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.
npx agentmods add instructions/chentao326/vibe-code/agents-mdgit clone --depth 1 https://github.com/chentao326/vibe-codeWhat 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 | $0.01784 | $0.01784 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
vibe-code 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- vibe-code CLAUDE.md — 94% identical, 13 lines differ
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Vibe Code
What this is
vibe-code turns vibe coding into a calibrated experiment: assess task → blind prediction → execute → retro → evolve the rubric. It is a Codex skill collection (13 skills, 7 protocols, adapters, hooks, templates).
The SKILL.md at project root is the master router; each skills/vibe-*/SKILL.md is a sub-skill workflow.
Directory map
skills/vibe-{init,assess,retro,bump,status,score,score-blind,seed,recommend,trends,profile,learn-from,migrate}/SKILL.md
shared-references/ — 7 protocols (blind-prediction, bump-validation, observation-lifecycle, etc.)
templates/ — 7 templates (rubric, task, prediction, retro, benchmark, status, prompt-patterns)
adapters/ — data collectors (git-stats, time-tracker, lint-collector)
hooks/ — prediction-immutability.sh, session-start.sh, log-event.sh + JSON configs
tasks/ — user task descriptions
predictions/ — immutable blind prediction logs
retros/ — per-task retro data
tests/ — test scripts for adapters/hooks/tools
tools/ — accuracy-curve.py
migrations/ — schema migration registry
starter-rubrics/ — rubric presets per project type
Three non-negotiable principles
- Blind prediction: Predictions written BEFORE coding, immutable once saved. Full spec:
shared-references/blind-prediction-protocol.md. - Bump = full rescore: Changing the rubric formula requires rescoring all historical tasks. Ranking consistency >= 80% + cross-model audit. Spec:
shared-references/bump-validation-protocol.md. - Rubric is a workbench, not a museum: Disproven observations get deleted, absorbed ones get deleted. Git history is the archive. Spec:
shared-references/observation-lifecycle.md.
Core convention: one task, three files, one hash
tasks/<date>_<hash>_<short>.md — task description
predictions/<date>_<hash>_<short>.md — blind prediction (immutable prediction section)
retros/<date>_<hash>_<short>/ — retro data
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.
- yesterday First seen · 170 lines · 1,784 tokens per session scan A 4cc232e1061e
vibe-code AGENTS.md is an instructions file published in the GitHub repository chentao326/vibe-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,784 tokens to every session, about $0.0089 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
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.
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).
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.