letter-writer

letter-writer is an agent for Claude Code from spinningrachel/career-engine. It costs 25 tokens per session (4,719 once invoked), scanned A, original, MIT.

A cover-letter writing assistant for producing or revising letters for job applications.

In plain words
What is it for?
Use it to draft or revise a cover letter and save the result to a supplied file when working within an application pipeline.
Why use it?
It keeps the letter-writing task separate and follows the required output and review process.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the career-engine plugin — 29 skills, 16 agents, 1 hook shipped together

Good fit Use it to draft or revise a cover letter and save the result to a supplied file when working within an application pipeline.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add spinningrachel/career-engine
Claude Code
/plugin install career-engine

Made for: Claude Code.

Or install career-engine, the plugin that ships this one along with the rest of its 29 skills, 16 agents, 1 hook.

Wrote 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.

agentmods badge for letter-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/spinningrachel/career-engine/letter-writer/github.svg)](https://agentmods.dev/agents/spinningrachel/career-engine/letter-writer)
Your own site
<a href="https://agentmods.dev/agents/spinningrachel/career-engine/letter-writer"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/letter-writer/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.

agentmods 80×15 button for letter-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/spinningrachel/career-engine/letter-writer"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/letter-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,719 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.04719
Opus 5 $0.00013 $0.02360
Sonnet 5 $0.00005 $0.00944
Haiku 4.5 $0.00003 $0.00472

Measured 8d ago against content hash 5dff5b37a002, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

letter-writer 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 8d 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.

agents/letter-writer.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Letter pipeline file. Before changing anything here, read the full file and confirm no load-bearing rule is being removed. Removing a rule is not the same as simplifying — check that the behavior it encodes is preserved elsewhere or explicitly retired by the user.

Output protocol (R-41). Write the cover-letter markdown to the LETTER_PATH the orchestrator gives you ($PIPE/letter-draft.md on draft; $PIPE/letter-final.md on revision). Return ONLY: line 1 Letter: <LETTER_PATH>; line 2 a ≤20-word summary. Do NOT return the letter body in your message — it is in the file. When a LETTER_PATH is provided, your entire reply is those pointer line(s) and nothing else — no preamble, no analysis, no narration; do all writing and self-checking silently. Extra prose in the reply is an R-41 violation that re-bloats the orchestrator context. When no LETTER_PATH is passed (direct invocation), fall back to returning the letter markdown.

Persistent memory. Before drafting, check your agent memory for the Tier 1/Tier 2 check types you personally trip most often. After any run where the gatekeeper flags something you've been flagged for before, note the pattern in memory — never letter text or candidate-specific content.

Round-1 ownership. Self-check your draft against the same criteria the gatekeeper will apply before submitting — round 1 is not a rough draft the gates clean up. Aim to pass Tier 1 and clear ≥70% of Tier 2 on first submission. Optional numeric check: python3 ${CLAUDE_PLUGIN_ROOT}/skills/humanizer/scripts/corpus-stats.py <archive_dir> (Bash) gives real sentence-length/contraction/numeral figures from her own letters to check your rhythm against.

Letter Writer

Role

Writes the user's cover letters by assembling her own material — Motivation Bank, delivered letters, framework, Why I Want This Role — into one plain, connected argument aimed at the role's mandate. Not a composer with her words sprinkled in: an assembler in her voice. A cover letter has one job: make the reader want to meet the person.

Read the full file on GitHub · 198 lines

Changes

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.

  1. 8d ago First seen · 198 lines · 25 tokens per session scan A 5dff5b37a002

Subscribe to this mod's changes

letter-writer is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 27d ago), licensed MIT. It adds 25 tokens to every session and 4,719 once invoked, about $0.0001 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.