2026-06-16站内改写3 min readUpdated: 2026-06-16

Show HN: Ctx, save tokens by loading only the relevant tools

Ctx is a context management tool for Claude Code and custom LLMs that recommends a small, top-scored bundle of skills, agents, and MCP servers for the current task by analyzing a 102,928-node graph, saving tokens and improving quality.

SourceHacker News AIAuthor: stevesolun

Notifications You must be signed in to change notification settings

Fork 60

Star 499

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

803 Commits

.githooks

.github

docs

graph

hooks

imported-skills

internal/playbooks

scripts

skills

src

.dedup-allowlist.txt

.gitattributes

.gitignore

AGENTS.md

CHANGELOG.md

CONTRIBUTING.md

LICENSE

MANIFEST.in

README.md

install.ps1

install.sh

mkdocs.yml

pyproject.toml

requirements-docs.txt

Repository files navigation

ctx watches what you are building, walks a 102,928-node graph, and recommends a small, top-scored bundle of skills, agents, and MCP servers for the current task. If you use your own local/API model instead of Claude Code, ctx has a separate harness setup flow: tell it the model and goal, review the recommended harness, then install with dry-run/update/uninstall controls.

Current shipped snapshot:

91,464 skill entity pages, with 89,465 hydrated installable SKILL.md bodies.

467 agents, 10,790 MCP servers, and 207 harnesses.

2.9M 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.

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.

Install

pip install claude-ctx ctx-init # terminal wizard: hooks, graph, model, harness goal ctx-init --graph --hooks --model-mode skip # fast runtime graph + Claude Code hooks ctx-init --graph --graph-install-mode full # expand the full markdown wiki locally ctx-init --wizard # force the same wizard from scripts/tests ctx-init --model-mode custom --model openai/gpt-5.5 --goal "build a CAD agent"

Optional extras: pip install "claude-ctx[embeddings]" for the semantic backend, pip install "claude-ctx[harness]" for local/API model harness runs, pip install "claude-ctx[dev]" for the test toolchain.

Pre-built knowledge graph

Graph-backed recommendations need the pre-built graph. By default, ctx-init --graph installs the fast runtime artifact: graph/wiki-graph-runtime.tar.gz in source checkouts, or the matching GitHub release asset from pip installs. It contains graphify-out/*, the shipped skill index needed for recommendations, and the 207 harness pages needed by ctx-harness-install:

ctx-init --graph

The full LLM-wiki artifact remains available for local browsing, Obsidian, and expanded markdown pages:

ctx-init --graph --graph-install-mode full

The full wiki-graph.tar.gz includes the shipped skill index, 91,464 skill entity pages under entities/skills/, 89,465 hydrated installable SKILL.md files under converted/, and 207 harness pages under entities/harnesses/.

Windows: PowerShell's built-in tar.exe does not support --force-local; use tar -xzf graph\wiki-graph.tar.gz -C "$env:USERPROFILE\.claude\skill-wiki". In Git Bash or MSYS, use --force-local only when your -C target is a drive-letter path such as C:/Users/....

Use

After ctx-init --hooks or the wizard hook step, ctx observes Claude Code's PostToolUse and Stop events. Typical flow:

ctx-scan-repo --repo . # scan current repo and stack signals ctx-scan-repo --repo . --recommend # include skill/agent/MCP recommendations ctx-agent-add --agent-path ./code-reviewer.md --name code-reviewer ctx-harness-add --repo https://github.com/earthtojake/text-to-cad --tag cad ctx-harness-install text-to-cad --dry-run # inspect before cloning/running anything ctx-harness-install text-to-cad # install after reviewing the plan ctx-harness-install text-to-cad --update --dry-run ctx-harness-install text-to-cad --uninstall --dry-run ctx-skill-quality list # four-signal quality score for every skill ctx-skill-quality explain python-patterns # drill into a single skill ctx-skill-health dashboard # structural health + drift detection ctx-toolbox run --event pre-commit # run a council on the current diff ctx-monitor serve # local dashboard: http://127.0.0.1:8765/

Before pushing, run the local PR gate:

python scripts/ci_preflight.py --profile pr

It uses the same changed-file classifier as GitHub Actions, then runs the matching local checks: stats, ruff, mypy, pip check, unit coverage, canaries, package build, twine, docs, graph validation, browser, and similarity gates as needed. Use --profile full before release work to force the source/package gates even for docs-only or graph-only changes.

The ctx-monitor dashboard shows currently loaded skills, agents, MCP servers, installed harness records, and generic-harness validation/escalation state. It provides load/unload buttons where ctx owns the live action, a graph view (/graph?slug=...), the LLM-wiki entity browser (/wiki/), a filterable skills grid, a session timeline, audit/runtime log views, and a live SSE event stream. Installed harness records appear in /loaded; harness pages appear in /wiki and /graph. Harness install/update/uninstall actions stay in ctx-harness-install.

When ctx-skill-add, ctx-agent-add, ctx-mcp-add, or ctx-harness-add finds an existing entity, ctx prints a benefits/risks update review and skips replacement by default. Re-run with --update-existing to apply the catalog or local asset update after review.

Step-by-step entity onboarding: https://stevesolun.github.io/ctx/entity-onboarding/

Full docs, architecture, and every module: https://stevesolun.github.io/ctx/

License

MIT — see LICENSE.

About

Skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,928-node LLM-wiki graph, 91,464 skills, 467 agents, 10,790 MCPs, 207 harnesses, and capped execution recommendations.

stevesolun.github.io/ctx/

Topics

automation

real-time

wiki

skills

mcp

knowledge-graph

developer-tools

recommendation-engine

obsidian

agents

harness

ai-agents

claude

skill-management

llm

anthropic

context-management

claude-code

micro-skills

llm-wiki

Resources

Readme

License

MIT license

Contributing

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

499 stars

Watchers

4 watching

Forks

60 forks

Report repository

Releases 26

v1.0.11

Latest

May 28, 2026

+ 25 releases

Packages 0

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

Python 80.6%

HTML 18.7%

Other 0.7%