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 skills add NVIDIA-NeMo/Megatron-Bridge --skill nemo-mbridge-perf-nsys-analysisgit clone --depth 1 https://github.com/NVIDIA-NeMo/Megatron-BridgeWrote 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/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-nsys-analysis)<a href="https://agentmods.dev/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-nsys-analysis"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-nsys-analysis/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/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-nsys-analysis"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-nsys-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
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 →
- medium Agent Snooping · line 314 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 315 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 316 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 317 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 318 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 319 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00118 | $0.03587 |
| Opus 5 | $0.00059 | $0.01793 |
| Sonnet 5 | $0.00024 | $0.00717 |
| Haiku 4.5 | $0.00012 | $0.00359 |
Grade A, and why
nemo-mbridge-perf-nsys-analysis 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 11d 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nsight Systems Analysis for Megatron Bridge
Turn an Nsight Systems trace into a critical-path diagnosis and a ranked, evidence-backed optimization plan. Treat the profile as timing evidence, not as a list of long kernels to optimize.
Use these principles throughout:
- Use the performance model as the ceiling and the profiler as the agenda.
- Compute wall time with interval unions, never summed stream or kernel time.
- Inventory the active communication backend; distributed work is not necessarily NCCL-only.
- Treat visible communication and copies as coincident work until a dependency proves that they blocked compute.
- Separate a measured phenomenon from its source-level root cause.
- Report a gain ceiling from recoverable critical-path time; do not invent a likely gain without comparable measured evidence.
Establish the analysis contract
Record before calculating:
- Trace path, rank id, hostname, GPU, Nsight Systems version, Bridge and MCore revisions, container, and whether CUDA graphs were enabled.
- Model, precision, sequence length, micro/global batch sizes, task, and the measured step definition.
- TP, PP, VPP, CP, EP, ETP, and DP sizes plus the rank-to-stage mapping.
- The steady-state iteration range, number of analyzed iterations, and same-run unprofiled reference steps when available.
- Capture diagnostics, hardware- versus software-instrumented mode, and any warning that events may be incomplete.
- Whether source for the exact profiled revision is available.
Never infer a rank id or pipeline stage from a filename. Never compare ranks that hold different model parts as if they performed identical work.
Preserve the input report. Export a separate SQLite file when necessary:
nsys export --type sqlite -o profile.sqlite profile.nsys-rep
Check the available tables before using a query because schemas vary by Nsight version. Read references/sql-recipes.md for portable inspection queries and references/pitfalls.md before making a bottleneck claim.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 352 lines · 118 tokens per session scan A eef76abb5d6d
nemo-mbridge-perf-nsys-analysis is a skill published in the GitHub repository NVIDIA-NeMo/Megatron-Bridge (905 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 3,587 once invoked, about $0.0006 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.