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/danielmiessler/paiplugin/always-initnpx skills add danielmiessler/PAIPlugin --skill always-initgit clone --depth 1 https://github.com/danielmiessler/PAIPluginWhat 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 | $0.00041 | $0.00740 |
| Opus 5 | $0.00020 | $0.00370 |
| Sonnet 5 | $0.00008 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
always-init 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 2d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ALWAYS-INIT - Universal Task Initializer
⚠️ CRITICAL SYSTEM REQUIREMENT ⚠️
AUTOMATIC INVOCATION REQUIRED: This skill MUST be automatically invoked as the FIRST action for EVERY user request without exception.
Trigger Pattern: ALL user messages/requests
Priority Level: P0 (Highest - blocks all other operations)
Automation Rule: if (userRequest) → invoke("always-init") → then processRequest()
🎯 Purpose
Universal context loader providing complete PAI (Personal AI Infrastructure):
- 👥 Contacts: Alice, Bob, Carol, Dave, team members
- 🛠️ Stack Preferences: TypeScript>Python, bun>npm, uv>pip
- 🔒 Security Protocols: Repository safety, credential handling
- 📝 Response Format: Structured output standards
- 🎙️ Voice Routing: ElevenLabs voice IDs for agents
- ⚙️ Operating Instructions: Personal preferences and workflows
❌ Consequences of Skipping
Without ALWAYS-INIT context loading:
- Responses lack relationship/contact awareness
- Wrong technical stacks used (npm instead of bun, pip instead of uv)
- Security protocols violated
- Incorrect response formatting
- Missing personalization
- Context-dependent decisions fail
- Agent routing fails
🔄 Implementation Protocol
For AI Assistant (Claude):
1. Receive user request
2. ⚡ IMMEDIATELY: Skill("always-init") ← THIS STEP
3. Wait for PAI context to load
4. THEN proceed with request processing
For Skill System (Automation):
// Automatic prepend to request pipeline
function handleUserRequest(request) {
await invokeSkill("always-init"); // MANDATORY FIRST STEP
const paiContext = loadContext();
return processWithContext(request, paiContext);
}
🎯 Success Criteria
This skill is working correctly when:
- ✅ Invoked before ANY tool use
- ✅ Invoked before ANY other skill
- ✅ Invoked before ANY response formulation
- ✅ Invoked for 100% of user requests
- ✅ PAI context available in all subsequent operations
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.
- 2d ago First seen · 99 lines · 41 tokens per session scan A d2121909cbd1
always-init is a skill published in the GitHub repository danielmiessler/PAIPlugin (56 stars, last pushed 9mo ago), licensed MIT. It adds 41 tokens to every session and 740 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…