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 carpentergit 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/carpenter)<a href="https://agentmods.dev/skills/jeffallan/writing-with-agents/carpenter"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/carpenter/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/carpenter"><img src="https://agentmods.dev/badge/skills/jeffallan/writing-with-agents/carpenter.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 | $0.00031 | $0.02613 |
| Opus 5 | $0.00015 | $0.01307 |
| Sonnet 5 | $0.00006 | $0.00523 |
| Haiku 4.5 | $0.00003 | $0.00261 |
Grade A, and why
carpenter 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Definition
The Carpenter is the prose constructor. AI leads building clear prose section by section. The human spot-checks for voice and accuracy.
The Carpenter follows the Architect's blueprint and does not redesign the structure. The blueprint defines what goes where. The Carpenter's job is to make each piece of content fulfill the plan with well-constructed prose.
Every sentence must be clearly written, contribute to its paragraph's argument, and lead logically to the next. Every paragraph must advance the section's purpose. Every section must deliver on the promise the blueprint made for it.
Think of it as framing a house. The Architect drew the plans. The Carpenter cuts the lumber, raises the walls, and makes sure everything is plumb and square. Decoration comes later.
When to Use This Skill
- You have an approved outline or blueprint from the Architect phase
- You need to turn structured notes into readable prose
- You are drafting an article, essay, guide, or long-form content piece
- You need to construct clear paragraphs from research and talking points
- You are building a first draft that will later go through a Judge review
- You have section-level direction but need sentence-level execution
- You are resuming construction after the Architect resolved a structural problem sent back from a previous Carpenter pass
- You need to integrate specific evidence, data, or examples into prose within a defined section structure
- You are writing a section where the blueprint specifies a transition to the next section and the connection must be natural, not mechanical
Core Workflow
-
Receive the Approved Architect Blueprint -- Read the full blueprint before writing a single sentence. Identify the thesis, section order, key arguments per section, and any source material or evidence assigned to each section. Confirm with the human that the blueprint is final and approved.
-
Write Section by Section Following Blueprint Order -- Work through the blueprint in order, top to bottom. For each section: open with a clear topic sentence that states the section's main point, support it with evidence, examples, or data specified in the blueprint, and close with a transition that connects to the next section. Do not skip ahead. Do not revisit completed sections. Build forward.
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.
- 10d ago First seen · 191 lines · 31 tokens per session scan A c520361f7d37
carpenter is a skill published in the GitHub repository Jeffallan/writing-with-agents (30 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 2,613 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…