Borrowing it
Nothing to install: this file belongs to easyvibecoding/vibe-resume. 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/easyvibecoding/vibe-resume/main/AGENTS.mdgit clone --depth 1 https://github.com/easyvibecoding/vibe-resumeWrote 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/easyvibecoding/vibe-resume/agents-md)<a href="https://agentmods.dev/instructions/easyvibecoding/vibe-resume/agents-md"><img src="https://agentmods.dev/badge/instructions/easyvibecoding/vibe-resume/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/easyvibecoding/vibe-resume/agents-md"><img src="https://agentmods.dev/badge/instructions/easyvibecoding/vibe-resume/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 | $0.02327 | $0.02327 |
| Opus 5.5 | $0.00931 | $0.00931 |
| Sonnet 5.5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
vibe-resume 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 2mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skill — vibe-resume
This repository ships an Agent Skill
that drives the full extract → aggregate → enrich → render → review → trend
pipeline for an agentic coding CLI. In 2026 the SKILL.md format has become
an industry convention — so a single canonical file works across every host
below with zero content duplication.
Canonical skill file
skills/ai-used-resume/SKILL.md
This file has the frontmatter-typed name and description that hosts use to
decide when to lazy-load the skill. The body follows the Hermes 5-section
convention (When to Use / Quick Reference / Procedure / Pitfalls /
Verification) — recognised by Anthropic's skill-authoring best practices
and natively understood by every host below. Advanced content is bundled
under skills/ai-used-resume/references/
and loaded progressively — strategic-resume.md (company / level axis),
troubleshooting.md (failure-mode playbook), and extending.md (Activity
schema + extractor registration) — per the
agentskills.io spec.
Every other host path (.claude/skills/, .gemini/skills/, .agents/skills/,
.opencode/skills/) is a relative symlink pointing at this canonical
directory. Editing the canonical updates every host in one pass, zero drift.
Plugin-layer manifests (2026 marketplaces)
This repo also ships two plugin manifests so users can install via the Claude Code and OpenAI Codex marketplaces:
.claude-plugin/plugin.json— Claude Code plugin spec.codex-plugin/plugin.json— OpenAI Codex plugin spec
Both auto-discover the bundled skill at skills/ai-used-resume/.
Host discovery matrix
| Host | Discovery path | Our setup |
|---|---|---|
| Claude Code | .claude/skills/<name>/SKILL.md |
../../skills/ai-used-resume symlink. Plugin-layer install via /plugin install easyvibecoding/vibe-resume (uses .claude-plugin/plugin.json) |
| Gemini CLI (Google) | .gemini/skills/<name>/SKILL.md |
../../skills/ai-used-resume symlink |
| GitHub Copilot CLI | reads .claude/skills/ natively (per 2026-04 changelog) |
Zero config — follows the Claude symlink |
| Cursor CLI | reads AGENTS.md + .cursor/rules/ |
This file points at canonical SKILL.md |
| Warp (agentic terminal) | reads .claude/skills/ + .agents/skills/ + .warp/skills/ |
Zero config; both symlinks resolve to canonical |
| OpenAI Codex (CLI, app, IDE ext) | .agents/skills/<name>/SKILL.md (repo) + .codex-plugin/plugin.json for plugin-level |
.agents/skills/ai-used-resume symlink ✓; .codex-plugin/plugin.json shipped ✓ — full plugin install supported |
| OpenClaw (Nov 2025 → 250k ⭐ Feb 2026) | ~/.openclaw/skills/<name>/SKILL.md (user scope only) |
User-scope symlink — see below |
| OpenCode (CLI agent) | .opencode/skills/<name>/ (project) + ~/.opencode/skills/ (user) |
../../skills/ai-used-resume symlink at project scope; user-scope optional |
| Hermes Agent (Nous Research) | repo layout <repo>/skills/<name>/SKILL.md — this IS our canonical path; installed to ~/.hermes/skills/<category>/<name>/; 5-section body is native |
Canonical location. Install via hermes skills tap add easyvibecoding/vibe-resume && hermes skills install easyvibecoding/vibe-resume/ai-used-resume — indexed on skills.sh |
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.
- 2mo ago First seen · 167 lines · 2,327 tokens per session scan A 6a9ff23a5624
vibe-resume AGENTS.md is an instructions file published in the GitHub repository easyvibecoding/vibe-resume (4 stars, last pushed 4mo ago), licensed MIT. It adds 2,327 tokens to every session, about $0.0093 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.