Setup · Open source · MIT

Four plugins.
Install only what you need.

Cortex, zetetic-team-subagents, automatised-pipeline, and prd-spec-generator each ship as an independent Claude Code marketplace — there is no combined monorepo install. One command adds the marketplace, one command installs the plugin. Under two minutes each.

Requires Claude Code. Each plugin installer copies its agents, skills, hooks, and tools into ~/.claude/.

Pick what you need.

Each plugin is useful alone. Installed together, they interoperate through the same MCP layer — memory remembers, reasoning reasons, codebase maps, prd adjudicates the spec.

Memory · v4.14.3

Cortex

Persistent memory across sessions. 50 MCP tools, 9 lifecycle hooks, 36 cited neuroscience mechanisms. LongMemEval-S MRR 0.9166 / Recall@10 98.20%. SQLite by default, PostgreSQL + pgvector optional.

> /plugin marketplace add cdeust/Cortex
> /plugin install cortex@cortex-plugins

Restart Claude Code, then run /cortex-setup-project to bootstrap the database, embedding model, and hooks. The same marketplace also carries the read-only cortex-viz companion: /plugin install cortex-viz@cortex-plugins. Read more →

Reasoning · v2.29.0

zetetic-team-subagents

119 reasoning agents (97 genius patterns + 22 team-role specialists). 64 skills, 19 lifecycle hooks, 288 tests. Pre-commit hook blocks unsourced constants (UNSOURCED / MAGIC_NUMBER / TODO_NO_REF).

> /plugin marketplace add cdeust/zetetic-team-subagents
> /plugin install zetetic-team-subagents

No toolchain prerequisite beyond Claude Code. The installer copies agents, skills, hooks, and tools into ~/.claude/. Read more →

Code intelligence · v0.7.0

automatised-pipeline

Rust MCP server. Indexes codebases across 10 languages into a property graph, resolves call chains, detects communities, traces execution flows. 24 MCP tools, 434 tests, 45,000+ lines of Rust.

> /plugin marketplace add cdeust/automatised-pipeline
> /plugin install automatised-pipeline

Requires Rust 1.94+ (rustup install stable) and CMake on PATH; the release binary builds on first launch (~5 minutes, cached after). Read more →

PRD pipeline · v0.6.0

prd-spec-generator

Multi-judge PRD generation with closed-loop, externally-grounded verification. 17 MCP tools, 10 pipeline steps, 877 tests. 10 packages, TypeScript/Node.

> /plugin marketplace add cdeust/prd-spec-generator
> /plugin install prd-spec-generator

Requires Node.js 20.x or 22.x. The bundled MCP server is self-contained; better-sqlite3 is an optional native dependency that degrades gracefully to in-memory mode when absent. Read more →

Visualization · v2.6.3

cortex-viz

Read-only companion to Cortex. Six reading angles over the memory store: Graph, an anatomical 3D brain view, Trace, Knowledge, Wiki, Board. Reads PostgreSQL read-only; never writes.

> /plugin marketplace add cdeust/Cortex
> /plugin install cortex-viz@cortex-plugins

Ships from the same marketplace as Cortex — no separate marketplace add. Read more →

Context budget · v1.4.3

session-optimizer

A visible, enforced context budget for long Claude Code sessions: a two-line status bar tied to per-model checkpoint thresholds, plus a Stop hook that performs the checkpoint automatically.

No plugin-marketplace install command is published for this repo. See cdeust/session-optimizer for manual setup instructions.

Generate your first PRD.

Once prd-spec-generator is installed, describe a feature in plain language.

1. Start the pipeline

> /generate-prd build a user authentication system with OAuth2, MFA, and session management

The reducer classifies intent, runs codebase discovery (deeper with automatised-pipeline installed), and asks clarification questions until you confirm the scope is right.

2. The pipeline runs 10 steps

Intent classification → codebase discovery → clarification → requirements → architecture → budget allocation → section generation (Cortex recall → draft → validate → retry up to 3x) → JIRA ticket synthesis → file export → multi-judge self-check.

3. Nine files are written

FileContents
01-prd.mdProduct requirements document
02-data-model.mdData model
03-api-spec.mdAPI specification
04-security.mdSecurity & performance requirements
05-testing.mdTesting strategy & acceptance criteria
06-deployment.mdDeployment plan, timeline, risks
07-jira-tickets.mdSynthesized JIRA tickets
08-source-code.mdSource code
09-test-code.mdTest code

Plus a 00-run-notes.md naming any skipped section and why. Every numeric claim in the output traces to a citation, a benchmark, or an explicit source: provisional heuristic admission.

What gets installed.

Verified counts per plugin, from each release tree.

PluginVersionShips
Cortex4.14.350 memory MCP tools (53 with upstream integrations), 9 lifecycle hooks, 36 cited neuroscience mechanisms, a 97-paper bibliography, 5,000+ tests
zetetic-team-subagents2.29.0119 reasoning agents (97 genius + 22 specialists), 64 skills, 19 lifecycle hooks, 288 tests
automatised-pipeline0.7.024 MCP tools, 10 languages, 434 tests, 45,000+ lines of Rust
prd-spec-generator0.6.017 MCP tools, 10 pipeline steps, 877 tests, 9 output files per run
cortex-viz2.6.3Six read-only reading angles over Cortex's store (Graph, 3D brain, Trace, Knowledge, Wiki, Board)
session-optimizer1.4.3Two-line status bar, Stop-hook auto-checkpoint against per-model context budgets

All are MIT-licensed and free. Figures are sourced to each plugin's own release tree (README badges, .claude-plugin/plugin.json version fields, and test-suite output), re-verified 2026-07-17.

Requirements.

Two of the four plugins need a toolchain on PATH. Two need nothing beyond Claude Code.

PluginPrerequisite
CortexNone — runs on the built-in SQLite backend by default. PostgreSQL 15+ with pgvector is opt-in for larger corpora.
zetetic-team-subagentsNone. On Windows, hooks additionally need Git Bash and a working Python 3 on PATH.
automatised-pipelineRust 1.94+ (rustup install stable) and CMake — the release binary builds on first launch, cached after.
prd-spec-generatorNode.js 20.x or 22.x. better-sqlite3 is an optional native dependency; the pipeline falls back to in-memory mode without it.

Troubleshooting.

Plugin not found

  • Re-run the marketplace add for that plugin, then /plugin install <name>
  • Restart Claude Code after any install
  • Update Claude Code: claude update

automatised-pipeline binary missing

  • Confirm rustc --version reports 1.94+
  • Build manually: cargo build --release inside the plugin's install path
  • CMake must be on PATH (LadybugDB's C++ core builds from source on first run)

prd-spec-generator MCP tools not registering

  • Confirm node --version reports 20.x or 22.x
  • Restart Claude Code — the 17 tools register on first stdio handshake
  • better-sqlite3 failing to build is non-fatal: the evidence repository degrades to in-memory mode

Cortex PostgreSQL connection

  • Verify with python3 -m mcp_server.doctor — 7 checks in two seconds
  • On the default SQLite backend, the PostgreSQL checks report “not set” and can be ignored
  • Re-run /cortex-setup-project to retry pgvector installation and database creation

Still stuck? Contact us or open an issue on the relevant plugin's GitHub repository.

Free & open source

All four plugins are MIT licensed. Install one, or install all four — each works standalone, all interoperate.

Part of the engagement journey · Exhibit 02

Where this setup fits in an engagement

This is the activation itself — workspace setup, permissions, MCP wiring, and team onboarding for the four plugins above, done so your team can run them without us in the room.

Stage Exhibit 02 · Claude Code activation