code-scout

A read-only code-search assistant that finds files, functions, entry points, and existing coding patterns related to a task.

In plain words
What is it for?
Use it to locate relevant code, record repository conventions, identify likely entry points, and note missing context before implementation.
Why use it?
It reduces the time spent searching an unfamiliar codebase and highlights areas that should or should not be changed.

Agent

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 agents/hiepdnh/agentic-development-lifecycle/code-scout
Clone the repo
git clone --depth 1 https://github.com/hiepdnh/Agentic-Development-Lifecycle
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 635 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 $0.00635
Opus 5 $0.00000 $0.00318
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00064

Measured 2d ago against content hash 4cf0b0c89a39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-scout 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 2d 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.

agents/code-scout.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: code-scout

Type: Subagent (spawned by dev-analyze)
Scope: Read-only. Tìm code liên quan đến task. Không sửa bất cứ gì.
Recommended model: haiku — file search and grep only, no synthesis.


Input

TASK SUMMARY:
[Output từ task-reader — task_id, type, business_goal, affected_areas]

TECH STACK:
[language, framework, folder structure nếu biết]

Nhiệm vụ

  1. Dùng Glob và Grep để tìm files/functions liên quan đến affected_areas
  2. Đọc structure của các files tìm được (không đọc full content nếu file > 200 lines — chỉ đọc relevant sections)
  3. Identify patterns/conventions hiện tại

Output format

{
  "relevant_files": [
    {
      "path": "src/auth/login.ts",
      "lines": "45-89",
      "reason": "Contains login logic, relevant to OTP feature",
      "read_status": "partial | full"
    }
  ],
  "entry_points": [
    "src/routes/auth.ts:23 — POST /auth/login"
  ],
  "conventions": [
    "Service layer pattern: services/ → controllers/",
    "Validation dùng Zod schemas",
    "Error handling: custom AppError class"
  ],
  "avoid_touching": [
    "src/legacy/old-auth.ts — deprecated, sẽ bị xóa"
  ],
  "missing_context": [
    "Không tìm thấy SMS service — có thể chưa có hoặc tên khác"
  ]
}

Quy tắc

  • Tối đa 20 files trong relevant_files — lọc kỹ, chỉ thực sự liên quan
  • Nếu không tìm thấy → ghi vào missing_context, không tự bịa
  • avoid_touching — chủ động flag code nguy hiểm/deprecated
  • Không sửa, không tạo file mới
  • read_status: full nếu file được đọc toàn bộ (file nhỏ, hoặc dưới ngưỡng 200 lines ở Nhiệm vụ bước 2, hoặc file trung tâm của task); partial nếu chỉ đọc một phần (file lớn, chỉ vài function/section liên quan) — khi dùng partial, lines phải phản ánh chính xác range đã đọc, không ước lượng

Error handling

Nếu không tìm thấy codebase hoặc tech stack không khớp:

{
  "error": "codebase_not_found",
  "message": "Không tìm thấy src/ directory — cần chạy từ root của project",
  "needs": ["Project root path", "Correct tech stack info"]
}

Read the full file on GitHub · 86 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. 2d ago First seen · 86 lines · 0 tokens per session scan A 4cf0b0c89a39

Subscribe to this mod's changes

code-scout is an agent published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 635 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens