~ / rigs / VonTerraProject501c3 / slushpile

VonTerraProject501c3/slushpile

An adversarial job search that gets better as it goes: pool-anchored fit scoring, a resume and cover letter built against the job description, seven agents that try to reject you before a recruiter does, and a profile that keeps what they f

↗ GitHub ★ 23 mit updated 2mo ago project Claude CodeCodexCursorGemini CLI Claude plugin
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~12.9k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit VonTerraProject501c3/slushpile/agents ./rig-slushpile/agents
$ npx degit VonTerraProject501c3/slushpile/skills ./rig-slushpile/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit VonTerraProject501c3/slushpile/.cursor/skills/slushpile .claude/skills/slushpile
$ npx degit <redacted>-review .claude/skills/adversarial-review
$ npx degit <redacted>-builder .claude/skills/application-builder
$ npx degit VonTerraProject501c3/slushpile/skills/explore-experience .claude/skills/explore-experience
$ npx degit VonTerraProject501c3/slushpile/skills/help .claude/skills/help
$ npx degit VonTerraProject501c3/slushpile/skills/job-board-search .claude/skills/job-board-search
$ npx degit VonTerraProject501c3/slushpile/skills/onboard .claude/skills/onboard
$ npx degit VonTerraProject501c3/slushpile/skills/outreach .claude/skills/outreach
$ npx degit VonTerraProject501c3/slushpile/skills/redesign-templates .claude/skills/redesign-templates
$ npx degit VonTerraProject501c3/slushpile/skills/removing-ai-tells .claude/skills/removing-ai-tells
$ npx degit VonTerraProject501c3/slushpile/skills/status .claude/skills/status
$ curl -fsSL --create-dirs -o .claude/agents/aaddrick-voice.md https://raw.githubusercontent.<redacted>-voice.md
$ curl -fsSL --create-dirs -o .claude/agents/slushpile-ats-simulator.md https://raw.githubusercontent.<redacted>-ats-simulator.md
$ curl -fsSL --create-dirs -o .claude/agents/slushpile-contrarian.md https://raw.githubusercontent.<redacted>-contrarian.md
$ curl -fsSL --create-dirs -o .claude/agents/slushpile-fatigued-reader.md https://raw.githubusercontent.<redacted>-fatigued-reader.md
$ curl -fsSL --create-dirs -o .claude/agents/slushpile-hiring-manager.md https://raw.githubusercontent.<redacted>-hiring-manager.md
$ curl -fsSL --create-dirs -o .claude/agents/slushpile-pool-analyst.md https://raw.githubusercontent.<redacted>-pool-analyst.md
$ curl -fsSL --create-dirs -o .claude/agents/slushpile-requirements-analyst.md https://raw.githubusercontent.<redacted>-requirements-analyst.md
$ curl -fsSL --create-dirs -o .claude/agents/slushpile-triage-screener.md https://raw.githubusercontent.<redacted>-triage-screener.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (11)

Subagents (8)

aaddrick-voice
model: sonnet
Voice replication agent that writes text matching aaddrick's documented writing style. Use for generating text, drafting responses, composing messages, or producing any written content that should sou
slushpile-ats-simulator
model: sonnet
Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.
slushpile-contrarian
model: opus
Falsification pass over an application decision. Challenges the hiring manager's synthesis, presses on queue rivalry, conversion calibration, kill criteria, and sunk-cost rationalization. Runs last in
slushpile-fatigued-reader
model: sonnet
Simulates a tired recruiter on application #61 of 80 today. Identifies what annoys, what gets skimmed, what feels try-hard, what would make them close the tab. Replaces "is this AI" framing with "woul
slushpile-hiring-manager
model: opus
Final decision-maker in the adversarial review pipeline. Synthesizes specialist reports + applicant pool analysis into channel-conditional verdicts with conversion-rate estimates, swap tests, and acti
slushpile-pool-analyst
model: opus
Estimates the realistic applicant pool for a specific role at a specific company, then locates the candidate within that distribution. Forces comparative reasoning instead of absolute reasoning. Runs
slushpile-requirements-analyst
model: sonnet
Deep-reads resume and cover letter against JD requirements. Checks min quals, "So What?" audits quantified claims, and evaluates L6+ scope dimensions.
slushpile-triage-screener
model: sonnet
Simulates a fatigued hiring manager's 11-second F-pattern triage scan of a resume. First-pass screener in the adversarial review pipeline.

Cursor rules (1)

slushpile · always

Similar rigs

copied ✓