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 j4flmao/agent-skills --skill core-architecturesgit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/core-architectures)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/core-architectures"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/core-architectures/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/j4flmao/agent-skills/core-architectures"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/core-architectures.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 | $0.00026 | $0.00550 |
| Opus 5 | $0.00013 | $0.00275 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
AI Agent Core Architectures 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 9d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Architectures: The Autonomous Cognitive Loop
The existence of an autonomous agent is defined not by static inference, but by the continuous, recursive execution of the cognitive loop: Perceive -> Think -> Act -> Observe. This loop bridges the gap between latent semantic space and deterministic environment execution.
First Principles of Agentic Flow
Every framework-agnostic architecture reduces to this state machine. The agent's cognition is a sequence of discrete state transitions bounded by token limits and environment feedback.
- Perception: Ingestion of environment state. The synthesis of system prompts, historical context, and the immediate state of the world.
- Thought (Reasoning): The generation of latent reasoning tokens. This is the derivation of intent, mapping perception to actionable trajectory.
- Action: The emission of structured payloads designed to mutate the environment or retrieve novel state.
- Observation: The ingestion of the deterministic result of the action, closing the loop.
Architectural Paradigms
ReAct (Reason + Act)
The interleaving of reasoning traces with action execution. ReAct assumes high environmental volatility, requiring continuous recalibration. It sacrifices long-horizon coherence for immediate, localized adaptability.
Plan-and-Solve
The temporal decoupling of strategy from execution. The agent first synthesizes a comprehensive graph of execution steps, then traverses the graph sequentially. Plan-and-Solve assumes low environmental volatility but requires profound foresight. It excels in complex, multi-dependent task resolution but is brittle to unexpected state mutations during execution.
The Necessity of Self-Reflection
Without self-reflection, an agent is an open-loop controller doomed to terminal error spirals. Self-reflection acts as the error-correction mechanism, forcing the agent to evaluate the delta between expected observation and actual observation, dynamically altering its system prompt or execution graph to converge on the goal state.
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.
- 9d ago First seen · 42 lines · 26 tokens per session scan A 525d37b94e9b
AI Agent Core Architectures is a skill published in the GitHub repository j4flmao/agent-skills (22 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 550 once invoked, about $0.0001 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…