vibe-resume AGENTS.md

vibe-resume AGENTS.md is an instructions file for Codex, OpenCode from easyvibecoding/vibe-resume. It costs 2,327 tokens per session, scanned A, original, MIT.

Project instructions for vibe-resume, a coding-agent project that extracts, organizes, enriches, renders, reviews, and analyzes trends in resume activity. It also defines where the main agent skill and related files live.

In plain words
What is it for?
Use it when changing the vibe-resume agent skill, its reference files, host integrations, or the resume-processing pipeline.
Why use it?
It gives coding agents the project’s expected file structure, workflow, and host-specific links. This avoids duplicating or placing instructions in the wrong locations.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/easyvibecoding/vibe-resume/agents-md
Clone the repo
git clone --depth 1 https://github.com/easyvibecoding/vibe-resume

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for vibe-resume AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/easyvibecoding/vibe-resume/agents-md.svg)](https://agentmods.dev/instructions/easyvibecoding/vibe-resume/agents-md)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 2,327 This file is loaded in full into every session.
When invoked 2,327 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02327 $0.02327
Opus 5 $0.01163 $0.01163
Sonnet 5 $0.00465 $0.00465
Haiku 4.5 $0.00233 $0.00233

Measured 3d ago against content hash 6a9ff23a5624, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

AGENTS.md · 167 lines

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:

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

Read the full file on GitHub · 167 lines

Changes

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.

  1. 3d ago First seen · 167 lines · 2,327 tokens per session scan A 6a9ff23a5624

Subscribe to this mod's changes

vibe-resume AGENTS.md is an instructions file published in the GitHub repository easyvibecoding/vibe-resume (4 stars, last pushed 3mo ago), licensed MIT. It adds 2,327 tokens to every session, about $0.0116 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.