smarter-agent AGENTS.md

smarter-agent AGENTS.md is an instructions file for Codex, OpenCode from AnimaApp/smarter-agent. It costs 331 tokens per session, scanned A, original, MIT.

Project instructions for changing the behavior of Smarter Agent, an AI-agent system. They require narrow changes, conflict checks, simulated comparisons, independent review, and a recorded PASS, PARTIAL, or FAIL result.

In plain words
What is it for?
Use them when changing agent skills, memory rules, prompts, routing, safety boundaries, evidence requirements, escalation rules, or completion rules.
Why use it?
They make behavioral changes easier to review and help distinguish actual improvement from merely editing a file or passing a basic check.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/animaapp/smarter-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/AnimaApp/smarter-agent

Made for: 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 smarter-agent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/animaapp/smarter-agent/agents-md.svg)](https://agentmods.dev/instructions/animaapp/smarter-agent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/animaapp/smarter-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/animaapp/smarter-agent/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 331 This file is loaded in full into every session.
When invoked 331 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00331 $0.00331
Opus 5 $0.00166 $0.00166
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured 3d ago against content hash 1978b52380a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smarter-agent 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 3d 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.

AGENTS.md · 16 lines

What it actually says

Smarter Agent

When you make a meaningful behavioral change to an agent skill, durable memory convention, system prompt, routing policy, safety boundary, classification rule, evidence threshold, escalation rule, or completion rule, load and follow skills/smarter-agent/SKILL.md before claiming the change is effective.

Apply all three pillars:

  1. Minimize: choose the narrowest correct durable home, replace rather than duplicate, and keep the smallest sufficient behavioral contract without cutting safety, authorization, evidence, or necessary context.
  2. Self-check: audit conflicts and falsify the candidate with positive, negative, boundary, and minimization controls.
  3. Simulate improvement: replay immutable baseline and candidate snapshots against the same chronological evidence, compare observable decision outputs, require independent review, then patch, minimize, and replay.

Do not treat a successful file write, grep match, schema check, or self-review as behavioral proof. Preserve a PASS / PARTIAL / FAIL artifact with reviewable snapshots, simulation settings, decision vectors, controls, minimization evidence, and residual limitations.

Keep the skill's scope honest: it is a verification and optimization protocol, not evidence that every mutation path is automatically gated. If any supported writer bypasses validation, report coverage as PARTIAL or FAIL and name the bypass. Do not claim universal enforcement merely because this instruction file or the skill is installed.

The public repository is self-contained and opt-in. These instructions apply when an agent operates inside this repository or when a user explicitly installs or copies them; they do not modify an existing agent runtime by themselves.

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. 3d ago First seen · 16 lines · 331 tokens per session scan A 1978b52380a4

Subscribe to this mod's changes

smarter-agent AGENTS.md is an instructions file published in the GitHub repository AnimaApp/smarter-agent (8 stars, last pushed 15d ago), licensed MIT. It adds 331 tokens to every session, about $0.0017 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.