arnesto: Skill for Claude Code

.agents/skills/xp-plan-untested-code/SKILL.md

xp-plan-untested-code is a skill for Claude Code, Codex from saski/arnesto. It costs 39 tokens per session (313 once invoked), scanned A, original, Unlicense.

A test-planning guide for finding untested parts of a codebase and deciding which tests matter most.

In plain words
What is it for?
Use it to identify missing tests, prioritize high-risk behavior, and plan small tests that improve reliability.
Why use it?
It helps turn vague coverage gaps into a short, risk-based testing plan, including edge cases and error paths.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is saski/arnesto's own configuration. It tells Claude Code and Codex how to work on arnesto 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 arnesto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saski/arnesto. 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/saski/arnesto/main/.agents/skills/xp-plan-untested-code/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/saski/arnesto

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 xp-plan-untested-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/saski/arnesto/xp-plan-untested-code.svg)](https://agentmods.dev/skills/saski/arnesto/xp-plan-untested-code)
Your own site
<a href="https://agentmods.dev/skills/saski/arnesto/xp-plan-untested-code"><img src="https://agentmods.dev/badge/skills/saski/arnesto/xp-plan-untested-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 313 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 $0.00039 $0.00313
Opus 5 $0.00019 $0.00156
Sonnet 5 $0.00008 $0.00063
Haiku 4.5 $0.00004 $0.00031

Measured 3d ago against content hash f805163e8e54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

xp-plan-untested-code 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.

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/skills/xp-plan-untested-code/SKILL.md · 37 lines

What it actually says

Senior XP Developer — Plan Tests for Untested Code

Act as a Senior XP Developer with Lean thinking. Work in small batches, prefer clarity, and improve reliability by expanding meaningful test coverage.

Task

Write a concise, actionable plan to create tests that exercise all untested code.

Focus on:

  1. Identify gaps

    • Use coverage analysis to list untested functions, branches, and edge cases.
    • Classify them by risk and production impact.
  2. Prioritize

    • Address highest-risk paths first (complex logic, error handling, integrations).
    • Defer low-value or dead code, calling it out explicitly.
  3. Design tests

    • Write small, behavior-focused tests.
    • Cover edge cases, invalid inputs, and boundary conditions.
    • Avoid over-mocking; keep intent clear.
  4. Iterate

    • Add one test at a time.
    • Run tests, confirm they fail for the right reason, then implement if needed.
    • Refactor both code and tests as clarity emerges.
  5. Validate completeness

    • Re-run coverage to confirm gaps are closed.
    • Explain any cases intentionally left untested.

This plan should emphasize simplicity, flow, and evolvability while increasing confidence in production reliability.

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 · 37 lines · 39 tokens per session scan A f805163e8e54

Subscribe to this mod's changes

xp-plan-untested-code is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed today), licensed Unlicense. It adds 39 tokens to every session and 313 once invoked, about $0.0002 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 2026-09-03.