agent-brain

agent-brain is an agent for coding agents from cpuguy96/StepCOVNet. It costs 0 tokens per session (729 once invoked), scanned A, original, Apache-2.0.

A human-maintained catalogue of the project's Cursor rules and agent skills. Cursor is a code editor that can automatically apply rules to guide an agent's work.

In plain words
What is it for?
Reviewing always-on and file-specific coding rules, checking for drift, and finding guidance for Python code, tests, documentation, and research notes.
Why use it?
It makes those rules easier to audit and helps reveal when the catalogue no longer matches the files that actually exist.

Agent

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 agents/cpuguy96/stepcovnet/agent-brain
Clone the repo
git clone --depth 1 https://github.com/cpuguy96/StepCOVNet

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 agent-brain

README.md
[![agentmods](https://agentmods.dev/badge/agents/cpuguy96/stepcovnet/agent-brain.svg)](https://agentmods.dev/agents/cpuguy96/stepcovnet/agent-brain)
Your own site
<a href="https://agentmods.dev/agents/cpuguy96/stepcovnet/agent-brain"><img src="https://agentmods.dev/badge/agents/cpuguy96/stepcovnet/agent-brain.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 729 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00729
Opus 5 $0.00000 $0.00365
Sonnet 5 $0.00000 $0.00146
Haiku 4.5 $0.00000 $0.00073

Measured 4d ago against content hash 13556b26fabd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-brain 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.

docs/agents/agent-brain.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent brain catalog

Human-maintained inventory of .cursor/rules and skills. Updated by the agent during agent-brain-refresh — not generated by a script.

Verify drift (read-only):

python scripts/audit_agent_brain.py

Cursor loads alwaysApply: true rules automatically. This file documents them for audits — not duplicated into AGENTS.md as prose.

Always-apply rules

File Description
agents-entry.mdc Session entry — route through AGENTS.md to one index only
python-environment.mdc Which Python executable to use — Windows venv (CPU) vs WSL (GPU)
state-and-paths.mdc Refresh repo state before routing edits; portable paths, scratch hygiene, Windows git hygiene

Scoped rules

File Globs Description
design-doc-fields.mdc docs/** Schema versions and per-field rationale in design/plan docs
python-style.mdc **/*.py Python code style — imports, third-party submodules, and docstrings
python-tests.mdc {src,scripts,tests}/**/* Tests and coverage when changing src/, scripts/, or tests/
research-logging.mdc docs/research/** Log EXP/NOTE; add paper citations to PAPER_LEDGER.md + paper.bib
scripts-execution.mdc scripts/** Visible console, TensorBoard stage log trees (AR + DDC placement), logs/_tmp captures, no repo-root tmp

Read the full file on GitHub · 48 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. 4d ago First seen · 48 lines · 0 tokens per session scan A 13556b26fabd

Subscribe to this mod's changes

agent-brain is an agent published in the GitHub repository cpuguy96/StepCOVNet (21 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 729 tokens. 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.