code-quality-fix-all

code-quality-fix-all is a skill for Claude Code from UKGovernmentBEIS/inspect_evals. It costs 82 tokens per session (3,575 once invoked), scanned A, original, MIT.

A workflow for fixing code-quality problems recorded in review files under agent_artefacts/code_quality/. It works through selected issues and checks the changes with validation and tests.

In plain words
What is it for?
Use it after a code-quality review to choose issue types, difficulty levels, evaluations, and a maximum number of fixes, then address the matching findings.
Why use it?
It turns a review's list of problems into an organised repair process instead of leaving developers to fix issues one by one without a shared record.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Use it after a code-quality review to choose issue types, difficulty levels, evaluations, and a maximum number of fixes, then address the matching findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ukgovernmentbeis/inspect_evals/code-quality-fix-all
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.

Any agent
npx skills add UKGovernmentBEIS/inspect_evals --skill code-quality-fix-all
Clone the repo
git clone --depth 1 https://github.com/UKGovernmentBEIS/inspect_evals

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 code-quality-fix-all

README.md
[![agentmods](https://agentmods.dev/badge/skills/ukgovernmentbeis/inspect_evals/code-quality-fix-all.svg)](https://agentmods.dev/skills/ukgovernmentbeis/inspect_evals/code-quality-fix-all)
Your own site
<a href="https://agentmods.dev/skills/ukgovernmentbeis/inspect_evals/code-quality-fix-all"><img src="https://agentmods.dev/badge/skills/ukgovernmentbeis/inspect_evals/code-quality-fix-all.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,575 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00082 $0.03575
Opus 5 $0.00041 $0.01788
Sonnet 5 $0.00016 $0.00715
Haiku 4.5 $0.00008 $0.00358

Measured 8d ago against content hash 6dbb15782694, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-quality-fix-all 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 8d 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/code-quality-fix-all/SKILL.md · 436 lines

How it starts

The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Quality Fix All

Fix code quality issues identified in a code quality review. This skill systematically addresses issues found by the code-quality-review-all skill for ANY code quality topic, with validation and testing at each step.

Expected Arguments

When invoked, this skill expects the path to a code quality topic as an argument (e.g., agent_artefacts/code_quality/private_api_imports).

If not provided, the skill will ask the user for the topic path. Within the topic path, there are several files:

  • README.md - contains description of the issue and examples of how to fix it
  • results.json - contains list of all identified issues
  • SUMMARY.md - contains summary of the identified issues

Filters and options are specified interactively after the skill starts by using the AskUserQuestion tool to present options unless specified otherwise in arguments.

  • Which issue types to target:
    • all
    • specific types
    • Fix complexity level (easy only, medium and below, or all)
  • Which evaluations to fix (all, specific ones, evaluations with small number of issues)
  • Maximum number of issues to fix in this run

Workflow

Phase 1: Understanding the Topic and Planning

  1. Read topic documentation

    • Read the README.md to understand:
      • What code quality issue this topic addresses
      • Why it matters (stability, maintainability, etc.)
      • How to detect the issue
      • How to fix the issue (fix patterns, examples)
    • Read results.json to get all identified issues
    • Identify which issues are in scope based on arguments
  2. Analyze and categorize issues

    • Analyze fix complexity based on:
      • issue_description
      • suggested_fix from results.json
      • Fix examples in README.md
    • Classify as:
      • Easy: Single-line changes, clear fix pattern in README
      • Medium: Multi-line changes, well-documented fix approach
      • Hard: No clear fix pattern, requires research or copying code
    • Group issues by evaluation and issue type
    • Generate statistics for presenting to user

Read the full file on GitHub · 436 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. 8d ago First seen · 436 lines · 82 tokens per session scan A 6dbb15782694

Subscribe to this mod's changes

code-quality-fix-all is a skill published in the GitHub repository UKGovernmentBEIS/inspect_evals (659 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 3,575 once invoked, about $0.0004 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.