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 Cratis/AI --skill safeguarding-ai-generated-codegit clone --depth 1 https://github.com/Cratis/AIWrote 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/cratis/ai/safeguarding-ai-generated-code)<a href="https://agentmods.dev/skills/cratis/ai/safeguarding-ai-generated-code"><img src="https://agentmods.dev/badge/skills/cratis/ai/safeguarding-ai-generated-code/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/cratis/ai/safeguarding-ai-generated-code"><img src="https://agentmods.dev/badge/skills/cratis/ai/safeguarding-ai-generated-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00101 | $0.00601 |
| Opus 5.5 | $0.00040 | $0.00240 |
| Sonnet 5.5 | $0.00020 | $0.00120 |
| Haiku 4.5 | $0.00010 | $0.00060 |
Grade A, and why
safeguarding-ai-generated-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.
What it actually says
Safeguarding AI-Generated Code
Use only in repositories that opted into cratis/codescene and have CodeScene MCP tools available; otherwise skip without blocking and say so. The Cratis policy in .cratis/ai/rules/codescene.md overrides this skill where they differ.
Overview
Use Code Health safeguards before declaring AI-touched code ready. The goal is to catch maintainability regressions early and prevent agents from normalizing technical debt.
When to Use
- The agent changed code and is about to suggest a commit.
- The user asks whether a branch or staged changes are safe to merge.
- The workflow needs a quality gate for AI-generated code.
Do not use this skill for broad refactoring discovery or project-level prioritization.
Quick Reference
code_health_review: Review each AI-modified file immediately after the change.pre_commit_code_health_safeguard: Check staged or modified files before commit.analyze_change_set: Check a branch or PR-style change set against a base ref.
Implementation
- After each AI modification to a file, run
code_health_reviewon that file. - If the review reports maintainability problems or regression risk, refactor the file in small steps and review it again.
- Run
pre_commit_code_health_safeguardbefore commit-oriented recommendations as a broader gate across staged or modified files. - Run
analyze_change_setbefore PR-oriented recommendations as a final branch-level gate. - If either later gate reports a regression, inspect the affected files with
code_health_reviewand keep iterating until the issue is removed or the user explicitly accepts the risk.
Common Mistakes
- Waiting until commit time to run the first Code Health check.
- Treating safeguard output as optional guidance instead of a release gate.
- Declaring work done after a failing safeguard.
- Jumping straight to broad rewrites instead of inspecting the flagged files first.
- Treating an accepted risk as invisible; call it out explicitly.
What ships with it
2 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.
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.
- 3d ago Changed · +43 tokens per session 4cf47b0641ee
- 7d ago Changed 3c8bbfb76788
- 11d ago First seen · 45 lines · 58 tokens per session scan A 5efc92798ac6
safeguarding-ai-generated-code is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 601 once invoked, about $0.0004 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 2026-10-11.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…