agentmods.dev

totem: Instructions file for Claude Code

AGENTS.md

totem AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from mmnto-ai/totem. It costs 1,585 tokens per session, scanned C, original, Apache-2.0.

A repository guide that defines how coding agents should work in Totem, a toolkit that checks project rules and records derived project information in Git. It includes required steps before searching, planning, coding, and pushing changes.

In plain words
What is it for?
Use it when developing Totem, checking repository health, searching its knowledge base, running its checks, or following its package, TypeScript, and testing conventions.
Why use it?
It reduces architecture mistakes and catches rule violations before changes are shared.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: SessionStart hook event, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is mmnto-ai/totem's own configuration. It tells Claude Code, Codex and OpenCode how to work on totem itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything totem configures →

not rated 17repo yesterday C scan 1,585 tokens original Apache-2.0
View source ↗ mmnto-ai/totem
Reuse

Borrowing it

Nothing to install: this file belongs to mmnto-ai/totem. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mmnto-ai/totem/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mmnto-ai/totem

Made for: Claude Code, 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 totem AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mmnto-ai/totem/agents-md.svg)](https://agentmods.dev/instructions/mmnto-ai/totem/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mmnto-ai/totem/agents-md"><img src="https://agentmods.dev/badge/instructions/mmnto-ai/totem/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,585 This file is loaded in full into every session.
When invoked 1,585 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01585 $0.01585
Opus 5 $0.00792 $0.00792
Sonnet 5 $0.00317 $0.00317
Haiku 4.5 $0.00159 $0.00159

Measured 7d ago against content hash 65e6473cef45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

totem AGENTS.md scanned grade C with 1 finding 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 7d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- totem-ignore-next-line -->
AGENTS.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Totem: Agent Instructions

Canonical source of truth for how AI coding agents (Claude Code, Gemini CLI, Cursor, etc.) behave in this repo. Per Totem ADR-038 (mmnto-ai/totem-strategy:adr/adr-038-agents-md-standard.md), mmnto-ai/totem consolidates tool-specific instruction files into this single AGENTS.md. Thin CLAUDE.md / GEMINI.md redirects point each tool here.

What Totem is

Totem is a deterministic, git-native governance toolkit — rules you enforce, state you derive, context you query. Lead with enforcement (totem lint + the gate engine), not recall. Derivation (totem status / orient, Tenet 20) and the queryable index serve it.

Session Start Protocol (MANDATORY)

  1. Run totem status for health.
  2. NEVER GUESS ARCHITECTURE. Before modifying any core system, run totem search <system_name>.
  3. Before writing code, call search_knowledge describing what you're changing.
  4. Before planning, query totem-strategy:search_knowledge for ADRs.
  5. Don't push speculative fixes. Run totem lint locally — front-load all checks before the first push.

Essentials

  • pnpm only (never npm/yarn). Use pnpm dlx (never npx). TypeScript strict mode.
  • main is protected. Feature branches + PRs. Never amend commits on feature branches. Use Closes #NNN in PR descriptions.
  • kebab-case.ts files, err (never error) in catch blocks, no empty catches.
  • Named constants for magic numbers. Zod at system boundaries only.
  • NEVER put secrets in config files. .env only.
  • Totem is NOT zero-user. Ships in production for downstream consumers beyond this repo's dogfood. Breaking changes need migration paths, not just "fix in next major."

Totem Workflow

Not mechanically enforced. Follow because they reduce PR bot noise.

  • Before coding: /preflight <issue>. Create a feature branch.
  • Before pushing: pnpm run format → totem lint → totem review → verify compile manifest is current.
  • After merging a PR: totem lesson extract <pr> --yes.
  • NEVER bypass quality gates without a ticket. No --no-verify, totem-ignore, eslint-disable, @ts-ignore, skipped tests, or CI-pacifying ignore patterns. Suppressions need a ticket-ref comment.
  • Open PRs Ready, not Draft. Ready signals review-readiness for the operator's trigger word (strategy#622).
  • Vendor routing. Claude is the default code executor; Gemini stays strategic (proposals, ADRs, audits). Cross-vendor second-opinion fine both ways; "Gemini implement" is not the default.

Read the full file on GitHub · 86 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. 7d ago First seen · 86 lines · 1,585 tokens per session scan C 65e6473cef45

Subscribe to this mod's changes

totem AGENTS.md is an instructions file published in the GitHub repository mmnto-ai/totem (17 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,585 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewProductivityai-agentsast-grepclideveloper-toolsgit-hooks
Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens