yih0nk/job-hunt-agent
Multi-agent recruiting pipeline for Claude Code: scan job sources, score fit, draft tailored applications to a review gate. Never auto-submits.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit yih0nk/job-hunt-agent/agents ./rig-job-hunt-agent/agents $ npx degit yih0nk/job-hunt-agent/skills ./rig-job-hunt-agent/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 yih0nk/job-hunt-agent/skills/outreach .claude/skills/outreach $ npx degit yih0nk/job-hunt-agent/skills/recruit .claude/skills/recruit
$ curl -fsSL --create-dirs -o .claude/agents/applier.md https://raw.githubusercontent.com/yih0nk/job-hunt-agent/main/agents/applier.md $ curl -fsSL --create-dirs -o .claude/agents/matcher.md https://raw.githubusercontent.com/yih0nk/job-hunt-agent/main/agents/matcher.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/yih0nk/job-hunt-agent/main/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/tracker.md https://raw.githubusercontent.com/yih0nk/job-hunt-agent/main/agents/tracker.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"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(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (2)
Subagents (4)
| applier | For auto-draft roles, resolve the real link, tailor the resume via the standing spec, fill the form up to the submit button, and STOP for review. Never submits, never creates accounts, never types pas |
| matcher | Score each queued role 0-100 against the profile using the scoring rubric; pick a resume category; flag ineligible roles. |
| scout | Poll job-listing repos, diff against seen roles, apply hard filters, queue the new ones. |
| tracker | Maintain the application board, detect recruiter replies via the connected email, and surface cross-application patterns. Never checks Applied without confirmation. |
Similar rigs
leavemagic-cyber/earned-confidence
A behavior contract for AI coding agents — every rule added after a real failure. Ships with a verifier agent that cannot edit what it judges.
Pragmatist 3.6k tok ·
uncoalesced/ArgusCouncil
Provenance locked, three agent research harness for any AI coding agent. A Scout downloads sources, an Archivist hashes and quotes them, an Integrator cites them into your paper, report, or dataset. A stdlib Python engine verifies every quo
Minimalist 1.2k tok ·
frontier-infra/adl
Agent Discipline Layer (ADL) — keep a coding agent honest and make it prove its work: layered guardrails + a /goal contract Warden verifies against reality and signs. Claude Code today; Grok/Codex CLI/Pi planned. (formerly Claude Layers)
Pragmatist 1.2k tok ·
j0yen/dotfiles
The claude-self cluster: machine-personal CLAUDE_SELF.md, its SessionStart hook, and the claude-self CLI.
YOLO Cowboy 4.5k tok ·