App Automaton / agent-designer
Repository · agent-designer Codex · Claude · Gemini MIT licensed

Methodical agents
by design.

A portable skills workspace for AI coding agents, the kind that gives Claude Code, Codex, and Gemini clear workflows, safe defaults, and the ability to delegate to one another with session continuity. Clone it as a starting point for any project where you want agents to work deliberately rather than freestyle.

4 skills · 3 bridge scripts · 1 issue-driven workflow · workflow-first · text, not code
github.com/appautomaton/agent-designer · Open source · Workflow-first
Why agent-designer

Agents write code well.
Sustaining intent is the harder part.

Models are good at the next token. They are less good at the next hour: keeping the work coherent across long sessions, multiple files, and the moments where one agent hands off to another.

agent-designer is built around that gap. Rather than another tool, it is a small workspace of disciplines you bring with you into a project: a folder of skills in plain markdown, a few bridge scripts, and a way to break large work down so an agent can drive it on its own.

Each skill follows the same shape, with frontmatter the agent always sees, a workflow body it loads on invocation, and references it pulls only when the path narrows. That shape is portable: the same skills work under Codex, under Claude Code, under Gemini, with minimal adaptation. Most changes here are text, not code. The repository is workflow-first.

Out of the box you get two complementary disciplines. Cross-agent collaboration gives you three bridge scripts that let one agent consult another with full session continuity, returning the same JSON envelope on every turn. The issue-driven workflow lets you plan once, then hand the agent a CSV it can execute end to end, every row a granular, testable, markable unit of work.

Cross-agent collaboration

Three bridges.
One session.

When Codex hits a problem it wants a second opinion on, it can ask Claude and stay in the same conversation through five turns. When Claude needs the web, it can hand the question to Gemini and read what comes back. Each bridge wraps a CLI and returns the same shape: a JSON envelope with a SESSION_ID you pass back to resume.

Claude Code
collaborating-with-claude

Delegate review, diff, and design consultation. Multi-turn back-and-forth while you implement locally, with second opinions, edge-case checks, and test gaps.

SAFETY --permission-mode plan
Codex
collaborating-with-codex

Delegate implementation, diagnosis, or adversarial review. Sandboxed by default, read-only unless you explicitly grant workspace writes.

SAFETY --sandbox read-only
Gemini
collaborating-with-gemini

Delegate research with built-in web grounding, or hand off image and screenshot analysis. Returns a unified diff when you ask for code changes.

SAFETY --sandbox
Session envelope · returned by every bridge stream-json
Turn 1 · open the conversation
$ python3 scripts/claude_bridge.py \
  --cd "." --PROMPT "Review login() in src/auth.py."
 
# returns ↓
{
  "success": true,
  "SESSION_ID": "f9d4-…",
  "agent_messages": "…"
}
Turn 2 · resume by ID
$ python3 scripts/claude_bridge.py \
  --cd "." \
  --SESSION_ID "f9d4-…" \
  --PROMPT "Now propose a fix."
 
# same shape on every turn,
# across every CLI.
Issue-driven workflow

Plan once.
Then let it run.

Front-load the thinking and the agent has a full plate of useful work per run. The plan and Issue CSV act as a work amplifier, every row a granular, testable, markable unit. The agent reads, sets Dev_Status = DOING, completes the row, and immediately moves to the next.

issues/2026-05-06_14-22-08-search-relevance.csv 7 rows · plan/2026-05-06_14-22-08-search-relevance.md
ID Task Dependencies Dev_Status Review1_Status
001 Audit current scoring weights in ranker.py Done Done
002 Add BM25 baseline test fixtures 001 Done Done
003 Implement reciprocal-rank fusion in ranker.py 001, 002 Doing Todo
004 Wire the fusion path through search/handler.py 003 Todo Todo
005 Add latency benchmark, assert p95 < 80ms 004 Todo Todo
006 Document the new ranking path in README 004 Todo Todo
007 Regression sweep across saved query corpus 003, 004, 005 Todo Todo

The CSV is the agent's state. It reads to know where it is, updates as it works, and keeps driving forward. It stops only for genuinely blocking unknowns and decides anything routine itself. Loop: plan → issues → implement → test → review.

In one breath

Three principles.

Workflow-first

Text, not code.

Skills are markdown. Most changes here are prose, not refactors. The discipline lives in how you write the workflow, not in the surrounding scaffolding.

Portable

One shape, every agent.

The same skills run under Codex, Claude Code, and Gemini. The same envelope returns from every bridge. Move between agents without re-learning the surface.

Methodical

Plan, then drive.

The Issue CSV turns vague intent into a queue the agent can complete autonomously. Stops only for genuinely blocking unknowns.

$ gh repo clone appautomaton/agent-designer