Borrowing it
Nothing to install: this file belongs to cpuguy96/StepCOVNet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cpuguy96/StepCOVNet/master/.cursor/skills/agent-brain-refresh/SKILL.mdgit clone --depth 1 https://github.com/cpuguy96/StepCOVNetWrote 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/skills/cpuguy96/stepcovnet/agent-brain-refresh)<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/agent-brain-refresh"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/agent-brain-refresh.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.01280 |
| Opus 5 | $0.00026 | $0.00640 |
| Sonnet 5 | $0.00011 | $0.00256 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
agent-brain-refresh 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 8d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent brain refresh
Holistic pass over rules, skills, and routing docs so they match disk and stay context-efficient.
What “refresh all rules” means
User phrases refresh all rules, refresh agent brain, and audit rules all invoke this skill (full refresh).
| You do | You do not |
|---|---|
Read every .cursor/rules/*.mdc from disk this turn — re-ground on bodies, not only agent-brain.md or audit stdout |
Assume summarized chat memory is current |
Reconcile rules ↔ skills ↔ AGENTS.md ↔ catalogs; optimize scope and dedupe |
Reload Cursor’s rule injection (alwaysApply is automatic) |
Run audit_agent_brain.py for inventory + drift; you edit catalogs if needed |
Let the script write markdown |
| Report clean — no edits when audit OK and content already agrees | Treat audit-only as sufficient without reading rule files |
| Edit rule/skill/router files only when judgment finds drift, waste, or duplication | Add always-on rules or load multiple AGENTS.md indexes |
Rules are the center; the brain is the scope. “All rules” means each .mdc is read and judged; refresh still covers skills and routing docs that must stay aligned with those rules.
When to run
| Trigger | Action |
|---|---|
| refresh all rules, refresh agent brain, audit rules, brain refresh | Full refresh (below) |
| After steering-correction-promotion | Quick refresh (below) |
| Session end (with agent-self-improvement) | Quick refresh if any brain file changed this session |
| Periodic | Every ~3 steering promotions or when audit_agent_brain.py reports drift |
Architecture (do not duplicate)
| File | Role |
|---|---|
.cursor/rules/*.mdc |
Source of truth for behavior — Cursor loads alwaysApply automatically |
| docs/agents/agent-brain.md | Human catalog — you update during refresh; not script-generated |
| AGENTS.md | Router only — task index; link to catalog |
| .cursor/skills/README.md | Skill index + scoped-rules summary |
scripts/audit_agent_brain.py |
Read-only — prints disk inventory + drift; does not write files |
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.
- 8d ago First seen · 116 lines · 53 tokens per session scan A 82665c8b0eaa
agent-brain-refresh is a skill published in the GitHub repository cpuguy96/StepCOVNet (22 stars, last pushed 13d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,280 once invoked, about $0.0003 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 skills, from other repositories
flow-nexus-neural
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus.
developing-with-streamlit
Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…
physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
lepton-cli
Operate NVIDIA DGX Cloud Lepton through the globally installed lep CLI. Use when the user asks to inspect or manage Lepton workspaces, endpoints/deployments, dev pods, batch jobs, fine-tuning jobs, Ray clusters, Slurm clusters, Dynamo endpoints, storage, secrets, nodes, ingress, templates, logs, authentication, or…
perforatedai
Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks. Triggers: 'Perforate my model' (start interactive setup), 'debug my perforated model' (debug/optimize existing integration), 'load my perforated model for inference' (deploy trained models). Also use when: debugging dendrite…