code-analyze

A command that examines an existing codebase and sends a summary into an evidence pipeline for analysis. The results can suggest additions to shared platform patterns, service definitions, and Architecture Decision Record drafts; an ADR is a written record of an important technical choice.

In plain words
What is it for?
Use it to analyze a repository or prepared bundle, choose the files to include, label the analysis, and generate proposed architecture and project decisions.
Why use it?
It turns the structure and configuration of an existing repository into organized evidence, reducing the need to inspect every relevant file manually before planning changes.

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/code-analyze
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 6,159 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 $0.06159
Opus 5 $0.00000 $0.03080
Sonnet 5 $0.00000 $0.01232
Haiku 4.5 $0.00000 $0.00616

Measured yesterday against content hash 35b503d235ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-analyze 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/code-analyze.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Analyze

Phân tích codebase có sẵn → snapshot metadata → đẩy vào evidence pipeline để đề xuất bổ sung platform patterns, platform contracts, project services, và decision (ADR) drafts cho workspace active.

Entry point user-friendly. Dưới capô gọi logic của /evidence-ingest --source code rồi /evidence-analyze (CORE-CODE prompts). Reference: code-snapshot-conventions.md, code-analysis-prompts.md, evidence-lifecycle.md.


Input

Arg Required Notes
--ref optional Repo path. Default: <cwd> của codebase (parent của .contextd/config.json). Mutually exclusive với --bundle.
--scope optional (Single-repo) Comma-separated paths/globs included. Default heuristic: src/**, pom.xml/package.json/build.gradle/Cargo.toml/go.mod, application.*, Dockerfile, *.yaml config.
--bundle optional Bundle mode: đường dẫn tới thư mục staging chứa bundle.yaml. Nếu pass --bundle, ignore --ref--scope. Mutually exclusive với --ref.
--label optional Mô tả ngắn (≤ 30 ký tự). Single-repo: default bootstrap-{project} hoặc refresh-{project}-{date}. Bundle: override bundle.yaml#label.
--skip-analyze optional Chỉ ingest, không tự chạy /evidence-analyze. Dùng khi muốn review snapshot trước.
--allow-configs optional Cho phép đọc file config vào Section 3. Mặc định tất cả config bị block. Khi set, sẽ AskUserQuestion từng nhóm file trước khi đọc. Hard blocklist (prod/secret/key files) vẫn áp dụng.
--with-drafts optional Chạy thêm ON-DEMAND drafts sau CORE: c05/c06/c07 (variant=code) hoặc a05/a06/a07 (variant=agentic-engine).
--variant optional code (default, runtime codebase) | agentic-engine (markdown-heavy: slash commands, sub-agents, prompt templates). Vắng mặt → auto-detect (xem Bước 1.4). Single-repo only — bundle dùng per-repo variant trong bundle.yaml.

Read the full file on GitHub · 392 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 · 392 lines · 0 tokens per session scan A 35b503d235ab

Subscribe to this mod's changes

code-analyze 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 6,159 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.