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/soupernerd/marge-simpson/agents-mdgit clone --depth 1 https://github.com/soupernerd/marge-simpsonWrote 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/soupernerd/marge-simpson/agents-md)<a href="https://agentmods.dev/instructions/soupernerd/marge-simpson/agents-md"><img src="https://agentmods.dev/badge/instructions/soupernerd/marge-simpson/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 | $0.01408 | $0.01408 |
| Opus 5 | $0.00704 | $0.00704 |
| Sonnet 5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
marge-simpson 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Assistant Operating Rules
Priority: correctness > safety > minimal diffs > speed
Core Principle
User prompt = Approval to execute.
When a user asks you to do something, DO IT. Don't announce it and stop. Don't ask for confirmation. Execute, then report what you did.
Non-Negotiable Rules
- NEVER claim verification passed without raw output
- NEVER skip expert load in Full mode
- NEVER leave work incomplete without stating what remains
- ALWAYS execute what you say you will execute in the same response
- ALWAYS declare MODE before first edit (inline with execution, not as a stopping point)
Mode Declaration
Before your first file edit, output:
+---------------------------------------------+
| MODE: [Lite | Full] |
| ID: [MS-#### | N/A] |
| REASON: [one sentence] |
+---------------------------------------------+
Then immediately execute. The MODE block is for visibility, not a checkpoint.
Scope
marge-simpson/ is tooling, not the target. Work/auditing happens OUTSIDE this folder. UNLESS .meta_marge exists and marge is being worked on.
- Track findings →
marge-simpson/system/tracking/ - Never create files from this folder elsewhere
Task Modes
| Trigger | Mode |
|---|---|
| Single-line typo, comment, format (no behavior change) | Lite |
| Feature, refactor, audit, multi-file, behavior change | Full |
Lite → Full escalation: files > 1, lines > 10, behavior changes, tests affected.
When in doubt → Full mode.
Core Rules
- Verify before acting → Read files, search codebase. Never assume.
- Root cause only → No band-aids
- Minimal surface → Fewest files, fewest lines
- Document reasoning → Capture why
- No hardcoded secrets → Environment variables only
- State uncertainty → Declare: checked, known, unknown
Just-in-Time Context
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 · 184 lines · 1,408 tokens per session scan A 69afca6b7b2e
marge-simpson AGENTS.md is an instructions file published in the GitHub repository soupernerd/marge-simpson (45 stars, last pushed 6mo ago), licensed MIT. It adds 1,408 tokens to every session, about $0.0070 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.
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.