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.
/plugin marketplace add avansaber/tailtestnpx agentmods add plugins/avansaber/tailtest/marketplacegit clone --depth 1 https://github.com/avansaber/tailtestGrade A, and why
avansaber-tailtest 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 2d 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": "avansaber-tailtest",
"owner": {
"name": "AvanSaber Inc.",
"email": "[email protected]"
},
"metadata": {
"description": "Quietly generates and runs tests alongside your Claude Code session. Any language. No commands. No setup.",
"homepage": "https://tailtest.com",
"repository": "https://github.com/avansaber/tailtest"
},
"plugins": [
{
"name": "tailtest",
"source": "./",
"description": "Automatically runs the test cycle you would otherwise ask Claude for manually. Generates production-like scenarios for what was just built, executes them, and surfaces only what fails.",
"version": "3.15.0",
"author": {
"name": "AvanSaber Inc.",
"email": "[email protected]",
"url": "https://avansaber.com"
},
"homepage": "https://tailtest.com",
"repository": "https://github.com/avansaber/tailtest",
"license": "MIT",
"keywords": [
"testing",
"auto-test",
"claude-code",
"assistant",
"framework-agnostic"
]
}
]
}
What ships with it
1 file beside marketplace.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.
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.
- 2d ago First seen · 36 lines scan A f78a4968800b
avansaber-tailtest is a plugin published in the GitHub repository avansaber/tailtest (11 stars, last pushed 2mo ago), 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 2026-08-31.
Other plugins, from other repositories
roam-code
Local codebase intelligence + change-safety gates for coding agents. REQUIRES Python 3.10+ and pip install roam-code first — this plugin launches the roam binary from your PATH, and its MCP server cannot start without it. Pre-indexes your repo's symbols, call graph, deps, and git history into SQLite (28 languages.
ring
Lerian Studio plugin marketplace: Core software engineering skills (TDD, debugging, code review), specialized developer agents (Backend, DevOps, Frontend, QA, SRE) plus 12 code-review reviewers (9 default hard-gate reviewers and 3 conditional stack specialists), product planning workflows (8-gate pre-dev system), and…
avtr-antidote
Plugin marketplace listing 1 plugin: antidote.
antidote
Stop AI agents from patching symptoms. Forces structural root-cause fixes over symptom patching in any language or stack.
dynos-work
Autonomous Software Foundry. Human-directed, tool-grounded, self-improving. Plans, executes, audits, repairs — calibrates to your project over time.
archlint
Catches architectural drift while the agent writes code — checks edited files' imports against layer rules declared in your CLAUDE.md.