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 spinningrachel/career-engine --skill writer-craftgit clone --depth 1 https://github.com/spinningrachel/career-engineWrote 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/spinningrachel/career-engine/writer-craft)<a href="https://agentmods.dev/skills/spinningrachel/career-engine/writer-craft"><img src="https://agentmods.dev/badge/skills/spinningrachel/career-engine/writer-craft/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/spinningrachel/career-engine/writer-craft"><img src="https://agentmods.dev/badge/skills/spinningrachel/career-engine/writer-craft.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 | $0.00162 | $0.00896 |
| Opus 5 | $0.00081 | $0.00448 |
| Sonnet 5 | $0.00032 | $0.00179 |
| Haiku 4.5 | $0.00016 | $0.00090 |
Grade A, and why
writer-craft 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writer Craft — Consolidated Doctrine
Reader change (2026-07-18, per the user's approved rulebook reduction): the letter-writer no longer loads this file — it loads skills/letter-core/SKILL.md, a ~1,500-word working core (preloaded via its frontmatter). This file's [CL] sections remain in place as the gatekeeper's enforcement reference (gates cite them by section number) and the maintainer's source of truth; every [CL] rule is either carried in letter-core or enforced at a gate — see docs/rule-map-letter-core.md for the complete mapping. No rule was removed.
One file's current readers: cv-writer (sections tagged [CV] plus every [ALL] section), the humanizer ([ALL] sections), and the gatekeeper (as reference). This file replaces four prior files — nothing here is optional because it moved. (The humanizer reads its own dedicated skill, skills/humanizer/SKILL.md, which now carries the humanizer-specific mechanics this file used to hold at former §12 Humanizer Mechanics and §13 Voice Calibration Protocol.)
Why this file is shaped the way it is. Real production runs hit 7-round whack-a-mole revision loops. Forensic analysis of those runs plus condensed-prompt experiments found: (1) most violations trace to a small, repeatable set of rules — not the long tail; (2) a narrowly-scoped rule ("no em dash as list separator") gets gamed around the narrow scope — bans here are stated at full width; (3) loading 3-4 large files per writer spawn has a real token cost per revision round. This file is short on purpose. Every rule below either fired in a real traced violation this session or defines document correctness (not style).
Where the doctrine lives (context-diet split, 2026-07-22)
The consolidated doctrine was split into three sub-files in this directory so each reader loads only what governs its surface. Section numbers (§1–12) are globally unique and preserved — a citation like "writer-craft §8" resolves unambiguously to exactly one sub-file.
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 · 32 lines · 162 tokens per session scan A 4f7a21b64837
writer-craft is a skill published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 29d ago), licensed MIT. It adds 162 tokens to every session and 896 once invoked, about $0.0008 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 2026-08-31.
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…