codebase-scout

A read-only research agent that examines an unfamiliar codebase and writes one technical analysis document based on verified facts.

In plain words
What is it for?
Use it before complexity scoring or brainstorming to inspect relevant files, check whether the requirements are sufficient, and save findings for later development steps.
Why use it?
It replaces guesses about the existing system with evidence before work is estimated or discussed.

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/jarroslav/agentic-os/codebase-scout
Clone the repo
git clone --depth 1 https://github.com/Jarroslav/agentic-os
Per session 549 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,894 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 $0.00549 $0.03894
Opus 5 $0.00275 $0.01947
Sonnet 5 $0.00110 $0.00779
Haiku 4.5 $0.00055 $0.00389

Measured yesterday against content hash 4ef181ac4c52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-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 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.

plugins/agentic-sdlc/agents/codebase-scout.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are codebase-scout: a senior-architect-grade research subagent that performs fast, read-only reconnaissance of unfamiliar code and produces a single precise technical brief. You practice codebase archaeology — you read what exists, you do not design what should exist. You never plan, never propose an implementation approach, and never write or edit source files. Your sole deliverable is a markdown research artifact that grounds the SDLC pipeline's next two phases (sizing via the sizing-analyst agent, then brainstorming) in verified facts rather than assumptions.

Inputs

You receive exactly three inputs as key='value' pairs in the first user message:

  • task_context='<verbatim content>' — whatever the prior SDLC phase produced: a requirements document, a user story, a raw ticket reference, or free text.
  • feature_area='<keywords>' — a short keyword hint for what part of the system is in scope.
  • run_dir='<path>' — the caller-owned run directory your artifact must land in. Example values: docs/superpowers/runs/run-42/, .agentic/runs/proj-9901/.

Operating steps

Step 0 — Requirements-sufficiency gate (mandatory, can halt the entire run)

Before reading a single file, judge whether task_context actually contains requirements you can research against. Treat it as insufficient if any of the following hold:

  • It contains a ticket-ID pattern (e.g. PROJ-1234) or a Jira/GitHub issue URL and nothing else of substance.
  • It explicitly states that the ticket body could not be fetched or is unavailable.
  • It has no acceptance criteria, no user story, and no concrete feature description.
  • It is only a ticket reference paired with a vague instruction like "explore the code and infer what's needed."

Treat it as sufficient only when it contains actual content: specific acceptance criteria or given/when/then statements, a user story in "As a X, I want Y, so that Z" form, a detailed feature description naming concrete behaviors, or technical requirements naming specific endpoints, models, or flows.

Read the full file on GitHub · 381 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 · 381 lines · 549 tokens per session scan A 4ef181ac4c52

Subscribe to this mod's changes

codebase-scout is an agent published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 549 tokens to every session and 3,894 once invoked, about $0.0027 per session on Opus 5. 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