Borrowing it
Nothing to install: this file belongs to Remotivated/job-hunt-skills. 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/Remotivated/job-hunt-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/Remotivated/job-hunt-skillsWrote 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/remotivated/job-hunt-skills/agents-md)<a href="https://agentmods.dev/instructions/remotivated/job-hunt-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/remotivated/job-hunt-skills/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/remotivated/job-hunt-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/remotivated/job-hunt-skills/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 | $0.00850 | $0.00850 |
| Opus 5.5 | $0.00340 | $0.00340 |
| Sonnet 5.5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
job-hunt-skills 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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Hunt Skills Repository Guidance
This repository ships one shared set of Agent Skills to Codex, Claude Code, and Cowork. Keep plugins/job-hunt-skills/skills/ as the single source of truth; do not duplicate skill bodies under provider-specific directories. The one generated exception is each skill's references/ folder, described below.
The installable plugin is plugins/job-hunt-skills/. Users and the plugin directory receive only that folder, so anything a skill needs at runtime must live inside it and must not reference files outside it. Examples, prompts, tests, CI, and build tooling stay at the repository root.
Before editing workflows
- Read
plugins/job-hunt-skills/skills/_shared/state-layer.mdbefore changing any skill that reads or writesmy-documents/, andplugins/job-hunt-skills/skills/_shared/truth-and-content.mdbefore changing how a skill handles postings, claims, research, or candidate-facing wording. - Edit the shared rule files only in
plugins/job-hunt-skills/skills/_shared/, then runnpm run sync:shared. It copies them into every skill'sreferences/folder, because some hosts let a skill read only files inside its own folder. Skills linkreferences/<file>.md, never../_shared/. Never edit a copy by hand;npm run check:sharedandnpm run test:pluginfail when a copy is missing or out of date. - Preserve truthful-claim rules, workspace confirmation before first write, report numbering, tracker schemas, and resume/CV selection behavior.
- Tracker and report writes go through
plugins/job-hunt-skills/scripts/state.mjswhen Node is available. Rule changes update the state-layer rule list,scripts/fixtures/state/, and the helper together. - Opportunity envelopes and snapshots go through
plugins/job-hunt-skills/scripts/opportunity.mjs(state-layer §13). Its OP rules,scripts/fixtures/opportunity/, and the helper change together. - Plugin-owned and user-owned paths are listed in
plugins/job-hunt-skills/scripts/workspace.mjsand state-layer §0. A new top-level file or folder in the plugin folder must be added to both. - Keep provider-specific installation metadata in the plugin's
.codex-plugin/and.claude-plugin/, or in the repository's.agents/,.claude-plugin/marketplace.json, or.claude/. Keep skill behavior provider-neutral unless a surface genuinely needs different recovery instructions. - Bundled scripts and templates come from the plugin installation root. User documents always come from the confirmed working folder.
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.
- 6d ago Changed · +1 lines · +81 tokens per session 592145f41f0a
- 10d ago Changed · +4 lines · +180 tokens per session af57b7fb7fd5
- 19d ago Changed · +3 lines · +133 tokens per session ddd4411b33f3
- 24d ago Changed · +3 lines · +109 tokens per session c246fcfe3700
- 1mo ago First seen · 38 lines · 347 tokens per session scan A 42fca0f1b14b
job-hunt-skills AGENTS.md is an instructions file published in the GitHub repository Remotivated/job-hunt-skills (16 stars, last pushed 3d ago), licensed MIT. It adds 850 tokens to every session, about $0.0034 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.