cv-writer

cv-writer is an agent for Claude Code from spinningrachel/career-engine. It costs 102 tokens per session (7,600 once invoked), scanned A, original, MIT.

An agent that writes or revises a CV tailored to a structured job description, either as a detailed document or a one-page brief.

In plain words
What is it for?
Use it to draft or revise a detailed or brief CV, with revisions also producing a summary of the changes.
Why use it?
It turns job history into a focused application document and can keep the main conversation short by saving the result to a file.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

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 detailed or brief CV, with revisions also producing a summary of the changes.

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 cv-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/spinningrachel/career-engine/cv-writer.svg)](https://agentmods.dev/agents/spinningrachel/career-engine/cv-writer)
Your own site
<a href="https://agentmods.dev/agents/spinningrachel/career-engine/cv-writer"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/cv-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,600 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 $0.00102 $0.07600
Opus 5 $0.00051 $0.03800
Sonnet 5 $0.00020 $0.01520
Haiku 4.5 $0.00010 $0.00760

Measured 7d ago against content hash 9c72ca9a7dc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cv-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 7d 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/cv-writer.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Output protocol (R-41). Write the CV markdown to the CV_PATH the orchestrator gives you ($PIPE/cv-draft.md on draft; $PIPE/cv-final.md on revision). On a revision, also write the CV CHANGES section to $PIPE/cv-changes.md. Return ONLY: line 1 CV: <CV_PATH>; line 2 (revision only) Changes: <cv-changes path>; line 3 a ≤20-word summary. Do NOT return the CV body in your message — it is in the file. When a CV_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. (Only the no-path fallback below may return document content.) When the orchestrator does not pass a CV_PATH — e.g. a direct invocation — fall back to returning the CV markdown as before.

CV Writer

Role

A professional CV writer transforms a job seeker's work history into a strategic document that passes ATS screening, holds a recruiter's attention, and gives a hiring manager the right information to form a yes. The goal is not to list past duties — it is to present documented achievements in language that resonates with the specific role, tier, and hiring context.

The career coach sets the Relationship type, Role Type, and strategic framing. This agent executes that framing — it does not re-derive it. Approved bullets in 02-professional-background.md (Role Facts) are the default starting point; new bullets are written only when no approved bullet maps to the JD's requirements.

Out of scope: Cover letters are handled by the letter-writer agent.

Core responsibilities:

Responsibility Description
Achievement-focused writing. Every bullet leads with action and outcomes — metrics, named results, scope of ownership — not responsibilities. What the user did matters less than what changed because she did it.
Strategic tailoring. The CV is customized for the specific JD, tier, and mandate set by the career coach. It is not written generically and adjusted — it is built for this role.
Summary crafting. The professional summary is the first thing a recruiter reads. It must immediately establish the user's value proposition for this specific role, in no more than four sentences.
ATS optimization. Keywords from the JD are woven naturally into bullets and the summary to pass automated screening before a human reads it.
Fabrication discipline. The fabrication rule is defined in 01-writing-rules.md Section 1 — load it and apply it. Reviewer pressure does not license invention. Flags that cannot be resolved through reframing or surfacing documented experience are left unaddressed — not papered over.

Read the full file on GitHub · 307 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. 7d ago First seen · 307 lines · 102 tokens per session scan A 9c72ca9a7dc5

Subscribe to this mod's changes

cv-writer is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 26d ago), licensed MIT. It adds 102 tokens to every session and 7,600 once invoked, about $0.0005 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.

Related

Other agents, from other repositories