Sync ctx 9ecbf5e

GitHub commit: 9ecbf5e8bf558dc7a235251c1b12936f0857017b

README.md

@@ -18,8 +18,8 @@ tags:
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Python 3.11+](https://img.shields.io/badge/Python-3.11+-green.svg)](https://python.org)
 [![PyPI](https://img.shields.io/pypi/v/claude-ctx.svg)](https://pypi.org/project/claude-ctx/)
-[![Tests](https://img.shields.io/badge/Tests-4286_collected-brightgreen.svg)](https://github.com/stevesolun/ctx/actions/workflows/test.yml)
-[![Graph](https://img.shields.io/badge/Graph-79%2C958_nodes_/_1.8M_edges-red.svg)](https://stevesolun.github.io/ctx/knowledge-graph/)
+[![Tests](https://img.shields.io/badge/Tests-4287_collected-brightgreen.svg)](https://github.com/stevesolun/ctx/actions/workflows/test.yml)
+[![Graph](https://img.shields.io/badge/Graph-79%2C958_nodes_/_1%2C778%2C069_edges-red.svg)](https://stevesolun.github.io/ctx/knowledge-graph/)
 [![Skills](https://img.shields.io/badge/Skills-68%2C494-blue.svg)](https://stevesolun.github.io/ctx/catalog/?type=skill)
 [![Agents](https://img.shields.io/badge/Agents-467-purple.svg)](https://stevesolun.github.io/ctx/catalog/?type=agent)
 [![MCPs](https://img.shields.io/badge/MCPs-10%2C790-pink.svg)](https://stevesolun.github.io/ctx/catalog/?type=mcp-server)
@@ -37,13 +37,13 @@ Current shipped snapshot:
 
 - **68,494 skill entity pages**, with **67,024** hydrated installable `SKILL.md` bodies.
 - **467 agents**, **10,790 MCP servers**, and **207 harnesses**.
-- **2.6M graph edges** across semantic similarity, tags, slug tokens, source overlap, direct links, quality, usage, type affinity, and graph structure.
+- **1,778,069 graph edges** across semantic similarity, tags, slug tokens, source overlap, direct links, quality, usage, type affinity, and graph structure.
 - **28,612 long skill bodies** converted through the micro-skill gate instead of shipping raw long prompts.
 - Entity updates for skills, agents, MCPs, and harnesses print benefits/risks and skip replacement unless you explicitly approve the update.
 
 ## Why it exists
 
-- **Discovery** — with 91K+ skill pages, 460+ agents, 10K+ MCP servers, and 207 harnesses, you can't possibly know which exist or which apply to your current work.
+- **Discovery** — with 68,494 skill pages, 467 agents, 10,790 MCP servers, and 207 harnesses, you can't possibly know which exist or which apply to your current work.
 - **Context budget** — loading everything wastes tokens and degrades quality. You need the right 10–15 per session.
 - **Skill rot** — skills you installed months ago and never used are cluttering context. Stale ones should be flagged automatically.
 

docs/index.md

@@ -55,8 +55,7 @@ memory that gets smarter every session.
 Claude Code skills, agents, MCP servers, and model harness profiles are
 powerful, but at scale they become unmanageable:
 
-- **Discovery problem** — with 91K+ skill pages, 460+ agents, 10,000+
-  MCP servers, and 207 harnesses, how do you know which
+- **Discovery problem** — with 68,494 skill pages, 467 agents, 10,790 MCP servers, and 207 harnesses, how do you know which
   ones exist and which are relevant to your current project?
 - **Context budget** — loading every installable entity wastes tokens and
   degrades quality. You need exactly the right skills, agents, and MCP
@@ -202,13 +201,13 @@ ones are flagged. New ones self-ingest.
     ---
 
     **v1.0.19** — MIT, CI-matrixed (Ubuntu 3.12 plus Windows/macOS 3.11/3.12),
-    4,286 tests collected. Ships console scripts including `ctx-init`,
+    4,287 tests collected. Ships console scripts including `ctx-init`,
     `ctx-monitor` (local dashboard with graph + wiki + load/unload for
     skills, agents, and MCP servers, plus Harness Setup for user-owned LLMs),
     `ctx-incremental-attach`, `ctx-incremental-shadow`, `ctx-dedup-check`
     (pre-ship near-duplicate gate), and
     `ctx-tag-backfill` (entity hygiene), plus a fast runtime graph artifact
-    and the full ~439 MiB wiki tarball with **79,958 nodes / 1,778,069 edges / 52 Louvain communities**.
+    and the full ~314 MiB wiki tarball with **79,958 nodes / 1,778,069 edges / 52 Louvain communities**.
 
     [:octicons-arrow-right-24: CHANGELOG](https://github.com/stevesolun/ctx/blob/main/CHANGELOG.md) ·
     [Repository](https://github.com/stevesolun/ctx)

docs/skill-router/index.md

@@ -8,8 +8,7 @@ skills/agents/MCP recommendation layer can be used by that host.
 ## Problem
 
 Every loaded skill, agent, and MCP server costs tokens, attention, and tool
-surface area. Most sessions need a small top-scored bundle from the 91K+ skills,
-460+ agents, and 10K+ MCP servers in the shipped graph, not the whole inventory.
+surface area. Most sessions need a small top-scored bundle from the 68,494 skills, 467 agents, and 10,790 MCP servers in the shipped graph, not the whole inventory.
 Loading too much:
 
 - wastes context on irrelevant instructions,