rollback is agent-read markdown (skill) from nahid-sparktales/agent-dispatcher: Get back to a known-good state, and know in advance which parts of a release cannot come back — destructive migrations, data the old version cannot read, messages already sent, published artifacts, cache and CDN state. Use while writing a release plan, when a deploy is going wrong, or when someone asks whether a change can be undone. Not the health check that decides you should revert (release-verification), not incident coordination, and it never runs a production revert without explicit per-ac.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Rollback
Rollback is not the absence of a deploy. It is another deploy, made under time pressure, against a
system whose state has already moved. Most failed rollbacks fail for that reason: the code went
back and the data did not.
## When this fires
While planning a release — the rollback path is part of the plan, not a thing to invent later — and
again the moment a release is going badly. It fires before the decision to revert, not after it.
## Procedure
1. **Name the known-good state as an artifact id.** The commit, digest or build you would return
to, confirmed still deployable — the image still present in the registry, the release still
installable. "The previous version" is not an address, and a rollback target that was garbage
collected is not a rollback target.
2. **Classify every part of the change** into three buckets, before you need them:
- *Reversible* — redeploying the old artifact restores the old behavior.
- *Forward-only* — the way back is a new fix, not the old code.
- *Irreversible* — nothing restores the prior state; only mitigation exists.
3. **Find the one-way doors.** These are the ones that turn a rollback into an incident:
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_neju5lon7obvrnfj
GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/rollback
GET https://markdownregistry.com/api/v1/blob/c95267f9dd5f0ddd0f053c031d81ce4596620acd51066f486f6ea4f6ea615847
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
nahid-sparktales/agent-dispatcher · skills/agent-dispatcher/SKILL.md · Route work to a specialist role and load its task-specific guidance. Use when the user invokes /agent-dispatcher, names…
nahid-sparktales/agent-dispatcher · skills/ai/agent-design/SKILL.md · Scope an agent or subagent before it is built — the one job it owns, the smallest tool set that closes that job, what…
nahid-sparktales/agent-dispatcher · skills/ai/agent-evals/SKILL.md · Build an eval suite that can actually detect a regression — cases pulled from real traffic, graders that check…
nahid-sparktales/agent-dispatcher · skills/ai/context-engineering/SKILL.md · Decide what actually occupies the model's window — progressive disclosure through an index, retrieval versus inlining…
nahid-sparktales/agent-dispatcher · skills/ai/llm-observability/SKILL.md · See what an agent actually did — one trace per run with nested model, tool and retrieval spans, token and latency…
nahid-sparktales/agent-dispatcher · skills/ai/mcp-design/SKILL.md · Build an MCP server, or bring an existing one into a project — choosing the transport, deciding which tools, resources…
nahid-sparktales/agent-dispatcher · skills/ai/memory-design/SKILL.md · Decide what an agent should remember, which layer holds it, who it is scoped to, and how a stale or contradicted memory…
nahid-sparktales/agent-dispatcher · skills/ai/model-routing/SKILL.md · Pick a model per job and degrade sensibly when one fails — a quality bar per call site, candidates compared on the same…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-engineering/SKILL.md · Write or revise a prompt so it holds up — output contract, instruction placement, examples that earn their place, an…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-injection-defense/SKILL.md · Treat everything an agent reads but did not author as data rather than instructions — an explicit trust boundary, a…
nahid-sparktales/agent-dispatcher · skills/ai/retrieval-rag/SKILL.md · Build and fix retrieval that actually returns the right passage — structure-aware chunking, one pinned embedding model…
nahid-sparktales/agent-dispatcher · skills/ai/structured-output/SKILL.md · Get parseable, trustworthy structured results out of a model — schema design, the enforcement mechanism the provider…
suboss87/fdeops · skills/rollback/SKILL.md · Prepare and rehearse a recovery path for an intended release. Use when rollback is assumed, untested or previously…
qwerfunch/cladding · skills/rollback/SKILL.md · Record a rollback event and print the maintainer-runnable git command for the most recent checkpoint of a feature. Use…
qwerfunch/cladding · plugins/codex/skills/rollback/SKILL.md · Record a rollback event and print the maintainer-runnable git command for the most recent checkpoint of a feature. Use…
qwerfunch/cladding · plugins/antigravity/skills/rollback/SKILL.md · Record a rollback event and print the maintainer-runnable git command for the most recent checkpoint of a feature. Use…