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/mennanov/blockwatchWrote 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/mennanov/blockwatch/agents)<a href="https://agentmods.dev/plugins/mennanov/blockwatch/agents"><img src="https://agentmods.dev/badge/plugins/mennanov/blockwatch/agents/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/mennanov/blockwatch/agents"><img src="https://agentmods.dev/badge/plugins/mennanov/blockwatch/agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
blockwatch 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 9d 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": "blockwatch",
"displayName": "blockwatch",
"description": "Keep co-dependent code, docs, and config in sync with blockwatch <block> annotations: drift detection (affects), sorted/unique lists, regex/line-count/AI/Lua validation. Includes a skill that teaches agents when and how to add and maintain blocks.",
"author": {
"name": "Renat Mennanov",
"url": "https://github.com/mennanov"
},
"homepage": "https://github.com/mennanov/blockwatch",
"repository": "https://github.com/mennanov/blockwatch",
"license": "MIT",
"keywords": ["linter", "sync", "drift-detection", "keep-sorted", "documentation"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 185 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 9d ago Changed c81abe2b089a
- 1mo ago First seen · 14 lines scan A f66f8bbfbe88
blockwatch is a plugin published in the GitHub repository mennanov/blockwatch (29 stars, last pushed today), licensed MIT. 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 2026-08-30.
Other plugins, from other repositories
rust-learner
Learn Rust language features and crate updates using Actionbook + agent-browser.
pkm
Personal knowledge management skills for a Scraps wiki - learn a source through explanation and comprehension checks and record only what was understood, or digest an article or talk into a short linked summary without dialogue.
vastlint
Validate VAST, VMAP, and DAAST ad tags against IAB Tech Lab specs. Hosted MCP at https://vastlint.org/mcp. Auth none for public tools.
vastlint
MCP configuration declaring 1 server: vastlint.
docvet marketplace
Plugin marketplace listing 1 plugin: docvet-lsp.
promql-cody
Unified agent, plus all six per-tool skills, for the PromQL/Alertmanager CLIs: orchestrates which are hermetic/CI-safe vs. interactive-only and in what order to run them.