Borrowing it
Nothing to install: this file belongs to philngt/contextd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/philngt/contextd/main/.claude/commands/contextd-explain.mdgit clone --depth 1 https://github.com/philngt/contextdWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/philngt/contextd/contextd-explain)<a href="https://agentmods.dev/commands/philngt/contextd/contextd-explain"><img src="https://agentmods.dev/badge/commands/philngt/contextd/contextd-explain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/philngt/contextd/contextd-explain"><img src="https://agentmods.dev/badge/commands/philngt/contextd/contextd-explain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01281 |
| Opus 5.5 | $0.00000 | $0.00512 |
| Sonnet 5.5 | $0.00000 | $0.00256 |
| Haiku 4.5 | $0.00000 | $0.00128 |
Grade A, and why
contextd-explain 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 1mo ago.
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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/contextd-explain — Explain Wiki Concepts
Giải thích một khái niệm wiki (pattern, contract, ADR, runbook, term) bằng plain language. Mục tiêu: non-tech reader hiểu được trong 2 phút.
Output in trực tiếp ra console — KHÔNG ghi file (đây là tra cứu nhanh, không phải artifact). Khác
/business-view(sinh document persistent cho audience cụ thể) —/contextd-explainlà on-the-fly explainer.
Input
| Arg | Required | Notes |
|---|---|---|
{topic} |
required | Tên pattern/contract/ADR/term, hoặc đường dẫn file. Vd: mqtt-topic-contract, circuit-breaker, ADR-0007, hoặc platform/patterns/event-sourcing.md. |
--depth {level} |
optional | tldr (1 paragraph) / short (default — 1 page) / deep (1 page + 3 examples + when-NOT-to-use). |
--lang {vi|en} |
optional | Language. Default: workspace language. |
Bước 0 — Workspace check
Resolve workspace. Set {ws}. STOP nếu chưa init.
Bước 1 — Locate topic
- Nếu
{topic}là path → đọc trực tiếp. - Nếu là tên → search theo thứ tự ưu tiên:
{ws}/patterns-index.mdlookup table{ws}/platform/patterns/{topic}.md,{ws}/platform/patterns/{topic}-*.md{ws}/platform/contracts/{topic}.md{ws}/decisions/*{topic}*.md,{ws}/projects/*/decisions/*{topic}*.md{ws}/runbooks/{topic}.md{ws}/domains/{topic}/*.md- Glob fallback: any
*.mdchứa H1 match (case-insensitive substring)
- Multiple match → AskUserQuestion liệt kê paths cho user chọn.
- Zero match → STOP với suggestion: "Topic không tìm thấy trong
{ws}. Có thể đây là engine/pack concept — check{knowledge_root}/agents/,{knowledge_root}/packs/*/, hoặc tạo doc mới."
Bước 2 — Read source + cross-references
- Đọc file source.
- Extract: H1 title, intro paragraph, all H2 headings, code fence count, link list.
- Đọc tối đa 3 cross-reference files (link xuất hiện đầu trong source) để có context broader.
- Identify category:
pattern/contract/decision/runbook/domain/term.
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.
- 1mo ago First seen · 133 lines · 0 tokens per session scan A 4d7a341a97f6
contextd-explain is a command published in the GitHub repository philngt/contextd (29 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,281 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.
Other commands, from other repositories
demo-consume-context
Worked example: discover, load, and tag an approved context package, then write a reverse-index addendum. Proves the produce/consume/tag loop end-to-end. Not for real feature work.
cat:learn
Analyze and learn from mistakes.
new-migration
Scaffold a new database migration file pair (up + down) with auto-detection of migration tool and numbering.
gaai-audit
Show workspace audit log with filters and optional JSON export.
start-0-8
A Japanese-language command that displays the current project setup progress.
cold-start
Bootstrap the ai/guide maps and diagrams (the cold-start pass). Drafts everything as [inferred] for a human to audit.