> D[design.md]
D --> G[oracle-grill-me]
G --> P[spec-plan]
G -.->|Refine design| D
P --> SA{Developer approval}
SA -->|Approved| J[plan.json]
SA -.->|Revise plan| P
SA -.->|Revisit design| B
J --> SI[spec-implement]
SI --> CR[code-review]
CR --> F[spec-finish]
F --> PR[code-pull-request]
SI -.->|Revise plan| P
SI -.->|Revisit design| B
F -.->|Issues found| SI
The workflow is deliberately harder to rush than an unstructured agent session. It records decisions when they need to survive the conversation, keeps implementation tied to an approved plan, and requires evidence before calling the work complete.
Grill the idea
oracle-grill-me interviews you one question at a time until the important decisions are explicit. It researches facts from the codebase instead of asking you to supply them, gives a recommended answer for each decision, and leaves the final choice with you.
As the discussion resolves, it maintains the project's domain language and architectural decisions. Use it on a proposal, plan, migration, or design that feels settled a little too quickly.
Grill me on this migration plan
Review the code
code-review runs a multi-agent review rather than asking one agent for a general opinion. Sentinel triages the diff, specialist reviewers examine likely failure modes in parallel, Architect checks design boundaries, and a final challenge pass removes weak or unsupported findings.
rq # Review the diff to main
rq develop # Review against another branch
rs # Work through the findings
It reports findings before changing code. You decide which fixes to apply.
What you get
Atelier installs a focused set of skills for the full development loop:
| Area | Capabilities |
|---|
| Spec workflow | Discovery, research, planning, implementation, validation, and finishing |
| Thinking | Root-cause debugging, decision grilling, and domain modelling |
| Delivery | Multi-agent review, subagent coordination, commits, handoffs, and pull requests |
The CLI also configures three specialist agents for Claude Code, OpenCode, Codex, or Cursor:
| Agent | Role |
|---|
| Sentinel | Fast codebase reconnaissance and review triage |
| Oracle | Requirements, trade-offs, and adversarial analysis |
| Architect | Domain modelling, system design, and architecture review |
Run npx @martinffx/atelier@latest --help for CLI commands and options. Each skill contains its own operating instructions and loads when its context applies.
Ecosystem
Language-specific guidance lives in companion repositories:
Rationale and inspiration
Better models alone do not produce better software. Coding agents, like human teams, are shaped by the systems they work within. Good outcomes depend on more than individual ability. They depend on the processes, constraints, shared context, and feedback surrounding the work. If that system does little to encourage quality or catch weak results, agents will simply produce unreliable code faster. Atelier is an attempt to build a better system around the agent, making robust output more repeatable. Building Your Own Agent Harness explains the thinking behind it.
The name is literal. An atelier is a workshop where a principal works with assistants. Here, the developer is the principal, agents are the assistants, the codebase is the workshop, and skills record how the work happens.
Atelier draws on spec-driven development and several projects that informed its approach to agent collaboration:
- Agent OS for discovering project standards and shaping lightweight specs.
- OpenSpec for fluid, artifact-guided workflows that support iteration and brownfield development.
- GitHub Spec Kit for making specifications central to a structured specify, plan, tasks, and implement workflow.
- Superpowers for composable skills, mandatory engineering workflows, TDD, and evidence-based verification.
- Matt Pocock's Skills for small, adaptable skills grounded in practical engineering and developer control.
Some Atelier skills have more direct lineage:
code-commit follows the Conventional Commits specification.
Atelier adapts these ideas into an opinionated toolkit that works across harnesses. It does not claim to have invented the practices it uses.
Development
Load the repository directly in Claude Code:
claude --plugin-dir ./atelier
Build and test the CLI:
bun run build
bun test
bun run typecheck
Restart your coding harness after changing skills so it reloads their definitions.
License
MIT Copyright (c) 2026 Martin Richards
