Borrowing it
Nothing to install: this file belongs to treymorgan/jobsearch-apply-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/treymorgan/jobsearch-apply-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/treymorgan/jobsearch-apply-mcpWrote 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/instructions/treymorgan/jobsearch-apply-mcp/agents-md)<a href="https://agentmods.dev/instructions/treymorgan/jobsearch-apply-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/treymorgan/jobsearch-apply-mcp/agents-md/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/instructions/treymorgan/jobsearch-apply-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/treymorgan/jobsearch-apply-mcp/agents-md.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 | $0.00917 | $0.00917 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
jobsearch-apply-mcp AGENTS.md 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
This workspace manages a job search: finding postings, evaluating fit, drafting CVs and cover letters, and preparing for interviews.
Thin-pointer design (single source of truth)
To avoid duplication and configuration drift across agent runtimes (Claude Code, GitHub Copilot CLI, Codex, Cursor, Gemini CLI and others), all runtimes load the canonical specifications from the files below. Do not duplicate rules into runtime-specific files.
-
Candidate profile. The user's real profile lives in
profile/at the workspace root, which is gitignored. The files under .claude/skills/job-application-assistant/ are blank templates; read them for structure, write answers toprofile/.CLAUDE.mdis the overview template and follows the same rule. -
Search settings. Job titles, target locations, salary floor and title filters live in
jobsearch.config.jsonat the workspace root, also gitignored.jobsearch.config.example.jsonis the tracked template. Never hardcode a preference that belongs there. -
Workflow specifications. The step-by-step instructions for
/setup,/scrape,/rank,/apply,/upskill,/interviewand the rest are in .claude/, under.claude/commands/and.claude/skills/. Treat those files as the single source of truth. -
Portal search tools. Job-board CLIs live under .agents/skills/ in the portable Agent Skills format, with a
SKILL.mdper portal. The/scrapeworkflow in .claude/skills/job-scraper/ orchestrates them. -
MCP server.
mcp_server/jobsearch_mcp/exposes the same data as MCP tools, for use from other clients or a phone. It owns data and state; it does not draft. See docs/TOOLS.md.
Standing rules
- Show question progress during a structured interview. When a workflow
asks a planned sequence of questions -
/setup,/expand, and the gap-filling follow-ups that come after them - work out the full sequence of currently applicable questions, ask them one at a time, and prefix each withQuestion <current> of <total> (<remaining> remaining), whereremainingis the number left after the current one. Exclude questions already answered or made irrelevant; if an answer adds or removes follow-ups, recalculate the total before asking the next question.
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 · 72 lines · 917 tokens per session scan A 1eb08f016853
jobsearch-apply-mcp AGENTS.md is an instructions file published in the GitHub repository treymorgan/jobsearch-apply-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 917 tokens to every session, about $0.0046 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.