What is claude-soul AGENTS.md?

A shared instruction file that defines how AI coding tools should work in a repository. It can serve tools such as Claude Code, Cursor, Gemini CLI, and GitHub Copilot from one source.

Use it to connect multiple coding agents to the same working rules, documentation map, and process for starting and recording work.

It avoids maintaining different rules for every coding tool and provides a fallback process that also works when automation is unavailable.

How tomdwipo/claude-soul configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to tomdwipo/claude-soul. 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/tomdwipo/claude-soul/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tomdwipo/claude-soul

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tomdwipo/claude-soul/agents-md.svg)](https://agentmods.dev/instructions/tomdwipo/claude-soul/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tomdwipo/claude-soul/agents-md"><img src="https://agentmods.dev/badge/instructions/tomdwipo/claude-soul/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,039 This file is loaded in full into every session.

When invoked 2,039 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02039	$0.02039
Opus 5	$0.01019	$0.01019
Sonnet 5	$0.00408	$0.00408
Haiku 4.5	$0.00204	$0.00204

Measured today against content hash 2e031655907c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-soul 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 today.

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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Operating Soul (tool-agnostic)

This is the canonical instruction file for any AI coding agent working in this repo. It is written to the cross-tool AGENTS.md convention so one file serves Claude Code, Cursor, Gemini CLI, Kiro, Copilot, Windsurf, Cline, Aider, and anything else that reads a project instruction file. Nothing here depends on a specific vendor's features — where automation helps it is noted, but the loop works by hand on any tool (graceful degradation).

Point your tool at this file. Most agents auto-load their own filename; make that file be or point to this one (symlink or one-line include) so there is a single source of truth:

Tool File it loads Wire-up

Claude Code CLAUDE.md keep CLAUDE.md, or ln -s AGENTS.md CLAUDE.md

Cursor .cursor/rules/*.mdc add a rule that says "follow AGENTS.md"

Gemini CLI GEMINI.md ln -s AGENTS.md GEMINI.md

Kiro .kiro/steering/*.md a steering file that includes AGENTS.md

GitHub Copilot .github/copilot-instructions.md include/point to AGENTS.md

Windsurf .windsurf/rules/ a rule pointing to AGENTS.md

Cline / Roo .clinerules ln -s AGENTS.md .clinerules

Aider CONVENTIONS.md ln -s AGENTS.md CONVENTIONS.md

Tool	File it loads	Wire-up
Claude Code	`CLAUDE.md`	keep `CLAUDE.md`, or `ln -s AGENTS.md CLAUDE.md`
Cursor	`.cursor/rules/*.mdc`	add a rule that says "follow `AGENTS.md`"
Gemini CLI	`GEMINI.md`	`ln -s AGENTS.md GEMINI.md`
Kiro	`.kiro/steering/*.md`	a steering file that includes `AGENTS.md`
GitHub Copilot	`.github/copilot-instructions.md`	include/point to `AGENTS.md`
Windsurf	`.windsurf/rules/`	a rule pointing to `AGENTS.md`
Cline / Roo	`.clinerules`	`ln -s AGENTS.md .clinerules`
Aider	`CONVENTIONS.md`	`ln -s AGENTS.md CONVENTIONS.md`

🫀 Operating principles (default every session — not optional)

Act from these from the first reply; no trigger word needed. Full set + the engine that grows them: .docs/principles/.

Lookup first — before the first reply, scan .docs/principles/ + .docs/common-issues/ + the current month's .docs/recent-updates/YYYY/MM.md. Act from what's already known; don't re-discover. On any keyword overlap, open the matching detail file before answering.
Explore before acting — a question about a diff/config/topic is exploration; wait for an action verb ("do it", "yes", "build it") before mutating files.
Principle over rule — prefer durable "how to think" over brittle "what to do"; demote to a rule only when a test/build/lint settles it.
Harvest before commit — capture session learnings into .docs/ before any git add/commit. This is gate-enforced by hooks/pre-commit (see below). Don't ask permission; if there are none, opt out consciously (SOUL_NO_LESSONS=1).
Shared over personal — learnings go to git (.docs/), not a tool's private memory, so the next session and any teammate on any tool inherit them.
Atomic & independent — split commits so each is reviewable and ships standalone.
Verify the live system — docs can drift; for anything about real runtime state (flags, prod, infra) check the actual config/runtime, not the doc. Jangan ambil kesimpulan tanpa mencoba.

Read the full file on GitHub · 134 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.

today Changed · +9 tokens per session 2e031655907c
8d ago First seen · 134 lines · 2,030 tokens per session scan A dbac5e682f68

Subscribe to this mod's changes

claude-soul AGENTS.md is an instructions file published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed yesterday), licensed MIT. It adds 2,039 tokens to every session, about $0.0102 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 2026-08-30.

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

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 · 5,153 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

claude-soul: Instructions file for Claude Code