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.
npx agentmods add instructions/akbardevop/ai-job-agent/claude-mdgit clone --depth 1 https://github.com/AkbarDevop/ai-job-agentWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.04101 | $0.04101 |
| Opus 5 | $0.02050 | $0.02050 |
| Sonnet 5 | $0.00820 | $0.00820 |
| Haiku 4.5 | $0.00410 | $0.00410 |
Grade B, and why
ai-job-agent CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
Skills find this repo via `$AI_JOB_AGENT_ROOT` → `~/.claude/skills/ai-job-agent/REPO_PATH` → `~/ai-job-agent`. Set the env var or rerun `install.sh` from a non-default clone location. How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Job Application Agent - Claude Code Instructions
Overview
This is a job application automation toolkit. It automates filling and submitting applications on LinkedIn Easy Apply, Greenhouse, Lever, Jobvite, and Ashby, plus email triage and Google Sheets tracking.
Two ways to drive it:
- Bundled skills (recommended) — type
/job-coach,/job-apply,/job-evaluate,/job-cv,/job-track,/job-triage,/job-status,/job-outreach,/job-followup,/job-dashboard,/job-interview,/job-patterns, or/job-setupin any Claude Code session. Each skill wraps the scripts below and renders results as a markdown table. Install once withbash skills/install.sh. - Raw scripts — call the Node.js / Python scripts in
scripts/directly from your terminal (documented below).
Bundled Skills
Installed by bash skills/install.sh (symlinks them into ~/.claude/skills/). Each skill's prompt lives at skills/<name>/SKILL.md — read it to see exactly what the agent does.
| Skill | Wraps | Output |
|---|---|---|
/job-coach |
the persona — intake, research, slate, dispatch | target-role slate + next-move suggestions; persists to config/search-plan.md |
/job-setup |
wizard.sh equivalent — but in chat |
conversational onboarding, auto-reads user files, writes configs, registers skills |
/job-apply <url> [--submit] |
5 ATS fillers (auto-routed by URL host) | result table: platform, outcome, exit code |
/job-track [sync] |
local CSV + google-sheet-sync.py |
counts-by-status table + recent activity |
/job-triage [query] |
outlook-triage.js |
classified-email counts + preview table, step-through extract/mark-read |
/job-status <updates.json> |
tracker-status-update.py |
before/after diff, confirmation prompt, result summary |
/job-outreach <target> |
send-cold-email.js + Claude (the agent drafts) |
research → draft preview → dry-run → send → log to outreach-log.csv |
/job-followup [send] |
outreach-log.csv + send-cold-email.js |
urgency table (overdue/due/soon/waiting) + optional step-through send |
/job-dashboard [live] |
job-dashboard.mjs (zero deps) |
ANSI tables: applications + outreach + follow-ups. Snapshot in chat or npm run dashboard for live TUI |
/job-evaluate <url> |
WebFetch + 7-block A-G rubric + /job-cv chain + tracker append |
structured eval report at reports/<date>-<company>-<role>.md + tailored PDF + tracker row |
/job-cv <jd> |
scripts/generate-tailored-cv.mjs (Playwright Chromium → PDF) |
Claude rewrites base CV (no invention) → ATS-friendly PDF at output/cv-<company>-<date>.pdf |
/job-interview <company> |
application-tracker.csv + WebSearch + WebFetch |
company snapshot + 10-15 likely Qs + 5-8 STAR stories from real projects + 5 smart asks + 3 red flags |
/job-patterns |
application-tracker.csv + outreach-log.csv |
rejection diagnostics (by ATS / time-to-rej / geography / role-type / day-of-week) + 3 actionable fixes |
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.
- yesterday First seen · 236 lines · 4,101 tokens per session scan B c4c149d661af
ai-job-agent CLAUDE.md is an instructions file published in the GitHub repository AkbarDevop/ai-job-agent (53 stars, last pushed 4mo ago), licensed MIT. It adds 4,101 tokens to every session, about $0.0205 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
jobseek AGENTS.md
Instructions for colophon-group/jobseek, covering agents.md — jobseek, project overview, repository structure, commands and ops routines (codex-first, claude-compatible).
Resume-Builder CLAUDE.md
Instructions for jananthan30/Resume-Builder, covering resume builder - project context, quick start, option 1: claude code custom commands (recommended), resume only - dual optimized and cover letter only.
Resume-Builder AGENTS.md
Instructions for jananthan30/Resume-Builder, covering resume builder - codex context, codex plugin surface, native four-role resume team and operating rules.
jobxhunter AGENTS.md
Instructions for soheilfallah/jobxhunter, covering agents.md, where the content comes from, start here, the pipeline and running the deterministic scripts.
openhire CLAUDE.md
Claude Code instructions for gzchenhao/openhire, covering claude.md — openhire 工作约定（每个会话必读）, 新会话恢复指引（开工前先做这三步）, 发布状态（v0.1 已上线 + 上架官方 registry · 2026-07-15）, 常设工作制度（持续遵守） and 三条隐私红线（ci 强制，永不可破）.
please-hire-me CLAUDE.md
Instructions for alecswang/please-hire-me, covering please-hire-me — agent entry point (read this first), setup, step by step, rules during onboarding, what this is and repo layout.