yet-another-agent-harness: Skill for Claude Code

.claude/skills/scout/SKILL.md

scout is a skill for Claude Code from dirien/yet-another-agent-harness. It costs 61 tokens per session (1,214 once invoked), scanned A, original, MIT.

A code-review helper that looks at the full contents of files changed in a Git project and identifies three high-impact, low-risk improvement opportunities. Git is a tool for tracking changes to code.

In plain words
What is it for?
Use it before a pull request, during code review, or after finishing a feature to find maintainability improvements in changed files.
Why use it?
It points out worthwhile pre-existing cleanup in the files you are already touching, so small quality improvements are less likely to be overlooked during reviews or feature work.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dirien/yet-another-agent-harness's own configuration. It tells Claude Code how to work on yet-another-agent-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yet-another-agent-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dirien/yet-another-agent-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dirien/yet-another-agent-harness/main/.claude/skills/scout/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dirien/yet-another-agent-harness

Made for: Claude Code.

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 scout

README.md
[![agentmods](https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/scout.svg)](https://agentmods.dev/skills/dirien/yet-another-agent-harness/scout)
Your own site
<a href="https://agentmods.dev/skills/dirien/yet-another-agent-harness/scout"><img src="https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,214 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00061 $0.01214
Opus 5 $0.00030 $0.00607
Sonnet 5 $0.00012 $0.00243
Haiku 4.5 $0.00006 $0.00121

Measured 7d ago against content hash a66c7575ef62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 7d 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.

.claude/skills/scout/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout Rule

"Leave the code better than you found it."

Identify the top 3 highest-impact, lowest-risk improvement opportunities in files touched by a diff. Reads entire file content, not just changed lines. Focuses on pre-existing code quality — things the next developer will thank you for fixing.

Prerequisite check

git --version 2>/dev/null && git rev-parse --is-inside-work-tree 2>/dev/null

If git is not installed or the working directory is not a git repository, stop and report the issue. Do not proceed.

Detect changed files

Determine which files to analyze based on input.

Default — working tree vs base branch

# Detect base branch
BASE_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null \
  | sed 's@^refs/remotes/origin/@@' || echo "main")

# Combine committed + uncommitted + staged changes vs base
{ git diff --name-only ${BASE_BRANCH}...HEAD 2>/dev/null; \
  git diff --name-only; \
  git diff --name-only --cached; } | sort -u

If all sources return empty, report that there are no changed files to analyze.

Specific branch

If the user specifies a target branch to analyze, detect the base branch the same way as the default mode, then diff:

BASE_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null \
  | sed 's@^refs/remotes/origin/@@' || echo "main")
git diff --name-only ${BASE_BRANCH}...${BRANCH}

Specific files

If given an explicit list of file paths rather than a branch name, use those directly without running git diff.

Scope

Read the full content of each changed file, not just diff hunks. Look for improvements in the entire file.

Do not:

  • Find bugs in PR changes (that's a code reviewer's job)
  • Suggest architectural redesigns
  • Flag style preferences not established in the codebase
  • Propose changes requiring new dependencies

Categories

Read the full file on GitHub · 164 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. 7d ago First seen · 164 lines · 61 tokens per session scan A a66c7575ef62

Subscribe to this mod's changes

scout is a skill published in the GitHub repository dirien/yet-another-agent-harness (20 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 1,214 once invoked, about $0.0003 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 2026-08-30.