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.
npx skills add UKGovernmentBEIS/inspect_evals --skill code-quality-fix-allgit clone --depth 1 https://github.com/UKGovernmentBEIS/inspect_evalsWrote 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.
[](https://agentmods.dev/skills/ukgovernmentbeis/inspect_evals/code-quality-fix-all)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.03575 |
| Opus 5.5 | $0.00033 | $0.01430 |
| Sonnet 5.5 | $0.00016 | $0.00715 |
| Haiku 4.5 | $0.00008 | $0.00358 |
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 2mo 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.
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
-
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
- Read the README.md to understand:
-
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
- Analyze fix complexity based on:
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.
- 2mo ago First seen · 436 lines · 82 tokens per session scan A 6dbb15782694
code-quality-fix-all is a skill published in the GitHub repository UKGovernmentBEIS/inspect_evals (721 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 3,575 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…