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 Jeffallan/writing-with-agents --skill architectgit clone --depth 1 https://github.com/Jeffallan/writing-with-agentsWrote 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/jeffallan/writing-with-agents/architect)<a href="https://agentmods.dev/skills/jeffallan/writing-with-agents/architect"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/architect/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/jeffallan/writing-with-agents/architect"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/architect.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 | $0.00038 | $0.02105 |
| Opus 5 | $0.00019 | $0.01052 |
| Sonnet 5 | $0.00008 | $0.00421 |
| Haiku 4.5 | $0.00004 | $0.00211 |
Grade A, and why
architect 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Definition
The Architect is the strategic structuring phase. Human leads decision-making. AI formulates the structure, presents options, and maps material to sections.
Lead: Human decides what the piece is about, what stays, what gets cut. Support: AI organizes, proposes structures, identifies gaps, and builds the blueprint.
The Architect is NOT sentimental about the Madman's output. The Madman overproduced on purpose. Cutting 70-80% of that material is normal and healthy. The goal is to find the strongest 20-30% and arrange it into something a reader can follow.
When to Use This Skill
- After the Whirlybird phase has selected and grouped raw Madman material
- When you have excess material and need to decide what stays and what goes
- When the piece lacks a clear throughline or argument
- When you need to choose between competing structures (technical vs. narrative vs. tutorial)
- When reorganizing an existing draft that has structural problems
- Before handing off to the Carpenter for construction
- When the Carpenter phase has identified a structural problem and sent it back for resolution
- When multiple throughline candidates exist and the human needs options to choose from
- When a draft reads as a collection of ideas rather than a single coherent argument
- When existing content needs to be repurposed for a different audience or format
- When estimating scope (word count, section count) for a planned piece
Core Workflow
-
Receive material -- Take the Whirlybird selection and the full Madman output. The Whirlybird clusters are your starting point; the raw Madman material is your backup inventory.
Return-from-Carpenter variant: When the Carpenter routes a marked-up draft back for structural rework, the input is different: the prior outline (
outline-N.md), the preservation draft (draft-N.md), the marked-up edit copy (draft-N-human-edits.md), and the Carpenter's edit catalog. Regenerate the outline asoutline-N+1.mdreflecting the human's structural edits; do not start the triage from scratch. Preserve the throughline unless the edits explicitly reframe it.
What ships with it
3 files 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.
- 9d ago First seen · 153 lines · 38 tokens per session scan A d75b6a9bced5
architect is a skill published in the GitHub repository Jeffallan/writing-with-agents (30 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 2,105 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…