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 confighub/confighub-skills --skill rollback-revisiongit clone --depth 1 https://github.com/confighub/confighub-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/confighub/confighub-skills/rollback-revision)<a href="https://agentmods.dev/skills/confighub/confighub-skills/rollback-revision"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/rollback-revision/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/confighub/confighub-skills/rollback-revision"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/rollback-revision.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 | $0.00071 | $0.02905 |
| Opus 5 | $0.00036 | $0.01452 |
| Sonnet 5 | $0.00014 | $0.00581 |
| Haiku 4.5 | $0.00007 | $0.00291 |
Grade A, and why
rollback-revision 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 12d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rollback-revision
Execution mode: follow references/execution-modes.md. This Skill grants no automatic tool permission. After binding and diffing the exact restore target, standalone use submits one requested head-moving restore to the host permission system. The later whole-Space publication is a separate host-permission call; an external overlay may stop either step before Bash.
Resolve and preview the exact Unit head or ChangeSet scope to restore. On a clear standalone rollback request, submit one exact restore through the host permission system, verify it, and treat the later whole-Space publication as a separate request.
cub unit update --restore is the only rollback mechanism
Rollback always means: create a new head whose data equals a bound prior Revision, then publish that restored desired state through a newly approved Space Release. Every subsequent mutation branches from the restored head, so the bad state stays gone.
Rollback is a head-moving cub unit update --restore followed, after verification, by a separate immutable Space Release. Each is its own host-permission call. Do not try to replay historical runtime data without moving head: the next mutation or promotion would re-introduce the bad state.
Recognize and refuse the retired-unit-runtime-verbs anti-pattern retained in
compatibility/no-loss-inventory.v1.json; the active skill deliberately does
not reproduce its executable spelling. That historical bridge-era form could
deploy old bytes without moving head, so it is not rollback. The current
OCI Release profile has no per-Unit apply fallback. The durable route is to resolve the
requested prior revision to RevisionID/DataHash, create a new head with
cub unit update --restore 47, and then prepare a fresh Space Release.
When to use
- User says "roll back", "revert", "undo" — and means it: the restored state should be the new baseline.
- Post-promotion rollback: a ChangeSet went out, the destination env rejects it, restore every affected Unit to
Before:ChangeSet:<slug>. - Single-Unit revert: one Unit got a bad revision, restore to
LastReleasedRevisionNumor a specific prior number.
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.
- 12d ago First seen · 183 lines · 71 tokens per session scan A 69008540c9b8
rollback-revision is a skill published in the GitHub repository confighub/confighub-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 2,905 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.