agent-role-designer
Design narrow Codex custom-agent role contracts and sandbox requirements for an approved team topology.
Skill by EmbroiderSnow
Chalk Labs
Need help deploying agent-role-designer?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/embroidersnow-agent-role-designer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-role-designer
What's inside
- Skill name
agent-role-designer- Description
- Design narrow Codex custom-agent role contracts and sandbox requirements for an approved team topology. Use when roles need explicit missions, non-responsibilities, inputs, outputs, stop conditions, or project-scoped TOML configuration.
- License
- MIT
- Instructions
- 20 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- render_agent_configs.py · scripts/
SKILL.md (first lines)
For each role, define: - stable role id and matching custom-agent profile - mission - responsibilities - non-responsibilities - sandbox mode - minimum tool access - inputs - structured outputs - stop conditions - escalation conditions Prefer read-only for analysis and review. Grant workspace-write only to implementation, test-writing, or integration roles that own explicit paths. Do not pin a model unless the user or repository has an evaluated model policy. Do not give a Reviewer write permissions merely for convenience. When asked to generate TOML, use the required Codex fields `name`, `description`, and `developer_instructions`, plus `sandbox_mode` where appropriate. Generated configurations take effect in a new Codex session.
From EmbroiderSnow/Agent-Team-Design, MIT.
More from EmbroiderSnow/Agent-Team-Design
- 0.479score
agent-team-designer
EmbroiderSnow
Design the smallest reliable Codex agent team for complex engineering work.
SkillCFreshness: CClaude Code +9 - 0.479score
agent-team-runner
EmbroiderSnow
Execute a validated Agent Team Specification with Codex subagents.
SkillCFreshness: CClaude Code +9 - 0.476score
stability-test-designer
EmbroiderSnow
Design static checks, runtime gates, failure injection, and regression evaluation for a Codex agent-team workflow.
SkillCFreshness: CClaude Code +9 - 0.476score
workflow-auditor
EmbroiderSnow
Audit an Agent Team Specification or run report for DAG validity, role boundaries, write conflicts, review independence, risk gates, retry safety, budget, and…
SkillCFreshness: CClaude Code +9 - 0.471score
workflow-retrospective
EmbroiderSnow
Analyze Agent Team run reports and evaluation metrics to improve topology, roles, prompts, ownership, validation, and budgets.
SkillCFreshness: CClaude Code +9 - 0.471score
workload-profiler
EmbroiderSnow
Convert an engineering task into a six-dimensional agent workload profile and deterministic routing recommendation.
SkillCFreshness: CClaude Code +9 - 0.471score
workflow-dag-designer
EmbroiderSnow
Convert an approved topology and role set into an executable task DAG with dependencies, ownership, timeouts, retries, and output contracts.
SkillCFreshness: CClaude Code +9 - 0.471score
team-topology-designer
EmbroiderSnow
Select and justify a bounded Codex agent-team topology from an accepted workload profile.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 10, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from EmbroiderSnow
- 0.479score
agent-team-designer
EmbroiderSnow
Design the smallest reliable Codex agent team for complex engineering work.
SkillCFreshness: CClaude Code +9 - 0.479score
agent-team-runner
EmbroiderSnow
Execute a validated Agent Team Specification with Codex subagents.
SkillCFreshness: CClaude Code +9 - 0.476score
stability-test-designer
EmbroiderSnow
Design static checks, runtime gates, failure injection, and regression evaluation for a Codex agent-team workflow.
SkillCFreshness: CClaude Code +9 - 0.476score
workflow-auditor
EmbroiderSnow
Audit an Agent Team Specification or run report for DAG validity, role boundaries, write conflicts, review independence, risk gates, retry safety, budget, and…
SkillCFreshness: CClaude Code +9 - 0.471score
workflow-retrospective
EmbroiderSnow
Analyze Agent Team run reports and evaluation metrics to improve topology, roles, prompts, ownership, validation, and budgets.
SkillCFreshness: CClaude Code +9 - 0.471score
workload-profiler
EmbroiderSnow
Convert an engineering task into a six-dimensional agent workload profile and deterministic routing recommendation.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get agent-role-designer running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
agent-role-designer skill. Agent Mart. https://agentmart.dev/skills/embroidersnow-agent-role-designer (last updated 2026-10-24)