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 skills add palashjain95/jobhunter --skill personalizegit clone --depth 1 https://github.com/palashjain95/jobhunterWrote 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.
[](https://agentmods.dev/skills/palashjain95/jobhunter/personalize)<a href="https://agentmods.dev/skills/palashjain95/jobhunter/personalize"><img src="https://agentmods.dev/badge/skills/palashjain95/jobhunter/personalize/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.
<a href="https://agentmods.dev/skills/palashjain95/jobhunter/personalize"><img src="https://agentmods.dev/badge/skills/palashjain95/jobhunter/personalize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.02152 |
| Opus 5 | $0.00039 | $0.01076 |
| Sonnet 5 | $0.00015 | $0.00430 |
| Haiku 4.5 | $0.00008 | $0.00215 |
Grade A, and why
personalize 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/personalize
Usage
/personalize # Auto-detect: new setup or update menu
/personalize quick # First-time: fast setup from resume
/personalize full # First-time: complete 9-step walkthrough
/personalize stories # Update: add or edit stories only
/personalize profile # Update: change targets, pillars, situation
/personalize negotiation # Update: adjust comp targets or priorities
/personalize framework # Update: revise writing framework
Before Anything Else: Detect State
Check if knowledge/profile.md exists.
If it does NOT exist → First-Time Setup (quick or full mode below).
If it DOES exist → Returning User. Read knowledge/profile.md and show:
Welcome back, [Name]! Here's your current setup:
knowledge/
├── profile.md ✅ [pillars summary]
├── resume/ ✅ / ❌
├── stories/ ✅ [N] stories
├── frameworks/ ✅ [framework name]
├── voice/ ✅ / ⏭️ Not set up
├── negotiation/ ✅ / ⏭️ Not set up
└── values/ ✅ / ⏭️ Not set up
What would you like to update?
- "Add a new story" → I'll walk you through STAR format
- "Update my targets" → Change target roles or companies
- "Change my comp range" → Update negotiation preferences
- "Redo everything" → Full setup from scratch
- Or tell me what's changed and I'll figure out which section to update
If the user specified a section in their command (e.g., /personalize stories), skip the menu and go directly to that section.
When updating an existing section, read the current file first, show what's there, then ask what to change. Never overwrite without showing current state.
How It Works (First-Time Setup)
┌─────────────────────────────────────────────────────────┐
│ PERSONALIZE │
├─────────────────────────────────────────────────────────┤
│ QUICK (5 min): Resume → auto-generate everything │
│ FULL (20 min): Walk through 9 steps conversationally │
│ │
│ Step 1: Resume → knowledge/resume/ │
│ Step 2: Profile → knowledge/profile.md │
│ Step 3: Stories (STAR) → knowledge/stories/ │
│ Step 4: Writing style → knowledge/frameworks/ │
│ Step 5: Voice samples → knowledge/voice/ (optional) │
│ Step 6: Negotiation → knowledge/negotiation/ │
│ Step 7: Values → knowledge/values/ (optional) │
│ Step 8: Pipeline setup → pipeline-data.md │
│ Step 9: Daily check-in → scheduled tasks (optional) │
│ │
│ Result: Fully personalized recruitment team │
└─────────────────────────────────────────────────────────┘
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 242 lines · 77 tokens per session scan A 85368765deb3
personalize is a skill published in the GitHub repository palashjain95/jobhunter (2 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 2,152 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
phx-mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
quick
Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
phx-freeze
Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…