What's in the seed
Think of it as a battle-tested checklist for working with AI coding tools.
A portable bootstrap for AI-assisted development. Six seed tiers cover Phase 0 setup, AGENTS.md scaffolding, coordination patterns, references to six optional modules.
Install — Register the marketplace, then install plugins
Install — Marketplace registration + plugin install
EstreGenesis ships as seven Claude Code plugins — a kit plugin that installs EstreGenesis itself, plus six optional modules. Two steps:
EstreGenesis ships as seven independent Claude Code plugins published through a single marketplace: the `estregenesis` kit + six optional modules. Two-step install:
(A) register the marketplace once, then (B) install the plugins you want from the cards below.
(A) one-time marketplace registration (idempotent — re-running is safe), then (B) per-plugin install commands. Plugins are independent — install any subset.
Run this once in Claude Code to tell it where the EstreGenesis plugins live.
Run once in Claude Code to register the marketplace source. The shorthand resolves to the repo's marketplace manifest.
/plugin marketplace add SoliEstre/EstreGenesisStart with the first card (the kit) — it installs EstreGenesis itself and gives you the /egboot command. Then pick any of the module cards.
Copy any install command from the seven cards below. Each plugin is independent. The `estregenesis` kit is the recommended first install: /egboot · /egmig · /egup · /egmem · /egrich fetch and run the seed for you.
Available plugins
EstreGenesis (kit)
EstreGenesis itself, as commands. Type /egboot and the agent fetches the right starter document and sets your project up — no copy-pasting a URL.
6 procedures: /egboot (new) · /egmig (existing rule files) · /egup (seeded — seed + plugin delta) · /egmem (memory ↔ docs true-up) · /eg-interview (intake brief) · /egrich (full arm). Seed URLs baked in; the seed is fetched and run, never restated.
/plugin install estregenesis@estregenesis-plugins
No extra libraries needed · Start here
Superscalar
Rules for running many AI agents in parallel without losing consistency.
Execution-scheduling discipline for parallel sub-agent dispatch: issue_width bound + worktree isolation + in-order retire + consistency gate.
/plugin install superscalar@estregenesis-plugins
No extra libraries needed
Hyperbrief
When an AI asks you to decide, it gives you a one-page summary in a fixed shape (what · why · options · recommendation).
Decision-delegation gating: 4-score trigger rubric + JSON IR + deterministic Node renderer → MD + interactive HTML. 9-section structure, 3-axis × 5-level tone profile, byte-identical output.
/plugin install hyperbrief@estregenesis-plugins
Needs: ajv library (one of the standard schema-checking libraries for Node)
Greatpractice
Small obligations you keep forgetting (update the docs · check before sending · sync paired files) get turned into auto-enforced rules.
Memory-triggered practice codification. feedback_*.md entries pass a 5-axis maturation gate, graduate into a 3-tier hierarchy, enforced via 7-event lifecycle hooks.
/plugin install greatpractice@estregenesis-plugins
No extra libraries needed · 🐶 Early dogfooding
Ultrasafe
Before each release, several AI helpers act like attackers and look for weak spots — at the same time, from different angles.
Pre-release simulated pentest. 8-agent parallel red-team fan-out + GTA/DSP cross-cutting. ≥3 iteration loop + 4-condition AND clean-signal gate. 3-layer synthesis (OSCAL + Hyperbrief IR + Greatpractice).
/plugin install ultrasafe@estregenesis-plugins
No extra libraries needed · 🐶 Early dogfooding
Constellation
Live workspace where multiple AI agents talk to each other in real time.
Live multi-agent orchestration: WebSocket + A2A + dashboard + MCP. 24h dogfood: 5 e2e PRs, 0 violations.
/plugin install constellation@estregenesis-plugins
Needs: ws library (one of the standard WebSocket libraries for Node)
Compendium
A shared dictionary for your project: one definition per term, plain and expert registers, always pointing back to the owning document.
Controlled-vocabulary layer over markdown+frontmatter: dual-register glossary, pointer-not-paraphrase authority, 8-tool MCP server, gardening lint, 2 cross-tool skills.
/plugin install compendium@estregenesis-plugins
No extra libraries needed · 🐶 Early dogfooding
All seven plugins work the same way in Claude Code CLI and VS Code extension — and also run on OpenAI Codex through a small included adapter. The environments section below shows where to start in each.
All seven plugins behave identically across Claude Code CLI and VS Code extension; the same skills + MCP servers also project onto OpenAI Codex via the bundled adapter. The environments section covers all three entry points.
How you'll use this
How to use it — per environment
You can use EstreGenesis in three places: the Claude Code terminal (CLI), the Claude Code panel inside VS Code, and — through a small included adapter — OpenAI Codex.
