code-scout

code-scout is a skill for Claude Code, Codex from di-sukharev/code-scout-skill. It costs 135 tokens per session (2,454 once invoked), scanned A, original, MIT.

A read-only repository-mapping helper for non-trivial coding tasks. It gathers evidence about likely code owners, connections between components, tests, and repository rules before implementation begins.

In plain words
What is it for?
Use it before implementing, debugging, reviewing, or planning work that spans files, modules, layers, interfaces, or tests.
Why use it?
It reduces the time spent searching an unfamiliar codebase and helps prevent changes in the wrong files or missed tests.

Skill for Claude CodeCodex

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 skills/di-sukharev/code-scout-skill/code-scout
Any agent
npx skills add di-sukharev/code-scout-skill --skill code-scout
Clone the repo
git clone --depth 1 https://github.com/di-sukharev/code-scout-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for code-scout

README.md
[![agentmods](https://agentmods.dev/badge/skills/di-sukharev/code-scout-skill/code-scout.svg)](https://agentmods.dev/skills/di-sukharev/code-scout-skill/code-scout)
Your own site
<a href="https://agentmods.dev/skills/di-sukharev/code-scout-skill/code-scout"><img src="https://agentmods.dev/badge/skills/di-sukharev/code-scout-skill/code-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,454 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 $0.00135 $0.02454
Opus 5 $0.00068 $0.01227
Sonnet 5 $0.00027 $0.00491
Haiku 4.5 $0.00014 $0.00245

Measured 3d ago against content hash 2e7a4410df78, 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/repository_fingerprint.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/code-scout/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Scout

Purpose

Run one bounded discovery pass before the primary agent designs or edits a non-trivial code change. Keep repository-search noise out of the primary conversation by returning a small, verifiable evidence map instead of a search transcript.

Keep ownership with the primary agent. The scout identifies likely owners, couplings, tests, flows, and constraints; it does not choose the fix, edit files, or replace local verification of its result.

Apply the Eligibility Gate

Run the scout only when all of these are true:

  • The task requires repository discovery.
  • The work is non-trivial or crosses files, modules, layers, contracts, or tests.
  • The owning files, entry points, important symbols, or closest tests are not already sufficiently explicit.
  • A fresh sub-agent can be started without inheriting the parent conversation.

Skip the scout when any of these are true:

  • The task is documentation-only.
  • The requested edit already names the exact file and symbol and nearby inspection is enough.
  • The change is an obvious local copy, style, or similarly bounded edit.
  • The user asks only for an answer that needs no code search.
  • The user forbids delegation.
  • This skill already produced a verified map for the same stable task scope and repository state.
  • The repository or fresh-agent capability is unavailable.

An explicit $code-scout invocation overrides the ordinary cost/benefit heuristic, but not a user prohibition, missing capability, or safety constraint. Run exactly one scout at a time. Do not turn discovery into a review loop.

Prepare the Scout

  1. Normalize the task into one implementation goal and one observable primary signal.
  2. Resolve the absolute Git repository root.
  3. Identify only the repository guidance the scout needs to read, such as AGENTS.md, a root README.md, CONTRIBUTING.md, and directly relevant architecture documents. Pass filenames and task constraints, not summaries of the expected answer.
  4. Resolve scripts/repository_fingerprint.py relative to this SKILL.md.
  5. Run the fingerprint script against the repository before spawning:

Read the full file on GitHub · 246 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 246 lines · 135 tokens per session scan A 2e7a4410df78

Subscribe to this mod's changes

code-scout is a skill published in the GitHub repository di-sukharev/code-scout-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 2,454 once invoked, about $0.0007 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens