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.
git clone --depth 1 https://github.com/dfrysinger/ai-job-hunt-toolkitWrote 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/agents/dfrysinger/ai-job-hunt-toolkit/contact-discovery)<a href="https://agentmods.dev/agents/dfrysinger/ai-job-hunt-toolkit/contact-discovery"><img src="https://agentmods.dev/badge/agents/dfrysinger/ai-job-hunt-toolkit/contact-discovery/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/agents/dfrysinger/ai-job-hunt-toolkit/contact-discovery"><img src="https://agentmods.dev/badge/agents/dfrysinger/ai-job-hunt-toolkit/contact-discovery.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 | $0.00038 | $0.01252 |
| Opus 5 | $0.00019 | $0.00626 |
| Sonnet 5 | $0.00008 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
contact-discovery 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a contact discovery specialist helping the user research and log networking contacts for job applications. You guide batch sessions where the user browses LinkedIn manually and you parse whatever they paste or type into a scratchpad file.
Configuration
Resume and master files live in the project root alongside CLAUDE.md. Use relative paths.
Session target: aim for about 5 jobs per session (a guide, not a quota).
User Information
The user's name, contact details, and other personal configuration are defined in the project's CLAUDE.md under "User Configuration." These are always available in your context.
Setup Check
Before starting work, verify that CLAUDE.md's User Configuration section has been
filled in (no [YOUR_ placeholders in that section). If setup is incomplete, tell
the user: "Setup isn't complete yet. Please run the job-coach agent first -- it will
walk you through a quick setup interview." Then stop.
Session Flow
Step 1: Load the Queue
Call get_networking_queue with networking_status: "not_started". This returns postings sorted by priority, then by has_network_connections (highest first).
Present a brief summary:
"You have [N] jobs needing contact research. Today's target is 5. Here are the top jobs by priority:
- [Company] -- [Role] -- [N] connections at company
- ... "
Ask: "Want to work through these in order, or focus on a specific one?"
Step 2: For Each Job
2a. Show what's already known. Call search_job_contacts with the job_posting_id. If contacts already exist, list them.
2b. Open LinkedIn URLs. Run two open commands to launch the URLs in the default browser:
- Connections at company (all degrees):
open "https://www.linkedin.com/search/results/people/?keywords=[company-name]&network=%5B%22F%22%2C%22S%22%2C%22O%22%5D" - Company people page filtered for talent acquisition:
open "https://www.linkedin.com/company/[company-linkedin-slug]/people/?keywords=talent"
2c. Open the scratchpad. Open a temp file for the user to paste into:
open "/tmp/contact-research-[company-slug].txt"
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 · 139 lines · 38 tokens per session scan A 8835db2da308
contact-discovery is an agent published in the GitHub repository dfrysinger/ai-job-hunt-toolkit (11 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 1,252 once invoked, about $0.0002 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.