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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/commands/christopherlouet/claude-base/ops-rollback)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/ops-rollback"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/ops-rollback/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/commands/christopherlouet/claude-base/ops-rollback"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/ops-rollback.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 | $0.00000 | $0.00307 |
| Opus 5.5 | $0.00000 | $0.00123 |
| Sonnet 5.5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
ops-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 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.
What it actually says
ROLLBACK Agent
Secure rollback procedure to revert to a stable version.
Request context
$ARGUMENTS
Objective
Execute a fast and secure rollback, whether at the code level (git), deployment level (Vercel, K8s, Docker, ECS) or database level.
Workflow
- Classify the rollback (urgent, planned, preventive)
- Assess the situation (confirm the problem, identify the target version)
- Communicate to the team BEFORE starting
- Create a save point (checkpoint tag)
- Execute the rollback with the appropriate strategy (git revert, kubectl rollout undo, etc.)
- Verify (health check, logs, metrics, smoke test)
- Communicate the result and plan the post-mortem
Expected output
- Classification of the rollback with chosen strategy
- Commands executed for the rollback
- Verification post-rollback (health, logs, metrics)
- Communication templates (during and after)
Related agents
| Agent | Usage |
|---|---|
/ops:ops-hotfix |
Quick fix after rollback |
/ops:ops-monitoring |
Verify metrics |
/ops:ops-health |
Quick health check |
IMPORTANT: A successful rollback is a FAST rollback. Rollback first, investigate later.
IMPORTANT: Always document rollbacks to improve processes.
YOU MUST verify that the service is stable after rollback.
NEVER rollback without having a verification plan.
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 · 47 lines · 0 tokens per session scan A 284162ac6ee8
ops-rollback is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 307 tokens. 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 commands, from other repositories
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
changelog
Generate a changelog entry from git commits since the last tag using conventional commit format.
deploy
Deploy application with pre/post-deploy checks.
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
cm
Stage working tree changes and create a Conventional Commit (no push).
deps-update
Audit and update dependencies safely.