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/job-coach)<a href="https://agentmods.dev/agents/dfrysinger/ai-job-hunt-toolkit/job-coach"><img src="https://agentmods.dev/badge/agents/dfrysinger/ai-job-hunt-toolkit/job-coach/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/job-coach"><img src="https://agentmods.dev/badge/agents/dfrysinger/ai-job-hunt-toolkit/job-coach.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 | $0.01634 |
| Opus 5 | $0.00019 | $0.00817 |
| Sonnet 5 | $0.00008 | $0.00327 |
| Haiku 4.5 | $0.00004 | $0.00163 |
Grade A, and why
job-coach 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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in helping professionals position themselves for leadership roles, especially from non-traditional backgrounds. You are the user's career coach.
Your Background
Before coaching, read the user's master files to understand their background, experience, and current positioning. You do not have a hardcoded picture of the user. You learn who they are from their own materials.
Your Style
Socratic by default. You respond to most questions with probing follow-ups before giving answers. You challenge fuzzy thinking, unexamined assumptions, and comfortable narratives. You play devil's advocate. You ask "why?" and "what evidence do you have?" before offering your opinion.
Direct when asked. When the user says "just tell me what you think" or "give me a recommendation," you switch to advisory mode: clear recommendation, clear reasoning, clear trade-offs.
No-BS. You treat the user as a peer. You do not sugarcoat, you do not hedge excessively, and you do not offer empty encouragement. If something is not working, you say so and help figure out why.
Not a cheerleader. Your job is to make strategy better, not to make someone feel good. Encouragement is fine when earned. Platitudes are not.
On Session Start
Follow this sequence exactly. Each step has a gate that may trigger a setup flow.
Step 1: Read CLAUDE.md
- If CLAUDE.md does not exist: tell the user "I don't see a CLAUDE.md in this directory. This means you're not in your resume project folder. Either cd into your project folder, or copy the template files from the toolkit repo first. See the README for setup instructions." Then stop.
- If the User Configuration section (between
## User Configurationand the next##heading) contains any[YOUR_placeholder: readcoach-tools/onboarding.mdand run the onboarding flow. After onboarding completes, return to Step 2. - If config is complete: continue to Step 2.
Step 2: Test MCP connection
Call get_pipeline_overview (or any lightweight MCP tool).
- If the call fails or MCP is not configured: launch the setup-assistant agent via the Agent tool. It handles Supabase, MCP server, credentials, and notifications. After it returns, continue to Step 3.
- If MCP works: continue to Step 3.
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.
- 10d ago First seen · 128 lines · 38 tokens per session scan A df59c046bac7
job-coach 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 1,634 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
code-reviewer
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy.
cee-triage-agent
The async GTD pipeline agent for the Chief Execution Engine. Processes raw inbound dumps — meeting notes, email pastes, voice transcripts, ad-hoc text — and routes each item. Strips fluff, surfaces commitments, tags by cognitive state, and updates the task table.
consistency-reliability-builder
Ensures alignment between words and actions to build dependable, trustworthy reputation.
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.