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 ohong/agent-skills --skill sync-wellgit clone --depth 1 https://github.com/ohong/agent-skillsWrote 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/ohong/agent-skills/sync-well)<a href="https://agentmods.dev/skills/ohong/agent-skills/sync-well"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/sync-well/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/ohong/agent-skills/sync-well"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/sync-well.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.00749 |
| Opus 5.5 | $0.00034 | $0.00300 |
| Sonnet 5.5 | $0.00017 | $0.00150 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
sync-well 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Well
Preserve both committed and uncommitted work while establishing what Git can safely do. Treat inspection, network refresh, reconciliation, commit, and push as separate authorization boundaries.
Inspect
- Run
scripts/inspect_sync.sh [repository]. It is read-only and uses only current local refs. - If it reports an in-progress merge, rebase, cherry-pick, or revert, stop and use the merge-conflict workflow.
- Confirm the intended branch and worktree. A branch checked out in another worktree must be handled there.
- Show the user the branch/upstream, staged and unstaged state, untracked files, ahead/behind counts, merge base, and all reported path overlaps.
Refresh Remote State
Fetching changes remote-tracking refs, so keep it visible:
/usr/bin/git remote -v
/usr/bin/git fetch --prune <remote>
scripts/inspect_sync.sh .
Fetch only when network access is allowed. Derive <remote> from the configured upstream; do not assume origin. Never claim the comparison is current if fetch failed or was skipped.
Recommend
- Fast-forward only: Recommend
/usr/bin/git merge --ff-only <upstream>when behind-only, on the intended worktree, and clean. Do not use a plaingit pull, because configured pull behavior is ambiguous. - Merge: Recommend
/usr/bin/git merge <upstream>when histories diverge, the tree is clean, and both histories must be preserved. Explain overlapping committed paths and the conflict risk. A normal merge may create a commit, so obtain explicit authorization first. - Stop for choice: Stop when the branch or upstream is unclear, histories are unrelated, the tree is dirty, another operation is active, the wrong worktree is open, or uncommitted work overlaps remote-only paths. Review the actual diffs before asking whether work should be kept.
- Ahead only: Report that syncing needs no inbound reconciliation. Ask separately before pushing; do not infer publication permission.
- Up to date: Report that no reconciliation is needed.
What ships with it
2 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.
- 1mo ago First seen · 52 lines · 85 tokens per session scan A 255ab11b6027
sync-well is a skill published in the GitHub repository ohong/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 749 once invoked, about $0.0003 per session on Opus 5.5. 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
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.