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/tuwulalo/git-sync-check/git-sync-checknpx skills add tuwulalo/git-sync-check --skill git-sync-checkgit clone --depth 1 https://github.com/tuwulalo/git-sync-checkWhat 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 | $0.00153 | $0.01610 |
| Opus 5 | $0.00077 | $0.00805 |
| Sonnet 5 | $0.00031 | $0.00322 |
| Haiku 4.5 | $0.00015 | $0.00161 |
Grade A, and why
git-sync-check 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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git sync pre-flight check
Several writers can touch the same working tree at once: the user, this session, and often a second Claude session that commits, builds and deploys in parallel. Your memory of the tree is stale the moment another writer acts. The point of this check is to learn the CURRENT state before you act on an outdated picture of it.
If the status is already in context
This skill ships with companion pre-flight scripts (see the repo README)
that many setups run automatically before each turn, injecting a
[git-sync] ... block into context. If you can see a fresh [git-sync]
line for the current prompt, do NOT re-run the commands — the snapshot is
already in front of you. Jump straight to the decision matrix and act on it.
The check
Run this before the first file edit of the task (one tool call):
git -C <repo> fetch origin --quiet
git -C <repo> status --short
git -C <repo> rev-list --left-right --count HEAD...origin/<default-branch>
When the default branch is unknown, resolve it first (falls back to
main):
git -C <repo> symbolic-ref --short refs/remotes/origin/HEAD
Three signals come back: dirty files, ahead count (left), behind count (right).
Decision matrix
| State | What to do |
|---|---|
| Clean tree, 0 ahead / 0 behind | Proceed. Report at most one line: ✅ git: чисто, синхронизировано |
| Behind, tree clean | git pull --rebase origin <branch>, then proceed |
| Ahead only | Note the unpushed commits. If they are complete work, push; if they look mid-flight (another session may still be working), leave them and say so |
| Dirty files | Classify them first — see below. Never blindly commit or revert |
| Dirty AND behind | Classify first, then follow the playbook below |
Operation in progress (.git/MERGE_HEAD, .git/rebase-merge/, .git/rebase-apply/, CHERRY_PICK_HEAD) |
STOP. Someone is mid-merge/rebase. Don't edit, don't commit, don't git rebase --abort on your own initiative — report it and wait for instructions |
Detached HEAD (git symbolic-ref HEAD fails) |
Don't commit onto it silently — a commit there is one GC away from being lost. Create/checkout a branch first, or ask which branch the work belongs on |
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.
- 2d ago First seen · 131 lines · 0 tokens per session scan A 718cd028387b
git-sync-check is a skill published in the GitHub repository tuwulalo/git-sync-check (5 stars, last pushed 2mo ago), licensed MIT. It adds 153 tokens to every session and 1,610 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…