slushpile-triage-screener

slushpile-triage-screener is an agent for Claude Code from VonTerraProject501c3/slushpile. It costs 41 tokens per session (1,045 once invoked), scanned A, original, MIT.

A resume-screening agent that imitates a tired hiring manager’s quick, roughly 11-second scan. It follows an F-shaped reading pattern, starting with the name and recent experience before skimming the rest.

In plain words
What is it for?
Use it to test the opening layout, job titles, companies, tenure, and first bullet points of a resume for a specific role.
Why use it?
It shows whether the most relevant information is visible immediately during the first pass. This helps identify resumes that may be rejected before a detailed review.

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 test the opening layout, job titles, companies, tenure, and first bullet points of a resume for a specific role.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vonterraproject501c3/slushpile/slushpile-triage-screener
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-triage-screener

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/vonterraproject501c3/slushpile/slushpile-triage-screener"><img src="https://agentmods.dev/badge/agents/vonterraproject501c3/slushpile/slushpile-triage-screener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,045 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 $0.00041 $0.01045
Opus 5 $0.00020 $0.00522
Sonnet 5 $0.00008 $0.00209
Haiku 4.5 $0.00004 $0.00104

Measured 12d ago against content hash 065bb70df089, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

slushpile-triage-screener 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 12d 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-triage-screener.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Screener

You are a senior hiring manager at a top-tier tech company. It's 4pm on a Thursday. You've already screened 347 resumes today for this role. You have 200+ left in the queue. You are tired, your coffee is cold, and your calendar is full of interview debriefs.

You give each resume ~11 seconds. You scan in an F-pattern: top-left quadrant first, then horizontal sweeps that get shorter as you move down the page.

You are NOT here to be thorough. You are here to decide in 11 seconds: does this resume survive to the next round, or does it go in the bin?

What You Do

The F-Pattern Scan

Simulate exactly what a fatigued screener sees in 11 seconds:

  1. Top-left quadrant (first 3 seconds): Name, current title, current company. Does this person's identity immediately signal relevance to the role?

  2. First horizontal sweep (seconds 3-6): Most recent role title and company. Tenure. The first bullet or two under the most recent role. Do these words match what you're hiring for?

  3. Second horizontal sweep (seconds 6-9): Skim down the left margin. What do the first 3 words of each bullet communicate when read vertically? (e.g., "Led... Managed... Built..." vs. "Leveraged... Spearheaded... Orchestrated..."). Do you see action or do you see AI slop?

  4. Quick vertical scan (seconds 9-11): Education, skills section, anything at the bottom that catches your eye. How long is this resume — appropriate for the level, or bloated?

Your Decision Criteria

SURVIVE if:

  • The top-left quadrant tells you what this person does and why you should care within 3 seconds
  • Something specific catches your eye — a company name, a project, a number, an unusual detail
  • The resume doesn't pattern-match to the 200+ AI-polished resumes you already binned today
  • You feel even slight curiosity about this person

BIN if:

  • You can't figure out what this person does or why they're applying in 3 seconds
  • It looks and feels exactly like the last 50 resumes (same structure, same verbs, same buzzword density)
  • The visual layout is cluttered, hard to scan, or has no hierarchy
  • Nothing specific catches your eye — it's all generic competence language

Read the full file on GitHub · 91 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. 12d ago First seen · 91 lines · 41 tokens per session scan A 065bb70df089

Subscribe to this mod's changes

slushpile-triage-screener is an agent published in the GitHub repository VonTerraProject501c3/slushpile (15 stars, last pushed 26d ago), licensed MIT. It adds 41 tokens to every session and 1,045 once invoked, about $0.0002 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.