Peaky8linders

46 mods across 3 repositories, 24 stars between them.

cortex

01

Peaky8linders/claude-cortex

Plugin Claude Code

Live knowledge graph, context intelligence, session dashboard, and optimization engine for Claude Code.

11 2mo ago A tokens not measured original MIT

cortex-advisor

02

Peaky8linders/claude-cortex

Agent Claude Code

Analyzes the session knowledge graph for optimization opportunities. Spawned when quality score drops below 60, after compaction events, or when user asks for deep context analysis. Runs in isolated context to avoid consuming main window tokens.

11 2mo ago A 50 tokens original MIT

graph-maintainer

03

Peaky8linders/claude-cortex

Agent Claude Code

Dedicated agent for knowledge graph hygiene — consolidation, pruning, and structural optimization. Spawned for periodic maintenance tasks or when the cortex-advisor identifies cleanup opportunities. Can write to the knowledge directory only.

11 2mo ago A 43 tokens original MIT

work-evaluator

04

Peaky8linders/claude-cortex

Agent Claude Code

Generator-evaluator pattern: independent QA agent that grades Claude's actual work output. Spawned after each Ralph iteration and after each run-tasks subagent. Evaluates the diff, runs tests, checks for known antipatterns from the knowledge graph. Returns a structured score (0-100) across 5 dimensions. Tuned to be…

11 2mo ago A 83 tokens original MIT

auto-research

05

Peaky8linders/claude-cortex

Command Claude Code

Structured experiment runner — define hypothesis, metric, and variations, then run automated eval loops with brainiac tracking.

11 2mo ago A 25 tokens original MIT

cortex-status

11

Peaky8linders/claude-cortex

Command Claude Code

Show current Cortex knowledge graph health — quality score, node/edge counts, top connections.

11 2mo ago A 17 tokens original MIT

learn

14

Peaky8linders/claude-cortex

Command Claude Code

Extract session learnings and save them as knowledge graph nodes with auto-linking.

11 2mo ago A 15 tokens original MIT

ralph-start

15

Peaky8linders/claude-cortex

Command Claude Code

Start an autonomous Ralph Wiggum loop — Claude works, tries to exit, Stop hook re-feeds the prompt with Cortex quality gating.

11 2mo ago B 31 tokens original MIT

ralph-status

16

Peaky8linders/claude-cortex

Command Claude Code

Show current Ralph Wiggum loop status without modifying it — iteration count, quality score, elapsed time, commits.

11 2mo ago B 26 tokens original MIT

run-tasks

19

Peaky8linders/claude-cortex

Command Claude Code

Looping subagent runner — reads a task list and executes each in an isolated subagent with generator-evaluator pattern and dual quality gating.

11 2mo ago A 31 tokens original MIT

cortex-advisor

21

Peaky8linders/claude-cortex

Skill Claude CodeCodex

Use when context quality degrades, after compaction, when repeated file reads are detected, or when the user asks about context optimization, token usage, knowledge graph health, or session quality. Also auto-invoke when starting work on a task that touches domains with known patterns or antipatterns.

11 2mo ago A 64 tokens original MIT

cortex-dashboard

22

Peaky8linders/claude-cortex

MCP server Claude CodeCodexCursor +2

MCP server "cortex-dashboard" as configured in Peaky8linders/claude-cortex. Runs ${CLAUDE_PLUGIN_ROOT}/cortex/dist/mcp/server.js with node. Needs 1 environment variable to run.

11 2mo ago A tokens not measured original MIT

code-review-graph

23

Peaky8linders/claude-cortex

MCP server Claude CodeCodexCursor +2

Local-first knowledge graph for token-efficient code review through MCP and CLI. Runs locally from the code-review-graph Python package.

11 2mo ago A tokens not measured copy · 92% MIT

Peaky8linders/claude-cortex

Instructions file

Instructions for Peaky8linders/claude-cortex, covering claude.md, commands, brainiac (python — semantic graph engine), cortex (typescript — hook processor + mcp dashboard) and contextscore (python — analyzers + snapshot + http api).

11 2mo ago A 1,122 tokens original MIT