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 update-instructiongit 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/update-instruction)<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/update-instruction"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/update-instruction/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/update-instruction"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/update-instruction.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 | $0.00033 | $0.01081 |
| Opus 5 | $0.00016 | $0.00541 |
| Sonnet 5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
update-instruction 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 10d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Instruction Templates
Instructions are persistent context and rules that apply to AI conversations, scoped by file patterns or always-on.
Finding the Right Instruction
1. Search existing instructions
List files in <%= instructionTemplatePath() %>/ and read their frontmatter (description, globs) to understand what each covers and its scope.
2. Match the user's intent to existing files
Look for instructions that already cover the same topic or a closely related topic. Consider:
- Exact match: an instruction about the same subject exists → update it
- Partial overlap: the topic fits within the scope of a broader instruction → add to it rather than creating a separate file
- Multiple candidates: several instructions touch on the topic → pick the one whose
globsand purpose align best with the user's intent
3. Determine scope for new instructions
If no existing instruction fits, investigate the project to decide where the instruction belongs:
- Search the codebase for how the topic is used — find which files and directories are relevant
- Cross-reference with the user's wording — the instruction may apply broadly (e.g. "always validate env vars") or narrowly (e.g. "feature flags in API routes should use env vars")
- Choose the right scoping:
- If the rule is universal across the project → use
alwaysApply: true - If it applies to a specific area → use
globsmatching only the relevant files/directories - If the topic appears in many places but the instruction only makes sense for a subset, scope to that subset
- If the rule is universal across the project → use
Example: The user says "feature flags should be loaded from env vars." Feature flags might appear in 10 places across the codebase, but if only the API layer loads them from config, the right scope is globs: ["src/api/**"] rather than alwaysApply: true.
Deciding What to Do
- Create new: when the topic is distinct from all existing instructions
- Update existing: when an instruction already covers the topic but needs changes — modify its content or frontmatter
- Add per-target override: when a frontmatter field needs different values per target, use the override object syntax:
description: claude: Claude-specific description copilot: Copilot-specific description default: Default description - Delete: when an instruction is obsolete or fully superseded by another
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.
- 10d ago First seen · 93 lines · 33 tokens per session scan A 8ed8d1aa1a3b
update-instruction is a skill published in the GitHub repository fabis94/universal-ai-config (11 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 1,081 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…