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/softspark/ai-toolkit/rollbacknpx skills add softspark/ai-toolkit --skill rollbackgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/rollback)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/rollback"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/rollback.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01193 |
| Opus 5 | $0.00019 | $0.00596 |
| Sonnet 5 | $0.00008 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
rollback 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rollback - Safe Rollback
$ARGUMENTS
What This Command Does
Safely revert changes with appropriate safety checks and confirmation.
Rollback Types
1. Git Rollback
# Revert last commit (creates new commit)
git revert HEAD --no-edit
# Revert specific commit
git revert <commit-sha> --no-edit
# Revert to specific state (CAUTION)
git reset --soft <commit-sha> # Keep changes staged
2. Database Migration Rollback
| Tool | Command |
|---|---|
| Alembic | alembic downgrade -1 |
| Prisma | npx prisma migrate resolve --rolled-back <name> |
| Laravel | php artisan migrate:rollback --step=1 |
| Django | python manage.py migrate <app> <previous> |
| Flyway | flyway undo |
3. Deployment Rollback
| Platform | Command |
|---|---|
| Kubernetes | kubectl rollout undo deployment/<name> |
| Docker Compose | docker compose up -d --force-recreate (with previous image tag) |
| Heroku | heroku rollback |
Gather Rollback Context
Run the rollback info script to assess current state before rolling back:
python3 ${CLAUDE_SKILL_DIR}/scripts/rollback_info.py
Returns JSON with:
git{}- current/previous commit, branch, commits ahead, uncommitted changesmigrations{}- detected tool (alembic/prisma/laravel/django/drizzle), rollback commanddocker{}- running services and image tags
Safety Checks (MANDATORY)
Before any rollback:
- Confirm what will be reverted (show diff/plan)
- Check for dependent changes that may break
- Verify backup exists (for database rollbacks)
- Get explicit user confirmation
Usage Examples
/rollback # Interactive - asks what to rollback
/rollback git last # Revert last git commit
/rollback migration # Rollback last database migration
/rollback deploy # Rollback to previous deployment
CRITICAL: Always confirm with the user before executing destructive rollback operations.
Rules
- MUST confirm the current state AND the target state before rolling back — surface the diff in plain English
- MUST verify a recent backup exists (for DB rollbacks) or explicitly warn the user that none was found
- NEVER roll back without an explicit "yes" from the user — rollbacks are irreversible in the user-experience sense even when technically reversible
- NEVER
git reset --hardon a branch others have pulled from — it rewrites shared history - CRITICAL: after any rollback, run a health check (
/healthor the project's equivalent) to confirm the target state is stable — a "successful" rollback to a broken baseline is worse than the original state - MANDATORY: log the rollback with timestamp, scope, and reason — post-mortems need this trail
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.
- 2d ago First seen · 114 lines · 39 tokens per session scan A f65750fa7a7b
rollback is a skill published in the GitHub repository softspark/ai-toolkit (170 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,193 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 2026-09-03.
Other skills, from other repositories
roo-bedrock-custom-arn
Roo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
argocd-expert
Expert-level ArgoCD GitOps deployment, application management, sync strategies, and production operations. Use when the user mentions GitOps, Kubernetes, continuous deployment, declarative, or automation, or when the task involves ArgoCD Architecture, Application CRD, AppProject, or ApplicationSet.
monitoring-alerting
Monitoring and alerting design reviewer for production backend services. ALWAYS use when writing Prometheus alerting rules, designing Grafana dashboards, defining SLI/SLO, configuring alert routing (PagerDuty/OpsGenie/Slack), or reviewing existing monitoring setups. Covers SLI/SLO definition, alert rule quality…
create-pr
Create evidence-backed pull requests to the GitHub main branch with strict preflight, quality, and security gates. Use when users ask to create/submit/open/update a PR to main (including private repos), decide draft vs ready state, and provide reviewer-ready context for team review.
git-commit
Safely create a git commit by validating repository state, staging intended changes, scanning for secrets/conflicts, generating a Conventional Commits message (repository convention first, else an English Angular default) from the staged diff, and committing without amend.