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 qwerfunch/cladding --skill rollbackgit clone --depth 1 https://github.com/qwerfunch/claddingWrote 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/qwerfunch/cladding/rollback)<a href="https://agentmods.dev/skills/qwerfunch/cladding/rollback"><img src="https://agentmods.dev/badge/skills/qwerfunch/cladding/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 | $0.00080 | $0.00533 |
| Opus 5 | $0.00040 | $0.00267 |
| Sonnet 5 | $0.00016 | $0.00107 |
| Haiku 4.5 | $0.00008 | $0.00053 |
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 7d 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
Cladding rollback
Run clad rollback <featureId> from the project root. The verb is the partner of clad checkpoint (iron-law.md §2.5 Iron Law backbone Phase 1) — it stamps a feature_rolled_back event into .cladding/events.log.jsonl and prints the git checkout <sha> command the maintainer can run. Cladding does not run the checkout itself — the host's branch policy, dirty-working-tree state, or detached-HEAD concerns may demand a non-default strategy, so the decision stays with the maintainer.
-r, --reason <reason>— optional free-text reason recorded on the event payload. Useful for post-mortems and the Librarian's archival flow.
clad rollback F-001
clad rollback F-a3f9c2 --reason "specialist dispatched a regression on the L1 lint gate"
The output is a single Pulse line plus the restoration command:
✓ rollback · F-a3f9c2 target head=<sha12> ts=<iso>
Run: git checkout <sha40>
When the latest checkpoint has no gitHead (the project is not a git repo), the verb prints No git head pinned — restore spec.yaml manually from VCS history. instead.
Exit codes
0— rollback event stamped, restoration command printed.1— no prior checkpoint exists for the feature; nothing to roll back to. Runclad checkpoint <featureId>next time before mutating.2— feature id argument missing.
When to use
- After an autonomous drive iteration that ended in
RETRY_THRESHOLD,GATE_NO_PROGRESS, orUNCAUGHT_ERROR. - After a manual implementation attempt that introduced a regression you don't want to bisect.
- Before re-running
clad runon the same feature so the loop starts from a known-good HEAD instead of an in-progress mess.
Pair with
clad checkpoint <featureId> — stamps the safety net rollback restores from. See skills/checkpoint/SKILL.md.
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.
- 7d ago First seen · 40 lines · 80 tokens per session scan A d472dc3a562b
rollback is a skill published in the GitHub repository qwerfunch/cladding (14 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 533 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 2026-08-30.
Other skills, from other repositories
investigating-repository-history
Investigate GitHub repository history before risky code changes using git blame/log, GitHub PRs, review comments, squash/rebase/cherry-pick/rename heuristics, and cited evidence. Use when asking why code exists, whether a change is safe, what PR introduced behavior, or before editing API, compatibility, security…
finishing-a-development-branch
Use when development work is complete and you need to prepare for merge. Guides through cleanup, testing, documentation, and creating a well-structured pull request.
repo-activity-summary
Summarize a repository's recent engineering activity from git history — technologies, work types, churn hotspots, contributor patterns, and velocity. Use when asking "what has this repo been working on", "is this project active", "who contributes what", "where are the hotspots", or before onboarding onto an unfamiliar…
verify-gates
Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…
worktree-pr
Decide whether a task deserves its own git worktree and, if chosen, run it end to end: branch from the integration branch rather than the current tree, keep the main working copy untouched while the task runs, compare the result against the untouched baseline before declaring it done, and prepare it for a pull request…
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.