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/rumotion/ai-agent-project-template/agents-mdgit clone --depth 1 https://github.com/rumotion/ai-agent-project-templateWrote 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/rumotion/ai-agent-project-template/agents-md)<a href="https://agentmods.dev/instructions/rumotion/ai-agent-project-template/agents-md"><img src="https://agentmods.dev/badge/instructions/rumotion/ai-agent-project-template/agents-md.svg" alt="Measured on agentmods" 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 | $0.01433 | $0.01433 |
| Opus 5 | $0.00717 | $0.00717 |
| Sonnet 5 | $0.00287 | $0.00287 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
ai-agent-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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Canonical Agent Instructions
Single source of truth for all AI agents in this repo. Adapters (GEMINI.md, CLAUDE.md, .clinerules/, .agents/, .github/copilot-instructions.md, .cursor/rules/agents.mdc, .codex/AGENTS.md) only point here.
Startup path — keep context small
- Read this file.
- Read
memory-bank/startup.md. - If resuming work or switching models, also read
memory-bank/handoff.md. - Read
memory-bank/00-index.mdonly to choose additional files. - Load source/docs/workflows/skills only when the task requires them.
Reserve most context for the actual project, not template instructions.
Cross-model continuity
Multiple models share this project (Gemini, Claude, Codex, Cline, Cursor, Copilot). memory-bank/handoff.md is the rolling "where we left off" pointer — update on pause/switch, read on resume. Model routing lives in memory-bank/model-routing.md.
Initialization modes
FAST_INIT (default)
Low-token initialization with verified basics only.
- Read only:
AGENTS.md,memory-bank/startup.md,memory-bank/00-index.md,memory-bank/handoff.md(if resuming), and stack-detection files (package.json,pyproject.toml,requirements.txt,go.mod,Cargo.toml,tsconfig.json,vite.config.*,next.config.*) when present. - Do not read by default:
README.md,docs/,workflows/, skills,references/,assets/,.mcp/, validator scripts. - Update only:
memory-bank/startup.md,memory-bank/handoff.md,memory-bank/projectbrief.md,memory-bank/activeContext.md,memory-bank/progress.md,memory-bank/techContext.md. - Keep unknowns as
TBD. Do not run full-repo audits. Minimize turns and narration.
DEEP_AUDIT (explicit only)
Use when the user asks for full template review, publishing readiness, architecture audit, or broad cleanup. Read deeper docs/workflows/skills/scripts as needed; document findings; propose focused changes.
Escalation rule
Start in FAST_INIT. Escalate only when required facts cannot be verified from allowed files, or the user explicitly asks.
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.
- 4d ago First seen · 102 lines · 1,433 tokens per session scan A 236e9eb52f54
ai-agent-project-template AGENTS.md is an instructions file published in the GitHub repository rumotion/ai-agent-project-template (1 stars, last pushed 14d ago), licensed MIT. It adds 1,433 tokens to every session, about $0.0072 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
agent-commons AGENTS.md
AGENTS.md instructions for jpbaking/agent-commons: This umbrella follows the Portable Agent Authoring guides.
agent-commons CLAUDE.md
Claude Code instructions for jpbaking/agent-commons, a project described as: One canonical source, every coding-agent harness — umbrella for portable Agent Skills, rules, and merge-aware installers (Codex, Claude Code, Antigravity, Cline).
nextarter-tailwind AGENTS.md
AGENTS.md instructions for agustinusnathaniel/nextarter-tailwind, covering next.js: always read docs before coding, ai agent guidance: nextarter-tailwind, 1. mental model for agents, implementation delegation and tooling strategy.
lovable-boilerplate global.instructions.md
Instructions for chihebnabil/lovable-boilerplate, covering react + vite + shadcn/ui template - premium design system, critical rules - read first, never create, always create and essential commands.
claude-code-templates CLAUDE.md
Claude Code instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
FrameCode-VibeWork AGENTS.md
AGENTS.md instructions for Sistema2D/FrameCode-VibeWork, covering agents.md, instruction order, reading-trigger rule, regression rule and when a plan is required.