Borrowing it
Nothing to install: this file belongs to PINA-org/PINA. 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/PINA-org/PINA/master/.opencode/skills/skill-sync-checker/SKILL.mdgit clone --depth 1 https://github.com/PINA-org/PINAWrote 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/pina-org/pina/skill-sync-checker)<a href="https://agentmods.dev/skills/pina-org/pina/skill-sync-checker"><img src="https://agentmods.dev/badge/skills/pina-org/pina/skill-sync-checker.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 | $0.00165 | $0.01420 |
| Opus 5 | $0.00082 | $0.00710 |
| Sonnet 5 | $0.00033 | $0.00284 |
| Haiku 4.5 | $0.00016 | $0.00142 |
Grade A, and why
skill-sync-checker 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.
Skill Sync Checker
Skills in this repo describe parts of the codebase by name (function names, class names, module names) rather than by file path. Code drifts — things get renamed, moved, deleted — and the prose in a SKILL.md doesn't automatically follow along. This skill catches that drift and helps fix it, one skill at a time, with the user confirming before anything is written.
Step 0: Confirm this is the right moment
This skill should only ever be invoked when the user's message opens with the exact phrase "I am a pina developer and I need to check skills are updated with code". If you've somehow ended up here without that phrase having been used, stop and ask the user to confirm that's really what they want — this skill's edits touch other skills' documentation and shouldn't run casually.
Step 1: Figure out the scope
Read the rest of the user's message after the trigger phrase for a specific skill name. Two cases:
- A skill is named → skip straight to Step 3 for that skill.
- No skill is named → run the overview scan first (Step 2) and ask the user which flagged skill they want to dig into. Don't deep-check every flagged skill in one pass — this skill fixes one skill at a time, by design, so a single bad suggestion can't cascade across the repo.
Step 2: Overview scan (only when no skill was named)
Run the script in overview mode to see drift counts across every skill:
python3 utils/check_skill_sync.py --skills-dir <path-to-skills-dir> --code-dir <path-to-code-dir> --overview
You'll need to figure out <path-to-skills-dir> and <path-to-code-dir> from
the repo layout — look for a skills/ folder and the actual source folder
(commonly src/, but check first). Present the table to the user in plain
language and ask which skill they'd like to check in depth.
Step 3: Deep check the named skill
python3 utils/check_skill_sync.py --skills-dir <path-to-skills-dir> --code-dir <path-to-code-dir> --skill <skill-name> --json-out /tmp/sync_report.json
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 · 165 tokens per session scan A 045095fe84b1
skill-sync-checker is a skill published in the GitHub repository PINA-org/PINA (790 stars, last pushed 7d ago), licensed MIT. It adds 165 tokens to every session and 1,420 once invoked, about $0.0008 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
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…
graphsignal-profiler
Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.
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.…
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…
ml-engineering
Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training…