Three host environments: Claude Code CLI + VS Code (identical plugin behaviour), and OpenAI Codex via the bundled adapter (skills + MCP project losslessly; hooks map to a documented manual discipline).
Claude Code CLI
Run Claude Code directly from the terminal.
Direct-from-terminal session. Best fit for headless workflows, CI integration, tmux-based multi-agent setups.
- Start Claude Code in the terminal:
claudeorclaude code - Register the marketplace:
/plugin marketplace add SoliEstre/EstreGenesis - Install your chosen plugin:
/plugin install constellation@estregenesis-plugins(or any other module name) - Use slash commands, skills, and hooks in your session.
- Launch a CLI session:
claude(orclaude code) from your project root. - Register the marketplace (one-time, idempotent):
/plugin marketplace add SoliEstre/EstreGenesis - Install per-plugin:
/plugin install <name>@estregenesis-plugins— any subset of the six modules. - Slash commands, skills, and hooks are now active — plugin hooks fire on lifecycle events (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, PostCompact).
Claude Code VS Code Extension
Use Claude Code as a panel inside VS Code.
VS Code extension surface — sidebar chat panel + integrated editor diff view. Best fit for IDE-resident workflows where the agent operates alongside open editor buffers.
- Install the Claude Code extension: search "Claude Code" in the VS Code extension marketplace (or visit https://claude.com/code)
- Open Claude Code: use the sidebar panel or press
Ctrl+Shift+P(Cmd+Shift+P on Mac) and search for "Claude Code: Open Chat" - Register the marketplace: type
/plugin marketplace add SoliEstre/EstreGenesisin the chat window - Install plugins: use
/plugin install <name>@estregenesis-plugins, then access modules from the sidebar.
- Install the Claude Code extension from the VS Code marketplace (search "Claude Code") or https://claude.com/code.
- Open the chat surface: sidebar panel or
Ctrl+Shift+P(Cmd+Shift+Pon Mac) → "Claude Code: Open Chat". - Register marketplace in the chat input:
/plugin marketplace add SoliEstre/EstreGenesis(one-time, idempotent). - Install per-plugin via
/plugin install <name>@estregenesis-plugins; skills and slash commands surface in the sidebar and accept the same lifecycle hooks as the CLI host.
OpenAI Codex (adapter)
Use the same EstreGenesis skills from OpenAI Codex — a small adapter that ships inside the repo sets everything up.
Codex converged on the same three customization surfaces EG speaks, so the codex/ adapter is a projection, not a fork: one script materializes the skills and generates the MCP config stanzas.
- Get the repo once:
git clone https://github.com/SoliEstre/EstreGenesis - Let the adapter place the skills:
node codex/gen-codex-adapter.cjs --install - (Optional) copy the tool-server entries from
codex/config.toml.exampleinto your Codex settings. - Read
codex/README.mdfor the full list and the short manual routines that replace the automatic hooks.
- Clone the repo (the adapter projects from the live plugin tree):
git clone https://github.com/SoliEstre/EstreGenesis - Materialize the skills into Codex's discovery path:
node codex/gen-codex-adapter.cjs --install - Register the MCP servers: merge the four
[mcp_servers.*]stanzas fromcodex/config.toml.exampleinto$CODEX_HOME/config.toml. - Hooks don't port — follow
codex/AGENTS.md: each lifecycle hook maps to a paired-skill invocation at the documented moment.
Across the two Claude Code environments everything behaves identically. On Codex, the same skills and tool servers work — only the automatic hooks become a short written routine.
The two Claude Code entry paths land on the same plugin runtime. The Codex path shares the skill set and MCP servers via the projection; hook parity is by discipline, not by runtime.
What we made in the first 24 hours
Initial 24h dogfood — what shipped
First day after public release, before the modules below were folded in. Numbers have grown since — see below.
Historical snapshot from the first 24h (around v2.5.15). Predates the Hyperbrief module ship + adopter bundles absorbed since.
Since then
Cumulative since the 24h baseline
Pace settled but didn't stop. Four more modules joined (→6 total); adopter reports keep folding back in.
Cumulative tags now at v2.5.183. Post-133: roundtable rooms + peer kind, loop contract + worker profile, adapter contract v0.2 (Hermes/OpenClaw candidates), the gateway-program six-cut day, /subscaler, and the board-UX wave. Thirteen cuts on 2026-07-19 alone.
The headline finding
Running AI agents in parallel doesn't automatically give good results. Speed without discipline ≠ quality.
Parallelism is not sufficient; orchestration discipline produces consistency. Wall-clock cost is phase serialisation, not parallel inefficiency.
AI-readable full text
Everything on these pages is a human-register summary. The complete normative text lives in the spec .md files.