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 agentmods add skills/nvidia-nemo/megatron-bridge/bump-dependencynpx skills add NVIDIA-NeMo/Megatron-Bridge --skill bump-dependencygit 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/bump-dependency)<a href="https://agentmods.dev/skills/nvidia-nemo/megatron-bridge/bump-dependency"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/bump-dependency.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00066 | $0.03291 |
| Opus 5 | $0.00033 | $0.01646 |
| Sonnet 5 | $0.00013 | $0.00658 |
| Haiku 4.5 | $0.00007 | $0.00329 |
Grade A, and why
bump-dependency 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 6d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bump Dependency
End-to-end workflow for shipping a dependency bump in Megatron Bridge. Optimised for the case where TE, MCore, or another GPU-heavy pin moves forward — which often surfaces flakes that have to be quarantined before the PR can land.
The pipeline is always: edit → relock → push → /ok to test → watchdog → quarantine on red → re-trigger → repeat until green.
When to reach for this skill
- Bumping a git-source pin in
pyproject.tomloverride-dependencies(e.g.transformer-engine @ git+...@<ref>). - Bumping the
3rdparty/Megatron-LMsubmodule. - Any change that touches
uv.lockand needs the full L0 + L1 matrix to prove out before merge.
For pure dep additions/removals without a CI loop, the
build-and-dependency skill is enough.
Required context
Read first, then follow the steps below:
- @CONTRIBUTING.md — PR title/label policy, DCO sign-off
- @skills/build-and-dependency/SKILL.md —
uv lockmechanics, container choice - @skills/cicd/SKILL.md — how
copy-pr-botand/ok to testwork - @skills/testing/SKILL.md —
active/vsflaky/directory layout,git mvquarantine recipe
Step 1 — Worktree and edit
Create a worktree off main per @CLAUDE.md. Then, before any uv lock:
git submodule update --init 3rdparty/Megatron-LM
The submodule must be initialised in the worktree or uv lock errors
with "not a Python project" on the MCore path.
Edit the pin. For TE the canonical knob is the override line in
pyproject.toml:
override-dependencies = [
...
"transformer-engine @ git+https://github.com/NVIDIA/TransformerEngine.git@<new-ref>",
...
]
Use a branch name (release_v2.15) only when you want to track a
moving tip; use a full SHA for reproducibility. TE branches use
release_vX.Y (underscore), not release/vX.Y. Verify with
git ls-remote https://github.com/NVIDIA/TransformerEngine.git.
Step 2 — Regenerate the lockfile
Run uv lock inside the project container per
@skills/build-and-dependency/SKILL.md "Regenerating uv.lock". Then
confirm only the intended packages moved:
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.
- 6d ago First seen · 324 lines · 66 tokens per session scan A 4f93bdce75b4
bump-dependency is a skill published in the GitHub repository NVIDIA-NeMo/Megatron-Bridge (901 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 3,291 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
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
atmos-cache
Atmos caching: CI cache configuration and commands, GitHub Actions cache integration, Terraform registry cache mirror/list/prune/stats/trust, and cache modernization guidance.
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.