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 agentmods add skills/bouob/sysadmin-skills/ai-changenpx skills add bouob/sysadmin-skills --skill ai-changegit clone --depth 1 https://github.com/bouob/sysadmin-skillsWrote 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/bouob/sysadmin-skills/ai-change)<a href="https://agentmods.dev/skills/bouob/sysadmin-skills/ai-change"><img src="https://agentmods.dev/badge/skills/bouob/sysadmin-skills/ai-change.svg" alt="Measured on agentmods" 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 | $0.00218 | $0.02841 |
| Opus 5 | $0.00109 | $0.01421 |
| Sonnet 5 | $0.00044 | $0.00568 |
| Haiku 4.5 | $0.00022 | $0.00284 |
Grade A, and why
ai-change 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 6d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI System Change Request Workflow
Structured change management for AI and ML systems, applying ITIL v5 AI Governance principles. Produces an RFC with an AI governance appendix.
This skill extends /change-request with AI-specific fields and governance requirements. For non-AI infrastructure changes, use /change-request instead.
Related Skills (auto-loaded)
- itil — change types, risk matrix, CAB process; reads
references/ai-governance-6c.mdfor 6C classification - done-ops — verification gate before finalizing the change
Output
File: {OUTPUT_DIR}/ai-change-{YYYY-MM-DD}-{slug}.md
- slug: kebab-case summary, e.g.
claude-sonnet-upgrade,rag-knowledge-base-refresh,sentiment-model-retrain - Change ID (
CHG-{YYYYMMDD}-{NNN}): same format as standard RFC
Default output directory: ./changes/ai/. Fall back to ./changes/ if that doesn't exist.
All change documents are written in English. Preview in user's preferred language before writing.
What Counts as an AI System Change
| Change Type | Examples |
|---|---|
| Model version update | Upgrading from GPT-4 to GPT-4o, Claude 3.5 → Claude Sonnet 4.6 |
| Prompt engineering | Modifying system prompts, changing output format, adding/removing instructions |
| Training data | Adding new data sources, re-weighting, removing data segments, updating cutoff date |
| RAG / knowledge base | Updating indexed documents, changing chunking strategy, switching embedding models |
| AI autonomy expansion | Allowing AI to take more actions without human approval |
| Model retraining / fine-tuning | Domain adaptation, task-specific fine-tuning, RLHF updates |
| AI infrastructure | Changing inference hardware, updating serving configuration, scaling policies |
If unsure whether a change qualifies, apply this test: Could the AI's behavior change as a result? If yes, this skill applies.
Workflow
Step 1: Gather Change Details
Collect the following (use AskUserQuestion for missing items):
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.
- 6d ago First seen · 284 lines · 218 tokens per session scan A 3b51fd68ab68
ai-change is a skill published in the GitHub repository bouob/sysadmin-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 218 tokens to every session and 2,841 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
servicenow-change-management
ITSM change-management operations on the ServiceNow Change API via the servicenow-api MCP server — the full change-request lifecycle: query changes, tasks, schedules, CIs, models and standard-change templates; create/update changes and change-tasks; run risk calculation and conflict checks; approve; and delete. Use…
binary-analysis
Analyze binary files (exe, dll, sys, bin, ocx, scr, cpl, drv, elf, so, macho, apk) to assess if they are malicious, perform decompilation, extract strings/imports/exports, detect malware, and provide threat assessment. Use this skill when user asks to analyze, examine, check, or assess any binary file, asks if a file…
kernel-cve-analysis
Query the Android/AOSP kernel CVE database to look up a specific CVE, find CVEs affecting a kernel version or build date, find unpatched CVEs in a branch, or identify exploitable vulnerabilities. Use this skill when the user asks about Android kernel CVEs, AOSP kernel vulnerabilities, which CVEs affect a kernel…
spill-scrub
Find and scrub credentials that leaked into Claude Code's own local logs (transcripts, paste-cache, shell snapshots, /.claude.json). Use when the user mentions a spillage, a leaked or pasted secret, "clean the logs", "scrub my transcripts", "I pasted a key", "did a token get logged", or after any incident where a…
pace-change
Use when user says "不做了", "搁置", "停掉", "加一个", "加需求", "追加", "改需求", "需求变了", "范围变了", "优先级调", "延后", "提前", "砍掉", "先做这个", "排到前面", "恢复", "捡回来", "pace-change", or wants to add, pause, resume, reprioritize, modify, undo, batch change, or query change history. NOT for code implementation (/pace-dev) or project init (/pace-init).
pace-retro
Use when user says "回顾", "复盘", "度量", "retro", "总结", "数据分析", "DORA", "质量报告", "交付效率", "度量报告", "趋势", "中期检查", "对比", "预测", "forecast", "能按时交付吗", "交付概率", "瓶颈", "pace-retro", or at iteration end when reviewing progress and metrics. NOT for next-step recommendations (use /pace-next). NOT for current status overview (use…