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 fabis94/universal-ai-config --skill report-feature-changesgit clone --depth 1 https://github.com/fabis94/universal-ai-configWrote 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/fabis94/universal-ai-config/report-feature-changes)<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/report-feature-changes"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/report-feature-changes/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/fabis94/universal-ai-config/report-feature-changes"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/report-feature-changes.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 | $0.00064 | $0.02115 |
| Opus 5.5 | $0.00026 | $0.00846 |
| Sonnet 5.5 | $0.00013 | $0.00423 |
| Haiku 4.5 | $0.00006 | $0.00212 |
Grade A, and why
report-feature-changes 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Feature Changes
Compare uac's implementation against the latest upstream documentation for each supported AI tool. Produce a structured report of out-of-date assumptions so the user can decide what to change.
This skill does not modify uac source files. It only produces a report. Any code/doc changes are a follow-up step.
Inputs
Parse $ARGUMENTS:
--tool <name>— restrict to one tool (claude,copilot,cursor,codex). Defaults to all supported tools.--feature <category>— restrict to one Part 1 feature category from the reference (e.g.hooks,mcp,frontmatter,tools). Defaults to all categories.
If no arguments are provided, ask the user with AskUserQuestion whether they want to validate everything (slow, thorough) or scope down to a single tool/feature first.
Step 1: Load the Validation Reference
Read upstream-validation-reference.md — the companion file in this skill directory. It defines:
- Part 1 — the feature categories to validate (file locations, frontmatter, hooks, tools, MCP, permissions, models, cross-tool discovery, etc.) and where each is implemented in uac (
src/targets/<tool>/index.ts, etc.). - Part 2 — per-tool documentation URLs grouped by tier. Tier 1 is authoritative (vendor reference docs). Tier 2 is for dating changes (changelogs). Tier 3 is community/supporting evidence only.
- Part 5 — known documentation quality caveats (beta-API churn, in-product-only docs, vendor terminology drift, multiple doc surfaces).
- Part 6 — how to investigate a tool's internals (isolated install, headless runs, where to see what was loaded, how to read its shipped code) when the docs don't settle a question.
Treat this reference as the source of truth for what to check and where to look. Do not invent new URLs — if a needed doc page is missing from the reference, note it as a gap in the final report.
Step 2: Snapshot uac's Current Assumptions
Before fetching any docs, read uac's current implementation for each tool in scope so you have a concrete baseline to compare against. For each tool:
What ships with it
1 file 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.
- yesterday Changed · +12 lines 841760a0ef67
- 2d ago Changed 9d16f57a3af9
- 2mo ago First seen · 132 lines · 64 tokens per session scan A aa184712de78
report-feature-changes is a skill published in the GitHub repository fabis94/universal-ai-config (14 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 2,115 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.
report-feature-changes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| report-feature-changesfabis94/universal-ai-config | Skill | 14 | 2d ago | MIT | A | 64 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |