rollback

A command for restoring a skill to an earlier saved version while first saving the current version as a new snapshot.

In plain words
What is it for?
Use it to roll a named skill back by one or more versions, such as restoring an earlier brainstorming skill.
Why use it?
It lets you undo a skill change while keeping the current state available for recovery.

Command

Install

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.

agentmods
npx agentmods add commands/lookatitude/guild/rollback
Clone the repo
git clone --depth 1 https://github.com/lookatitude/guild
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00675
Opus 5 $0.00023 $0.00338
Sonnet 5 $0.00009 $0.00135
Haiku 4.5 $0.00005 $0.00068

Measured yesterday against content hash d59679a84b3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

commands/rollback.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/guild:rollback — self-maintenance (Guild-on-Guild)

Reverts a skill to a previous version. Maps to skill guild:rollback-skill. The rollback is itself a versioned artifact — non-destructive (snapshots current state as vN+1, restores vN or vN-n).

Usage

/guild:rollback guild-brainstorm
/guild:rollback guild-brainstorm 2

Args

  • <skill> — the skill to roll back.
  • [n] — number of steps to walk back (default 1).

Gates

Confirm past v1 I.

Output

.guild/skill-versions/<skill>/v<N+1>/.

Run-start preflight (settings-control-and-tmux U3/U6)

Before the rollback skill is invoked — and before run-trace start — the run-trace CLI runs this preflight for you — you do not call runStartPreflight yourself.

Since wave 2, run-trace.js start (below) is the sole caller of runStartPreflight (scripts/lib/runstart-preflight.ts; canonical contract in guild.md §Run-start preflight): on start the CLI resolves the 7-source inheritance chain, validates closed keys, probes tmux, detects providers, and writes .guild/runs/<id>/resolved-settings.json (+ a compact settings_ref in run.yaml) automatically before the run opens. If this command needs the resolved config — e.g. the dispatch backend effective.agent_mode — read the snapshot back with readResolvedSettingsSnapshot(runId, { cwd }); never re-resolve.

Run recording

Before the rollback-skill is invoked, start a run (SC-B, §435):

node ${GUILD_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$HOME/.local/share/guild/dist/claude-code}}/hooks/dist/run-trace.js start \
  --command=/guild:rollback \
  --cwd "$(pwd)"

run-class default (full). Records the run before the snapshot + restore so the complete session — confirm-past-v1 gate and eval suite re-run — is replayable from the entrypoint. Writes to .guild/skill-versions/ — not .guild/initiatives/ (NN#5 unaffected). No --initiative flag.

Dispatch

Skill: guild:rollback-skill
args: $ARGUMENTS

Re-runs the restored version's eval suite after rollback to confirm the older content still passes; flags drift if not. Rollback logic and .guild/ writes live in the guild:rollback-skill skill.

Read the full file on GitHub · 75 lines

Changes

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.

  1. yesterday First seen · 75 lines · 46 tokens per session scan A d59679a84b3b

Subscribe to this mod's changes

rollback is a command published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 675 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 2026-08-31.