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 davekilleen/Dex --skill dex-rollbackgit clone --depth 1 https://github.com/davekilleen/DexWrote 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/davekilleen/dex/dex-rollback)<a href="https://agentmods.dev/skills/davekilleen/dex/dex-rollback"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/dex-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/skills/davekilleen/dex/dex-rollback"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/dex-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 | $0.00049 | $0.00862 |
| Opus 5.5 | $0.00020 | $0.00345 |
| Sonnet 5.5 | $0.00010 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
dex-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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dex Rollback
Use this skill when someone wants to undo a Dex adoption. Keep the language calm and concrete. This skill selects and renders a receipt; it never restores, copies, deletes, renames, or rewrites vault files itself.
The one route
Every rewind goes through core.lifecycle.service version 1.0.0. The only mutation operation this skill may request is rewind_adoption_by_receipt. There is no manual fallback and no file-by-file workaround.
Use the service in this order:
- Ask
read_lifecycle_statefor the verified ledger and retention state. - Render the adopted items that have receipt-backed rewind evidence.
- Let the user choose exactly one adoption receipt.
- Show the receipt’s transaction identifier and complete file list.
- Ask for explicit confirmation of that exact adoption and file list.
- Pass the unchanged adoption receipt and its exact acknowledgement token to
rewind_adoption_by_receipt. - Ask
read_lifecycle_stateagain and render the rewind receipt and resulting state.
If the snapshot has aged out, a file changed after adoption, the ledger cannot be verified, the acknowledgement does not match, or the service refuses for any other reason, stop. Explain that no files were changed. Never guess an older state from release files or version labels.
Choice view
For each rewindable adoption, show:
- item names and versions;
- when the lifecycle ledger recorded it, if the state provides that time;
- adoption transaction identifier;
- number of receipt-declared files;
- whether the retained snapshot is still available;
- whether any adopted file has drifted since adoption.
Example register:
I found one update that can still be undone exactly. It changed three Dex-owned files, and none of those files has changed since.
A version update appears as dex-release at the installed version. Treat it
the same as any other receipt-backed item: it is rewindable only when the
verified state says its receipt and retained snapshot pass preflight.
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 · 88 lines · 49 tokens per session scan A aaeca0df014a
dex-rollback is a skill published in the GitHub repository davekilleen/Dex (508 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 862 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-02.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
publish
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: . Triggers: publish, release, deploy, npm publish.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…