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 linting-and-formattinggit 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/linting-and-formatting)<a href="https://agentmods.dev/skills/nvidia-nemo/megatron-bridge/linting-and-formatting"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/linting-and-formatting/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/linting-and-formatting"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/linting-and-formatting.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.01860 |
| Opus 5 | $0.00022 | $0.00930 |
| Sonnet 5 | $0.00009 | $0.00372 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
linting-and-formatting 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 12d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linting and Formatting
Single source of truth for code style in Megatron Bridge. Read this before writing new code or reviewing PRs.
Style Guides
- Python: Google Python Style Guide
- Shell: Google Shell Style Guide
Target Python 3.10+.
Formatting and Linting
Run before every commit:
uv run ruff check --fix .
uv run ruff format .
Pre-commit hooks run these automatically. If hooks auto-fix files, re-stage and re-run until clean:
git add -u
pre-commit run
# if it auto-fixed files:
git add -u
pre-commit run
Ruff Rules (from ruff.toml)
| Rule | ID | Description |
|---|---|---|
| Line length | — | 119 characters (formatter) |
| Quote style | — | Double quotes |
| f-string without placeholders | F541 | Error |
| Unused local variable | F841 | Auto-removed by --fix |
| Unused import | F401 | Auto-removed by --fix (ignored in __init__.py) |
| Ambiguous variable name | E741 | Error (e.g., l, O, I) |
| Undefined name | F821 | Error |
| Block comment format | E266 | Error (too many #) |
| Import sorting | I | isort-compatible, auto-fixed |
| Public class docstring | D101 | Warning (ignored in test files) |
| Public function docstring | D103 | Warning (ignored in test files) |
Per-file overrides:
__init__.py: F401 and F403 ignored (re-exports expected).test_*.py,*_test.py,tests/*.py: D101 and D103 ignored.
Naming Conventions
| Kind | Convention | Example |
|---|---|---|
| Files | snake_case | model_bridge.py |
| Classes | PascalCase | MegatronModelBridge |
| Functions/methods | snake_case | load_weights_hf_to_megatron |
| Local variables | snake_case | megatron_weights |
| Variables starting with digit | prefix k |
k_99th_percentile |
| Global variables | UPPER_SNAKE + prefix G |
G_LOGGER |
| Constants | UPPER_SNAKE | DEFAULT_HIDDEN_SIZE |
- Avoid shadowing variables from an outer scope.
- Initialize all externally visible class members in the constructor.
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.
- 12d ago First seen · 240 lines · 44 tokens per session scan A b5d33da41870
linting-and-formatting is a skill published in the GitHub repository NVIDIA-NeMo/Megatron-Bridge (906 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 1,860 once invoked, about $0.0002 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…