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 ZaxbyHub/opencode-swarm --skill git-revert-safetygit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote 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/zaxbyhub/opencode-swarm/git-revert-safety)<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/git-revert-safety"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/git-revert-safety/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/zaxbyhub/opencode-swarm/git-revert-safety"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/git-revert-safety.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 | $0.00079 | $0.02085 |
| Opus 5.5 | $0.00032 | $0.00834 |
| Sonnet 5.5 | $0.00016 | $0.00417 |
| Haiku 4.5 | $0.00008 | $0.00209 |
Grade A, and why
git-revert-safety 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 7d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Revert Safety Protocol
Two internal workflows: Safe Git Revert (Steps 1-4) and Branch Contamination Recovery (Steps 5-6). Use the first when reverting known commits. Use the second when the wrong code was merged and you need a clean slate.
Workflow A — Safe Git Revert
Step 1 — Collateral Damage Assessment
Before reverting, list ALL files touched by each commit being reverted. Use the correct command for the situation:
Single commit:
git show --name-only --format= <sha>
Multiple commits (contiguous range):
git diff --name-only <commit-before-first>..<last-commit-sha>
Merge commit — inspect all parents (handles octopus merges with 3+ parents):
git show --format="%H %P" <merge-sha> # Shows ALL parent SHAs
git log --oneline <merge-sha>^1 # First parent (usually main)
git log --oneline <merge-sha>^2 # Second parent (feature branch)
# For octopus merges: also inspect ^3, ^4, etc.
Identify which files in the diff are NOT part of the feature being reverted:
.release-please-manifest.json— version statepackage.json— version field + dependency additions/removalsCHANGELOG.md— release history- Lockfiles (
bun.lock,package-lock.json) — dependency graph - Any config files modified by release PRs between the feature and now
dist/ is generated and NOT committed, so it never appears in a revert diff and
needs no rebuild+commit as part of a revert — reverting the source is enough.
Gate: If ANY version metadata or dependency file appears in the diff, you MUST verify post-revert state (Step 3).
Step 2 — Choose Recovery Strategy
| Scenario | Strategy | Caveat |
|---|---|---|
| Single commit that does NOT touch release/build artifacts | git revert <sha> |
Still verify metadata diff after |
| Single commit that DOES touch release artifacts | Verify post-revert metadata manually | May need corrective commit |
| Multi-commit revert, no releases between | git revert <sha1> <sha2>... |
Verify each commit's file scope |
| Multi-commit revert, releases between | Cherry-pick fix onto fresh branch | Avoids collateral damage from reverse-apply |
| Merge commit revert | git revert -m <parent-number> <merge-sha> |
Must specify correct parent (usually -m 1 for main) |
| Branch contamination (wrong code merged) | Fresh branch + cherry-pick | See Workflow B |
| Revert of revert (re-apply feature) | git revert <revert-sha> |
⚠️ Code may have drifted — check for conflicts |
| Squash merge revert | Fresh branch + cherry-pick preferred | Squash merges have no merge-parent metadata |
| Octopus merge (3+ parents) | Fresh branch + cherry-pick unless parent is unambiguous | -m parent selection is error-prone; prefer clean slate |
What ships with it
1 file 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.
- 7d ago Changed · -8 lines ea90ec570888
- 12d ago Changed · +1 lines f0aee0ceab84
- 1mo ago First seen · 199 lines · 79 tokens per session scan A ff89776998a7
git-revert-safety is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (510 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 2,085 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 2026-09-03.
Other skills, from other repositories
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
docs-update-from-diff
Review local code changes with git diff and update the official docs under docs/ to match. Use when the user asks to document current uncommitted work, sync docs with local changes, update docs after a feature or refactor, or when phrases like "git diff", "local changes", "update docs", or "official docs" appear.
prepare-pr
Prepare GitHub pull request title and body files from the current branch diff, especially for non-interactive CI/autofix flows that must follow the repository PR template without pushing or creating the PR.
triage
Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.