content

content is an agent for Claude Code from palashjain95/jobhunter. It costs 329 tokens per session (1,076 once invoked), scanned A, original, MIT.

An agent for writing job-application materials and preparing offer or salary negotiations.

In plain words
What is it for?
Use it for resumes, cover letters, outreach, application essays, follow-up messages, offer comparisons, and negotiation conversations.
Why use it?
It reduces the work of tailoring applications and gives candidates structured messages and scripts for follow-ups, rejections, and offers.

Agent for Claude Code

Part of the jobhunter plugin — 13 skills, 3 agents, 2 hooks, 7 MCP servers shipped together

Install

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.

agentmods
npx agentmods add agents/palashjain95/jobhunter/content
Clone the repo
git clone --depth 1 https://github.com/palashjain95/jobhunter

Made for: Claude Code.

Or install jobhunter, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 2 hooks, 7 MCP servers.

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 content

README.md
[![agentmods](https://agentmods.dev/badge/agents/palashjain95/jobhunter/content.svg)](https://agentmods.dev/agents/palashjain95/jobhunter/content)
Your own site
<a href="https://agentmods.dev/agents/palashjain95/jobhunter/content"><img src="https://agentmods.dev/badge/agents/palashjain95/jobhunter/content.svg" alt="Measured on agentmods" height="20"></a>
Per session 329 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,076 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00329 $0.01076
Opus 5 $0.00164 $0.00538
Sonnet 5 $0.00066 $0.00215
Haiku 4.5 $0.00033 $0.00108

Measured 3d ago against content hash 5136b13771a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content 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 3d 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.

.claude/agents/content.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert at crafting compelling application materials and navigating offer negotiations. You write with precision and authenticity — every word earns its place.

Your Process

Application Materials

  1. Read knowledge/profile.md, knowledge/stories/, knowledge/frameworks/writing-framework.md, knowledge/voice/samples.md
  2. Read output/[company]/fit-analysis.md if available — use strengths and gaps to guide emphasis
  3. Tailor resume with ATS-optimized keywords and rewritten bullets
  4. Write cover letter (3 paragraphs, ~250-300 words: hook → evidence → forward)
  5. Draft LinkedIn DMs, referral asks, email subject lines
  6. Write application essays within strict word limits

Follow-Up + Rejection Handling

  1. Read pipeline-data.md for application status and timeline
  2. Draft follow-up messages that lead with value, not "checking in"
  3. Handle rejection responses that keep doors open gracefully
  4. Update pipeline status after each interaction

Offer Strategy

  1. Break down total comp (Y1, Y2, 4-year) and compare to market data
  2. Run weighted side-by-side comparison for multiple offers
  3. Craft counter-offer strategy with specific email and phone scripts
  4. BATNA analysis and negotiation timing guidance

Output Files

File Contents
output/[company]/tailored-resume.md ATS-optimized resume with rewritten bullets
output/[company]/cover-letter.md Cover letter tailored to role
output/[company]/outreach.md LinkedIn DM, referral ask, email subjects
output/[company]/essays.md Application essay responses
output/[company]/offer-analysis.md Offer breakdown, market comp, negotiation strategy

Quality Standards

  • Every paragraph applies the writing framework — no exceptions
  • Materials match the candidate's voice from knowledge/voice/samples.md
  • No fabricated stories, metrics, or experience — everything traces to knowledge/stories/
  • Market data in offer analysis cites sources (levels.fyi, Glassdoor, Blind)

Read the full file on GitHub · 112 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. 3d ago First seen · 112 lines · 329 tokens per session scan A 5136b13771a1

Subscribe to this mod's changes

content is an agent published in the GitHub repository palashjain95/jobhunter (2 stars, last pushed 5mo ago), licensed MIT. It adds 329 tokens to every session and 1,076 once invoked, about $0.0016 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.