agentmods.dev

atelier

A personal development toolkit for AI coding agents that uses written specifications, focused reasoning, and code-quality workflows. It includes agents and skills for planning, implementation, debugging, review, handoffs, pull requests, and commits.

In plain words
What is it for?
Use it for specification-led planning, domain modelling, debugging, code review, creating pull requests, coordinating subagents, and preparing commits or handoffs.
Why use it?
It provides a structured way to move from an idea to reviewed code. The included workflows help clarify requirements, make decisions explicit, and keep development work organized.

Plugin for Claude Code

44 23d ago A scan tokens not measured original MIT
View the source file martinffx/atelier
Install

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.

Claude Code
/plugin marketplace add martinffx/atelier
agentmods
npx agentmods add plugins/martinffx/atelier/marketplace
Clone the repo
git clone --depth 1 https://github.com/martinffx/atelier

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

atelier 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.

.claude-plugin/marketplace.json · 43 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "atelier",
  "description": "Personal development toolkit for AI agents - spec-driven development, code quality, and deep thinking",
  "owner": {
    "name": "Martin Richards"
  },
  "renames": {
    "spec": "atelier",
    "oracle": "atelier",
    "code": "atelier"
  },
  "plugins": [
    {
      "name": "atelier",
      "description": "Spec-driven development, deep thinking, and code quality workflows",
      "source": "./",
      "strict": false,
      "agents": [
        "./agents/oracle.md",
        "./agents/architect.md",
        "./agents/sentinel.md"
      ],
      "skills": [
        "./skills/spec-brainstorm",
        "./skills/spec-finish",
        "./skills/spec-implement",
        "./skills/spec-plan",
        "./skills/atelier-orchestrator",
        "./skills/atelier-setup",
        "./skills/oracle-debug",
        "./skills/oracle-grill-me",
        "./skills/oracle-domain-modelling",
        "./skills/code-commit",
        "./skills/code-handoff",
        "./skills/code-pull-request",
        "./skills/code-review",
        "./skills/code-subagents"
      ]
    }
  ]
}
Changes

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.

  1. 2d ago First seen · 43 lines scan A 007c53ce2ff0

Subscribe to this mod's changes

atelier is a plugin published in the GitHub repository martinffx/atelier (44 stars, last pushed 23d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Code reviewData and AIDebuggingagent-skillsagentic-codingclaude-codeopencodeprompt-engineering
Related

Other plugins, from other repositories

oh-my-claudecode

Multi-agent orchestration system for Claude Code.

Yeachan-Heo/oh-my-claudecode · not measured

omc

Claude Code native multi-agent orchestration - intelligent model routing, 28 agents, 35 skills.

Yeachan-Heo/oh-my-claudecode · not measured

rp1-base

Core knowledge management, documentation generation, and strategic analysis for Claude Code.

rp1-run/rp1 · not measured

rp1-dev

Development workflow automation including feature development, code quality, and PR management.

rp1-run/rp1 · not measured

rp1-run

Plugin marketplace listing 2 plugins: rp1-base, rp1-dev.

rp1-run/rp1 · not measured

antimicrobial-resistance-scientist

Reasons from MIC distributions, ECOFFs, and phenotype–genotype concordance through EUCAST/CLSI AST, CARD/RGI and AMRFinderPlus resistomes, GLASS/WHONET/NARMS surveillance, carbapenemase/ESBL/MRSA mechanism panels, and heteroresistance PAP while treating breakpoint mixing, genotype-without-phenotype overclaim…

K-Dense-AI/scientific-agents · not measured