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 letter-coregit 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/letter-core)<a href="https://agentmods.dev/skills/spinningrachel/career-engine/letter-core"><img src="https://agentmods.dev/badge/skills/spinningrachel/career-engine/letter-core/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/letter-core"><img src="https://agentmods.dev/badge/skills/spinningrachel/career-engine/letter-core.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 | $0.00079 | $0.03443 |
| Opus 5 | $0.00039 | $0.01722 |
| Sonnet 5 | $0.00016 | $0.00689 |
| Haiku 4.5 | $0.00008 | $0.00344 |
Grade A, and why
letter-core 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Letter Core — the letter-writer's complete working doctrine
This is the ONLY doctrine file the letter-writer loads. Everything else about letters is enforced at the gatekeeper — when a violation comes back, it arrives with the rule quoted and a fix direction; fix that, touch nothing else. Write plainly from her material and you will pass.
1. The job: assemble her material, don't compose
The rule, in the user's own words (2026-07-24): "open the letter with context using the outline, templates, verbatim banks etc. to write that sentence and the rest of the letter, and adding additional content insofar as may prove to be necessary AFTER an exhaustive search of all available insights inside the /career-data skill." That is the whole method — the outline gives the structure, her templates and verbatim banks give the sentences, and composing anything new is the last resort, not a parallel track.
The letter is built FROM the user's existing words, aimed at this role. Her material: the role-matched Motivation Bank rows, delivered-letter phrasings and openers (read at the Voice Gate), 03-framework.md lines, and Why I Want This Role when present. Reusing her sentences verbatim is not a shortcut — it is the method. Her proven phrasing lands better than anything composed fresh, and she recognizes it as hers. Fresh content is permitted only AFTER an exhaustive search of ALL of career-data comes up short for that specific need — not just the Bank and delivered letters, but 03-framework.md and its sub-files, the role-facts files, approved summaries and bullets, testimonials, and portfolio. "I didn't find it in the first two files I opened" is not exhaustion. When you do compose, it exists to connect her pieces or fill a genuine gap the whole of career-data couldn't — and keep it plain.
Two kinds of her material, handled differently:
- Finished prose (a Bank row written as sentences, a delivered-letter line): carry it intact. Do not paraphrase, polish, or "improve" it.
- Note-form shorthand (a telegraphic WIWTR jot — "Doing good. Win win."): that is meaning, not prose. Develop it into a sentence in her voice, keeping her exact words inside a grammatical frame. Never paste it raw; never erase it into polished-professional language either. Both directions lose her.
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 · 106 lines · 79 tokens per session scan A 9d2d436a07bc
letter-core is a skill published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 28d ago), licensed MIT. It adds 79 tokens to every session and 3,443 once invoked, about $0.0004 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…