ai-engineering-fluency: Command for GitHub Copilot

.github/prompts/improve-mutation-score.prompt.md

improve-mutation-score is a command for GitHub Copilot from rajbos/ai-engineering-fluency. It costs 24 tokens per session (1,240 once invoked), scanned A, original, MIT.

A command that reads a Stryker mutation-testing report and recommends which surviving changes deserve new tests. Mutation testing changes code in small ways to check whether tests detect those changes.

In plain words
What is it for?
Use it in GitHub Actions after mutation testing to find gaps worth addressing and open a single issue with concrete recommendations.
Why use it?
It turns a large report into one triaged GitHub issue and keeps this review separate from modifying source or test files.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

This is rajbos/ai-engineering-fluency's own configuration. It tells GitHub Copilot how to work on ai-engineering-fluency 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 ai-engineering-fluency configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/.github/prompts/improve-mutation-score.prompt.md
Clone the repo
git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency

Made for: GitHub Copilot.

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 improve-mutation-score

README.md
[![agentmods](https://agentmods.dev/badge/commands/rajbos/ai-engineering-fluency/improve-mutation-score/github.svg)](https://agentmods.dev/commands/rajbos/ai-engineering-fluency/improve-mutation-score)
Your own site
<a href="https://agentmods.dev/commands/rajbos/ai-engineering-fluency/improve-mutation-score"><img src="https://agentmods.dev/badge/commands/rajbos/ai-engineering-fluency/improve-mutation-score/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for improve-mutation-score

Your own site · 80×15
<a href="https://agentmods.dev/commands/rajbos/ai-engineering-fluency/improve-mutation-score"><img src="https://agentmods.dev/badge/commands/rajbos/ai-engineering-fluency/improve-mutation-score.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,240 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 $0.00024 $0.01240
Opus 5.5 $0.00010 $0.00496
Sonnet 5.5 $0.00005 $0.00248
Haiku 4.5 $0.00002 $0.00124

Measured yesterday against content hash 721db13d57c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

improve-mutation-score 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.

.github/prompts/improve-mutation-score.prompt.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improve Mutation Score — Issue Recommendations

You are running in GitHub Copilot CLI inside a GitHub Actions workflow. The mutation testing job has just finished and produced a Stryker report. Your job is to read that report, decide which surviving mutants are genuinely worth killing, and open a single GitHub issue with concrete recommendations.

You must not modify source or test files in this run. Open an issue only.


Step 1 — Locate the mutation report

The report is at the path given in the Context Paths section below (typically vscode-extension/reports/mutation/mutation.json). If the file does not exist or has zero mutants, exit cleanly without opening an issue and print:

NO_REPORT — nothing to recommend.

Step 2 — Parse the report

The Stryker JSON has the structure:

{
  "files": {
    "out/src/foo.js": {
      "mutants": [
        { "id": "...", "mutatorName": "...", "replacement": "...",
          "location": { "start": { "line": N, "column": N }, "end": { ... } },
          "status": "Survived", "description": "..." }
      ]
    }
  }
}

Compute:

  • total, killed, survived, timedOut, noCoverage
  • score = killed / (killed + survived + timedOut) * 100

Map compiled JS paths back to TypeScript sources:

Compiled path TypeScript source
out/src/tokenEstimation.js src/tokenEstimation.ts
out/src/sessionParser.js src/sessionParser.ts
out/src/workspaceHelpers.js src/workspaceHelpers.ts
out/src/claudecode.js src/claudecode.ts
out/src/utils/dayKeys.js src/utils/dayKeys.ts
out/src/utils/errors.js src/utils/errors.ts
out/vscode-extension/src/utils/html.js vscode-extension/src/utils/html.ts

For unmapped paths, infer the TypeScript path by replacing out/ with vscode-extension/ and .js with .ts.


Step 3 — Triage surviving mutants

For each Survived mutant, read a few lines of TypeScript context around its location and classify it as one of:

Read the full file on GitHub · 156 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 · 156 lines · 24 tokens per session scan A 721db13d57c1

Subscribe to this mod's changes

improve-mutation-score is a command published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,240 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-26.