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/SeeleAI/ThothWrote 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/seeleai/thoth/thoth)<a href="https://agentmods.dev/plugins/seeleai/thoth/thoth"><img src="https://agentmods.dev/badge/plugins/seeleai/thoth/thoth/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/seeleai/thoth/thoth"><img src="https://agentmods.dev/badge/plugins/seeleai/thoth/thoth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
thoth 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": "thoth",
"version": "0.4.3",
"description": "Dashboard-centric Agent Project OS for auditable AI execution, persistent project state, and human-visible workflow orchestration.",
"author": {
"name": "SeeleAI",
"url": "https://github.com/SeeleAI"
},
"homepage": "https://github.com/SeeleAI/Thoth",
"repository": "https://github.com/SeeleAI/Thoth",
"license": "MIT",
"keywords": [
"research",
"project-management",
"dashboard",
"autonomous",
"audit",
"execution"
]
}
What it installs
The manifest is a name and a version. 1 skill, 11 commands travel with it, and installing the plugin installs all of them — 292 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill thoth A 38 tokens
- Command thoth:auto A 26 tokens
- Command thoth:discuss A 16 tokens
- Command thoth:init A 32 tokens
- Command thoth:loop A 18 tokens
- Command thoth:run A 32 tokens
- Command thoth:argue A 25 tokens
- Command thoth:extension A 24 tokens
- Command thoth:dashboard A 24 tokens
- Command thoth:doctor A 20 tokens
- