Global behavior
AGENTS.md holds durable rules that should apply across projects: verify before stating, fix root causes, respect approval boundaries, and communicate like a human.
Back to homeOPEN SOURCE · CODEX + CLAUDE · MIT
Agent Brain
The public-safe master brain I use with coding agents: current operating instructions, 26 reusable skills, and adapters for Codex and Claude Code.
bash <(curl -fsSL https://dormizrahi.com/install)macOS or Linux · Codex, Claude Code, or both · Existing matching files are backed up first.
One brain, two runtimes
AGENTS.md is the canonical source. Codex reads it directly. Claude gets a tiny CLAUDE.md that imports it and adds only Claude-specific wiring.
Source of truth
~/.codex/AGENTS.mdCollaboration rules, verification discipline, approval boundaries, communication style, and information ownership.
Claude adapter
~/.claude/CLAUDE.mdImports the canonical brain and describes only Claude's skill and style-hook wiring.
On-demand workflows
~/.agents/skills/ + ~/.claude/skills/The same 26 master skills are exposed to both agents and loaded only when relevant.
Where every kind of truth lives
Project behavior
A project AGENTS.md contains only unusual local rules and pointers. A project CLAUDE.md imports it instead of duplicating it.
Operational facts
Code, configuration, migrations, logs, and live inspection remain authoritative. The brain tells the agent to look; it does not cache facts that will rot.
Current work
The project's existing sprint, session, issue tracker, or handoff system owns status. Agent Brain follows the project's existing structure.
Reusable procedure
Skills hold conditional workflows. They load when their trigger matches instead of living in the global context on every turn.
26 reusable master skills
These are the cross-project workflows from my real shared brain. Client, CodeApp, Puffa, and other project-specific skills are not included.
Core workflow
init-projectorient-statuswait-whatsprinthandoffEngineering
implementdiagnosing-bugstddcode-reviewresolving-merge-conflictsArchitecture and modeling
codebase-designimprove-codebase-architecturedomain-modelingprototypeThinking and planning
grillinggrill-megrill-with-docsresearchto-specto-ticketsto-questionnairetriagewayfinderAgent tooling
writing-for-agentswizardteachSession summaries in English and Hebrew
The handoff skill recognizes natural requests in either language, writes the next project-native session file, updates the active progress log when appropriate, and records the exact next action.
Summarize the sessionClose the sessionסכם את הסשןתסכם את השיחהסגור את הסשןWhat changes in the agent
Evidence before confidence
Claims about files, runtime behavior, tests, and external facts must come from something inspected or run. Unknowns stay labeled unknown.
Outcome before implementation
The agent establishes what the user is trying to achieve before choosing a technical mechanism.
Autonomy with real boundaries
Safe reads, diagnostics, and approved local work continue without ceremony. Pushes, deployments, destructive deletion, purchases, and messages to others still wait for explicit approval.
Plain communication
The style layer leads with the answer and removes filler without reducing English to cryptic fragments.
Exactly what gets installed
| Path | Owner |
|---|---|
| ~/.codex/AGENTS.md | Canonical global brain |
| ~/.agents/README.md | Shared-layer map |
| ~/.claude/CLAUDE.md | Thin Claude adapter |
| ~/.agents/skills/<skill>/ | Shared Codex skill copies |
| ~/.claude/skills/<skill>/ | Claude skill copies |
| ~/.claude/rules/conversation-style.md | Full Claude response-style rule |
| ~/.claude/hooks/conversation-style-*.js | Session and per-prompt style reinforcement |
| ~/.claude/commands/summarize-session.md | Claude compatibility alias for handoff |
| ~/.claude/settings.json | Two hook entries merged; other settings preserved |
| ~/.agents/backups/agent-brain-install-*/ | Pre-install copies of replaced files |
What it deliberately does not do
- ✓It does not copy Dor's client instructions, project lists, audit archives, credentials, or personal work history.
- ✓It does not enable bypass-permissions or change any existing permission mode.
- ✓It does not install notification sounds, send messages, connect accounts, push code, or deploy anything.
- ✓It installs the public-safe cross-project master layer, not client or product-specific workflows.
Install it only after you understand it
The installer asks three personalization questions, prints every destination, backs up matching files, and then writes the package. Read the source or run it locally first if you want to inspect every line.
bash <(curl -fsSL https://dormizrahi.com/install)