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 Koredotcom/agents-mcp-tools --skill arch-agent-guidegit clone --depth 1 https://github.com/Koredotcom/agents-mcp-toolsWrote 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/koredotcom/agents-mcp-tools/arch-agent-guide)<a href="https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-agent-guide"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-agent-guide/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/koredotcom/agents-mcp-tools/arch-agent-guide"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-agent-guide.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00108 | $0.02570 |
| Opus 5.5 | $0.00043 | $0.01028 |
| Sonnet 5.5 | $0.00022 | $0.00514 |
| Haiku 4.5 | $0.00011 | $0.00257 |
Grade A, and why
arch-agent-guide 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arch Agent Guide
Use this skill first when a developer asks about an agent and you are not sure which Arch skill fits. It sets up the connection, routes the question, and applies the working rules every other skill assumes.
0. If the Arch MCP tools are not available
If no platform_* or debug_* tools are available, the MCP server is not connected. Offer to add it:
claude mcp add arch-agent-platform -- npx -y @koreai/arch-mcp-tools
codex mcp add arch-agent-platform -- npx -y @koreai/arch-mcp-tools
- Pin the environment by setting
AGENTS_URLin the server'senv: productionhttps://agents.kore.ai, devhttps://agents-dev.kore.ai, staginghttps://agents-staging.kore.ai, QAhttps://agents-qa.kore.ai. - Pin the package version (
@koreai/arch-mcp-tools@<version>) when a team must see the same tools. - After restarting the client, confirm the server shows as connected (
/mcpin Claude Code, the MCP list in Codex). Ifplatform_connectfails, report its error as-is; do not fall back to REST calls or the UI.
1. Connect and scope before answering
- Call
platform_connect. If no environment is pinned, ask which one. - Get the project ID. If the developer does not know it, list projects with
platform_projects. - For a debugging question, get the session ID, or find it with
debug_session_history. - Read the project's
AGENTS.mdorCLAUDE.md. If there is none, offer to create one:
# Agent project
- Platform environment: <production | dev | staging | QA>, project ID: <id>
- Channels and languages: <chat, voice pipeline, speech-to-speech; languages>
- Topology: <one paragraph: entry agent, specialists, how each is reached>
- Experience contract: docs/experience-contract.md (latency and model-call budgets per intent)
- Eval sets: <names>; baseline run: <run id>
- Always use the arch-agent-platform MCP tools to read sessions, traces, flow graphs and eval
runs before answering or changing anything. Follow the arch-\* skills' output contracts.
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 First seen · 156 lines · 108 tokens per session scan A 869675b11d7a
arch-agent-guide is a skill published in the GitHub repository Koredotcom/agents-mcp-tools (4 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 2,570 once invoked, about $0.0004 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 2026-10-09.
Other skills, from other repositories
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…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…