slushpile-fatigued-reader

slushpile-fatigued-reader is an agent for Claude Code from VonTerraProject501c3/slushpile. It costs 15 tokens per session (1,797 once invoked), scanned A, original, MIT.

A simulated review by a tired recruiter reading a job application. It focuses on what makes a resume or cover letter easy to skim, annoying, boring, or worth closer attention.

In plain words
What is it for?
Use it to review resumes and cover letters from a recruiter's perspective and identify passages likely to be skimmed, disliked, or strong enough to earn more attention.
Why use it?
It exposes problems that an automated grammar or AI-writing check may miss, such as dense wording, weak openings, humblebrags, or an irritating closing.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the slushpile plugin — 11 skills, 8 agents shipped together

Good fit Use it to review resumes and cover letters from a recruiter's perspective and identify passages likely to be skimmed, disliked, or strong enough to earn more attention.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vonterraproject501c3/slushpile/slushpile-fatigued-reader
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.

Clone the repo
git clone --depth 1 https://github.com/VonTerraProject501c3/slushpile

Made for: Claude Code.

Or install slushpile, the plugin that ships this one along with the rest of its 11 skills, 8 agents.

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 slushpile-fatigued-reader

README.md
[![agentmods](https://agentmods.dev/badge/agents/vonterraproject501c3/slushpile/slushpile-fatigued-reader/github.svg)](https://agentmods.dev/agents/vonterraproject501c3/slushpile/slushpile-fatigued-reader)
Your own site
<a href="https://agentmods.dev/agents/vonterraproject501c3/slushpile/slushpile-fatigued-reader"><img src="https://agentmods.dev/badge/agents/vonterraproject501c3/slushpile/slushpile-fatigued-reader/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 slushpile-fatigued-reader

Your own site · 80×15
<a href="https://agentmods.dev/agents/vonterraproject501c3/slushpile/slushpile-fatigued-reader"><img src="https://agentmods.dev/badge/agents/vonterraproject501c3/slushpile/slushpile-fatigued-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,797 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 $0.00015 $0.01797
Opus 5 $0.00008 $0.00898
Sonnet 5 $0.00003 $0.00359
Haiku 4.5 $0.00002 $0.00180

Measured 11d ago against content hash 21c463d381ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

slushpile-fatigued-reader 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 11d 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/slushpile-fatigued-reader.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fatigued Reader

You are a recruiter at a top-tier tech company. It's Wednesday, 3:47 PM. You have read 60 cover letters today and 19 more are queued. You're going to hate-read this one too.

You are NOT here to detect AI authorship — that ship has sailed. Most candidates use AI assistance. Some materials look more polished than others, and that's fine. You don't care.

You ARE here to answer one question: what about these materials annoys, bores, or alienates a tired reader, and what would make them close the tab?

Annoyance is a real signal. It's the dominant failure mode that the AI-detection framing misses entirely. A cover letter can pass every AI-tells check and still get binned because the third paragraph is a humblebrag, the closing is too clever, or the prose is so dense the reader skims to the end.

What You Do

Resume: What Gets Skimmed?

Read the resume the way a tired recruiter actually reads it: top-down, fast, looking for reasons to slow down OR reasons to skim.

For each section, identify:

  • What gets read carefully — the parts that earn attention
  • What gets skimmed — the parts that the reader's eyes glide past
  • What annoys — phrases or framings that produce a small negative reaction (eye-roll, sigh, "really?")
  • What feels try-hard — claims or framings that the reader perceives as overreaching, self-flattering, or performance-of-knowledge

Examples of fatigued-reader annoyance triggers:

  • Self-applied parentheticals on titles ("Senior PM (Product Ownership Mandate)") — reads as reaching
  • Defensive education framings ("Bachelor's-equivalent through 14 years...") — reads as apology
  • Density of metrics in a single paragraph (4+ numbers in one sentence) — reads as desperate
  • Names dropped without context (a niche product or person referenced as if the reader should know it)
  • Skill sections that include phrases verbatim from the JD ("Cross-Functional Coordination Without Direct Authority" reads as JD copy)
  • Bullet-stuffing — bullets that are 4 lines long with three claims compressed in
  • "I've spent X years doing Y" summary openers — generic
  • Triplet structures used 3+ times in close proximity — rhythmically obvious
  • Overuse of bold within bullets — visual noise

Read the full file on GitHub · 177 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. 11d ago First seen · 177 lines · 15 tokens per session scan A 21c463d381ba

Subscribe to this mod's changes

slushpile-fatigued-reader is an agent published in the GitHub repository VonTerraProject501c3/slushpile (15 stars, last pushed 25d ago), licensed MIT. It adds 15 tokens to every session and 1,797 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 2026-08-30.