principles

principles is a skill for Claude Code, Codex from melodic-software/claude-code-plugins. It costs 159 tokens per session (1,215 once invoked), scanned A, original, MIT.

A reference guide to mutation testing, a method that inserts small faults into code to see whether tests catch them. It explains the method, its measurements, its theory, and the tools used in different programming ecosystems.

In plain words
What is it for?
Use it to answer questions about mutants, mutation scores, surviving faults, equivalent changes, tooling, and when to use mutation testing.
Why use it?
It helps developers interpret mutation results instead of treating a test score or code coverage number as the whole story.

Skill for Claude CodeCodex

Part of the mutation-testing plugin — 1 skill shipped together

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/melodic-software/claude-code-plugins/principles
Any agent
npx skills add melodic-software/claude-code-plugins --skill principles
Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code, Codex.

Or install mutation-testing, the plugin that ships this one along with the rest of its 1 skill.

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 principles

README.md
[![agentmods](https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/principles.svg)](https://agentmods.dev/skills/melodic-software/claude-code-plugins/principles)
Your own site
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/principles"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/principles.svg" alt="Measured on agentmods" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,215 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 $0.00159 $0.01215
Opus 5 $0.00079 $0.00607
Sonnet 5 $0.00032 $0.00243
Haiku 4.5 $0.00016 $0.00121

Measured yesterday against content hash e4e2a7d1b6e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

principles 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/mutation-testing/skills/principles/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mutation Testing Knowledge Base

Distilled from the primary sources, the foundational papers, the industrial-scale reports, and the tool documentation that defines the vocabulary everyone else borrows. Reference files in reference/ are source-attributed; this file routes and answers the common questions without a load.

Routing Table

Query about... Load
Mutant states (killed/survived/no-coverage/timeout), operator catalogs, what a mutation actually is operators-and-states.md
Mutation score, covered-code score, test strength, MSI, the oracle gap, what to report metrics.md
Cost, diff-scoping, arid nodes, productive vs unproductive mutants, suppression, why not to gate scaling-and-suppression.md
Which tool for which ecosystem, what each supports, what to do when no tool exists tooling.md
Equivalent mutants, coupling effect, competent programmer hypothesis, the theory theory.md

Quick decision guide (no load required)

"What is mutation testing?". Coverage tells you a line executed. It cannot tell you the line was checked. Mutation testing introduces a small deliberate fault (a mutant), re-runs the tests, and observes: tests fail → the mutant is killed, something genuinely asserted on that behavior; tests pass → the mutant survived, that line ran and nothing noticed it was wrong. The mutation is always reverted; the source is unchanged at the end.

"Is it just better coverage?". It answers a different question. Coverage measures execution; mutation testing measures fault detection. PIT states it directly: line coverage "does not check that your tests are actually able to detect faults." A file at 100% coverage and 40% mutation score has tests that run the code and assert almost nothing about it.

"Which number do I look at?". The covered-code one, always. Plain mutation score mixes two unrelated problems: "my tests are weak" and "I have no tests here." The covered-code variant (PIT calls it test strength, Infection calls it Covered Code MSI) isolates the first. A wide gap between the two means the coverage you have is thin, not that the tests are bad.

Read the full file on GitHub · 78 lines

Files

What ships with it

6 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. yesterday First seen · 78 lines · 159 tokens per session scan A e4e2a7d1b6e3

Subscribe to this mod's changes

principles is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 1,215 once invoked, about $0.0008 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.

Related

Other skills, from other repositories