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/muntello/vibe-project-template/agents-mdgit clone --depth 1 https://github.com/Muntello/vibe-project-templateWhat 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 | $0.02442 | $0.02442 |
| Opus 5 | $0.01221 | $0.01221 |
| Sonnet 5 | $0.00488 | $0.00488 |
| Haiku 4.5 | $0.00244 | $0.00244 |
Grade A, and why
vibe-project-template 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 2d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — {{PROJECT_NAME}}
This is the master file.
CLAUDE.mdandGEMINI.mdare symlinks to this file. Edit ONLYAGENTS.md— changes propagate automatically. NEVER break the symlink structure.
Critical Production Rules
1. Read-Only Mode (ABSOLUTE)
Default behavior on production servers: READ ONLY.
The agent MUST NOT perform any of these actions without explicit user permission:
- Install or remove software
- Modify configuration files (
.env, service units, reverse proxy configs) - Create, modify, or delete files on the server
- Start, stop, or restart any service
- Run database migrations or write to databases
- Create, modify, or remove system users
- Modify firewall rules or network configuration
If a write operation is needed: describe what you want to do, explain why, and WAIT for explicit "yes" from the user.
2. SSH Connection Failures
STOP on first SSH error. Do NOT retry.
Production servers use fail2ban. Repeated failed attempts will ban the IP address. If SSH fails:
- Report the exact error to the user
- Do NOT attempt alternative connections
- Wait for user guidance
3. Database Migrations / Schema Changes
ALWAYS apply migrations to ALL project databases. Projects may use multiple databases (primary, analytics, secondary services, etc.).
Verify which databases exist and run migrations for each one.
4. Configuration Comments
ENGLISH ONLY (ASCII) in all configuration files:
.envfiles- Service unit files (systemd, supervisor, etc.)
- Shell scripts (
.sh) - Reverse proxy configs (nginx, caddy, traefik, etc.)
- Docker/Compose files
- CI/CD pipeline configs
Non-ASCII characters (Russian, Chinese, etc.) cause encoding issues in system services.
5. Timezone Awareness
ALWAYS use the project-configured timezone for:
- Scheduled tasks (cron, task queues, schedulers)
- Log analysis and timestamp comparisons
- Database queries with time filters
Never assume UTC unless the project explicitly uses it.
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.
- 2d ago First seen · 275 lines · 2,442 tokens per session scan A 68fec502d6df
vibe-project-template AGENTS.md is an instructions file published in the GitHub repository Muntello/vibe-project-template (5 stars, last pushed 26d ago), licensed MIT. It adds 2,442 tokens to every session, about $0.0122 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
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.
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.
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.