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.
git clone --depth 1 https://github.com/madeinplutofabio/vibe-revertWrote 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/plugins/madeinplutofabio/vibe-revert/gemini-extension)<a href="https://agentmods.dev/plugins/madeinplutofabio/vibe-revert/gemini-extension"><img src="https://agentmods.dev/badge/plugins/madeinplutofabio/vibe-revert/gemini-extension/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/plugins/madeinplutofabio/vibe-revert/gemini-extension"><img src="https://agentmods.dev/badge/plugins/madeinplutofabio/vibe-revert/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
viberevert 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.
What it actually says
{
"name": "viberevert",
"version": "0.8.0-beta.1",
"description": "Deterministic risk checks and session recovery for AI coding agents.",
"mcpServers": {
"viberevert": {
"command": "npx",
"args": ["-y", "[email protected]", "mcp", "serve"],
"cwd": "${workspacePath}"
}
}
}
What ships with it
39 files beside gemini-extension.json 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.
- scripts/bench-end-latency.ts 8.0 KB runs code
- scripts/check-dependency-policy.ts 3.5 KB runs code
- scripts/check-support-manifest.ts 3.0 KB runs code
- scripts/decision7/decision7-lib.mjs 44 KB runs code
- scripts/decision7/fixture-agent.mjs 4.2 KB runs code
- scripts/decision7/operator-harness.mjs 75 KB runs code
- scripts/decision7/operator-template.mjs 2.4 KB runs code
- scripts/decision7/README.md 12 KB
- scripts/decision7/summarize-matrix.mjs 28 KB runs code
- scripts/decision7/summarize-matrix.test.mjs 31 KB runs code
- scripts/dependency-policy-core.ts 20 KB runs code
- scripts/license-audit-core.ts 37 KB runs code
- scripts/license-audit-render.ts 13 KB runs code
- scripts/license-collector.ts 32 KB runs code
- scripts/license-lockfile-v9.ts 35 KB runs code
- scripts/license-schemas.ts 29 KB runs code
- scripts/mcp-stdio-probe.mjs 16 KB runs code
- scripts/post-publish-smoke.ps1 22 KB runs code
- scripts/probe-end-phases.ts 9.0 KB runs code
- scripts/rc-smoke-consumer.mjs 4.4 KB runs code
- scripts/rc-validation/rc-capture.sh 4.1 KB runs code
- scripts/refresh-license-metadata-core.ts 11 KB runs code
- scripts/refresh-license-metadata.ts 16 KB runs code
- scripts/refresh-net.ts 12 KB runs code
- scripts/refresh-registry.ts 25 KB runs code
- scripts/refresh-sri.ts 7.5 KB runs code
- scripts/refresh-tarball.ts 13 KB runs code
- scripts/regen-goldens.ts 13 KB runs code
- scripts/regen-license-audit-core.ts 9.4 KB runs code
- scripts/regen-license-audit.ts 5.5 KB runs code
- scripts/release-targets.json 394 B
- scripts/scratch-cleanup.ts 1.9 KB runs code
- scripts/smoke-test.ps1 95 KB runs code
- scripts/strict-json.ts 11 KB runs code
- scripts/support-manifest-core.ts 20 KB runs code
- scripts/support-manifest-live-pty.ts 7.0 KB runs code
- scripts/support-manifest-parser.ts 737 B runs code
- scripts/support-manifest-workflow.ts 14 KB runs code
- scripts/workspace-collector.ts 12 KB runs code
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 Changed dfa88c9e250b
- 1mo ago First seen · 13 lines scan A 4d43185fea26
viberevert is a plugin published in the GitHub repository madeinplutofabio/vibe-revert (0 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-07.
Other plugins, from other repositories
odh-git
Git utilities, GitHub/GitLab workflow automation, and CI debugging.
devcodex-workspace
User-global DevCodex bridge for Cursor local IDE and CLI workflows.
hunch
A git-native reasoning graph of decisions, bugs, and invariants for your codebase — queried and enforced at reasoning time. Adds the hunch MCP tools plus /hunch:capture, /hunch:heal, /hunch:why, /hunch:fix, /hunch:fragile.
octo-cluster
Ship logical commits safely (direct push or PR, never force), turn rough requests into ready-to-run prompts, debug with evidence, and keep always-on context thin.
shiplog
Git-as-knowledge-graph workflow for traceability across issues, branches, commits, reviews, and PRs.
bashback
Undo for the shell commands your coding agent runs — snapshots the working tree around every command so file side effects (rm, mv, sed -i, ...) can be audited and restored.