contextd-detect

A command that checks whether the current project has a valid contextd configuration and connected workspace knowledge.

In plain words
What is it for?
Use it to diagnose contextd setup problems, validate the project and workspace configuration, and locate the knowledge map and related files.
Why use it?
It quickly identifies missing files, invalid paths, and unavailable workspaces when contextd cannot find the project’s settings.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/philngt/contextd/contextd-detect
Clone the repo
git clone --depth 1 https://github.com/philngt/contextd

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,574 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01574
Opus 5 $0.00000 $0.00787
Sonnet 5 $0.00000 $0.00315
Haiku 4.5 $0.00000 $0.00157

Measured yesterday against content hash 8b8969a2e1a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contextd-detect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/contextd-detect.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/contextd-detect — Detect contextd Config

Skill này chạy tự động khi /use-contextd không resolve được config của codebase, hoặc gọi trực tiếp để kiểm tra trạng thái tích hợp contextd của dự án hiện tại.

Knowledge giờ tổ chức theo workspace. Mọi path scan/validate đều scope trong {knowledge_root}/workspaces/{workspace}/ — KHÔNG cross-workspace.


Bước 1 — Kiểm tra local config

Tìm file .contextd/config.json trong thư mục gốc của dự án (codebase) hiện tại.

Nếu file tồn tại → Validate config

Đọc file và kiểm tra từng field:

Kiểm tra Hành động nếu lỗi
project có giá trị Báo lỗi: thiếu tên project
workspace có giá trị Báo lỗi: thiếu workspace; gợi ý chạy /contextd-setup
knowledge_root resolve được (hoặc null → fallback ~/.contextd/config.json) Nếu không resolve → báo path sai
{knowledge_root}/workspaces/{workspace}/ tồn tại Nếu không → báo workspace không tồn tại; liệt kê workspaces có sẵn
knowledge_map resolve trong {knowledge_root}/workspaces/{workspace}/ Nếu không tồn tại → báo file không tìm thấy
domain có trong {knowledge_root}/workspaces/{workspace}/domains/ Nếu không tồn tại → cảnh báo
patterns đều có trong {knowledge_root}/workspaces/{workspace}/patterns-index.md Liệt kê pattern không nhận ra
contracts đều có trong {knowledge_root}/workspaces/{workspace}/platform/contracts/ Liệt kê contract không tìm thấy
services đều resolve trong {knowledge_root}/workspaces/{workspace}/projects/{project}/services/ Liệt kê service doc không tìm thấy

Hiển thị kết quả:

✅ contextd config hợp lệ
   Workspace: {workspace}
   Project  : {project}
   Knowledge root: {resolved_path}
   Domain   : {domain}
   Patterns : {danh sách}
   Contracts: {danh sách}
   Services : {danh sách}

Hoặc nếu có lỗi:

⚠️  contextd config có vấn đề
   [ERROR] workspace 'foo' không tồn tại trong {knowledge_root}/workspaces/
           Có sẵn: example-surgery, company-b, ...
   [ERROR] knowledge_map không tìm thấy: workspaces/{ws}/projects/xyz/knowledge-map.md
   [WARN]  domain 'surgery' không có trong workspaces/{ws}/domains/
   → Chạy /contextd-setup để sửa

Read the full file on GitHub · 145 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 145 lines · 0 tokens per session scan A 8b8969a2e1a7

Subscribe to this mod's changes

contextd-detect is a command published in the GitHub repository philngt/contextd (29 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,574 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.