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 blasrodri/truthnpx agentmods add plugins/blasrodri/truth/marketplacegit clone --depth 1 https://github.com/blasrodri/truthGrade A, and why
truth 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 yesterday.
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": "truth",
"description": "truth — the deterministic fact-checker for AI coding agents. Verifies every claim an agent makes about its own work against the real code, git diff, and recorded runs.",
"owner": {
"name": "Blas Rodriguez Irizar",
"url": "https://github.com/blasrodri"
},
"plugins": [
{
"name": "truth",
"source": "./",
"description": "Fact-check every agent turn: deterministic, cited verdicts against your repo, working-tree diff, and recorded runs. Contradictions block the turn before you read them."
}
]
}
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.
- yesterday First seen · 16 lines scan A 986ec4c1b383
truth is a plugin published in the GitHub repository blasrodri/truth (1 stars, last pushed 1mo 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
pibox
pi-coding-agent running in a container — interactive shell, one-shot exec, an HTTP REST API, an OpenAI-compatible chat endpoint, an MCP server, a Telegram bot, and a cron scheduler, all on one image.
ai-maestro-plugins
Plugin marketplace listing 1 plugin: ai-maestro.
rvdbreemen-adr-kit
Marketplace hosting the adr-kit plugin: a drop-in Architecture Decision Record toolkit for AI coding agents.
skillpack
Generate and verify the agent-distribution layer for any OSS project.
pluribus
First-party Pluribus memory loop for Claude Code: MCP, hooks (session wake-up + prompt recall, optional failure hint), skills, and a recall-first investigator agent. Server owns memory; plugin orchestrates.
playwright
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.