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/steering-correction-promotion/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/steering-correction-promotion)<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/steering-correction-promotion"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/steering-correction-promotion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/steering-correction-promotion"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/steering-correction-promotion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 58 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00061 | $0.01230 |
| Opus 5 | $0.00030 | $0.00615 |
| Sonnet 5 | $0.00012 | $0.00246 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
steering-correction-promotion 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 10d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steering correction promotion
Run this skill in the same turn as any user steering correction — how you decide, operate, route, log, or commit. Finish with artifact + JRN + brief confirmation.
Also invoked from agent-self-improvement.
Context budget (optimize every promotion)
| Layer | Cost | Use for |
|---|---|---|
alwaysApply: true rules |
Every turn — add sparingly; merge or scope when possible | Routing, portable paths, Python env — only what every task needs |
globs rules |
When matching files are in play | Script execution, docs schema, test patterns |
| Skills | When task matches or agent opens skill | How to decide or run — not live F1 / EXP ids / today's Next action |
| Current phase | Live scoreboard | Next action, blockers, run numbers — EXPERIMENT_LOG.md |
AGENTS.md |
Router only — stay thin | One index table; no procedure prose |
| Self-journal | Receipt — not loaded every turn | Audit trail with Artifact path |
Default: prefer skill section or scoped rule over a new alwaysApply rule. Put live experiment state in Current phase, not in the skill body.
Decision tree
Answer in order; stop at the first fit.
1. Multi-step procedure (train, debug playbook, log EXP)?
→ Extend existing skill OR new skill + skills README row
→ AGENTS.md: new index row ONLY if nothing routes there yet
2. Only matters when editing/running certain paths?
→ Scoped rule (.mdc with globs, alwaysApply: false)
→ Merge into existing scoped rule if same glob family (e.g. scripts/**)
3. Universal but <5 lines and same topic as an existing alwaysApply rule?
→ Merge into that rule — do NOT add a new file
4. Truly required on EVERY turn (safety, entry routing)?
→ alwaysApply rule — LAST RESORT
→ Keep under ~40 lines; regenerate [agent-brain.md](../../../docs/agents/agent-brain.md)
5. One-off preference for this session only?
→ Chat — no JRN unless user says remember this
6. Mechanical bug with a code fix?
→ Code/tests first; optional scoped rule if agents keep repeating it
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.
- 10d ago First seen · 97 lines · 61 tokens per session scan A 96c6903e1c1c
steering-correction-promotion is a skill published in the GitHub repository cpuguy96/StepCOVNet (22 stars, last pushed 16d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,230 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
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…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
wax
Swift framework guidance for Wax on-device memory/RAG. Use when writing Swift code with the public Memory facade, experimental PhotoMemory / VideoMemory, BuiltInMultimodalEmbeddings, embedding providers, retrieval modes, or hybrid search. For agent operators using the Wax MCP server tools, use the separate wax-mcp…