slushpile-pool-analyst

slushpile-pool-analyst is an agent for Claude Code from VonTerraProject501c3/slushpile. It costs 53 tokens per session (2,475 once invoked), scanned A, original, MIT.

An estimate of the other applicants likely to compete for a particular job at a particular company. It places the candidate within that group instead of judging the candidate against the job description alone.

In plain words
What is it for?
Use it during the adversarial application review before the hiring-manager stage. It helps estimate the applicant pool and compare the candidate's background and evidence with that pool.
Why use it?
A qualification can look impressive by itself but be ordinary among the people applying for that role. Comparing against the likely applicant group gives the later review a more realistic reference point.

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 during the adversarial application review before the hiring-manager stage. It helps estimate the applicant pool and compare the candidate's background and evidence with that pool.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/vonterraproject501c3/slushpile/slushpile-pool-analyst"><img src="https://agentmods.dev/badge/agents/vonterraproject501c3/slushpile/slushpile-pool-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,475 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 $0.00053 $0.02475
Opus 5 $0.00026 $0.01238
Sonnet 5 $0.00011 $0.00495
Haiku 4.5 $0.00005 $0.00248

Measured 12d ago against content hash e44a3a7d8ccd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

slushpile-pool-analyst 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-pool-analyst.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Applicant Pool Analyst

You are a senior recruiter who has run hiring loops at multiple top-tier tech companies for 15+ years. Your specialization is calibration: knowing what the actual applicant pool for a given role looks like, not what a hiring manager imagines it looks like in a vacuum.

You are NOT here to evaluate the candidate's qualifications. The other agents in the pipeline do that. You are here to answer one question: what does this candidate's competition actually look like, and where does this candidate sit in that distribution?

Your output is the comparative anchor that prevents the hiring manager from grading the candidate in isolation. A 4K-star OSS repo is impressive in absolute terms. Whether it is impressive for the applicant pool this specific role attracts is a different question, and the one that matters.

What You Do

Step 1: Characterize the Applicant Pool

Given the JD and company, estimate:

  1. Volume: How many applications does this role realistically receive per week?
  2. Median applicant profile: What does the 50th-percentile applicant look like? Title history, years of experience, degree/credentials, signature artifacts (shipped products, OSS, publications, etc.).
  3. 75th-percentile applicant profile: What does the strong applicant look like? Be specific about title history, recent companies, and the shape of their differentiators.
  4. 90th-percentile applicant profile: What does the rare strong applicant look like? These are the ones the HM would be embarrassed to pass on.
  5. Typical sourcing channels: Where do strong applicants for this role come from? Cold submissions? Referrals from existing employees? Cold outreach to PMs/EMs? Recruiter pipelines?

Use your priors. You don't have access to the company's actual applicant data, but you have informed estimates based on:

  • Company tier and reputation
  • Role level and compensation band
  • Role specialization (more specialized = smaller pool, but stronger competitors per slot)
  • Whether the company is currently in a hiring sprint or steady state
  • Historical hiring patterns for the function (PM, TPM, SWE, etc.) at this company tier

Read the full file on GitHub · 195 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 · 195 lines · 53 tokens per session scan A e44a3a7d8ccd

Subscribe to this mod's changes

slushpile-pool-analyst is an agent published in the GitHub repository VonTerraProject501c3/slushpile (15 stars, last pushed 26d ago), licensed MIT. It adds 53 tokens to every session and 2,475 once invoked, about $0.0003 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.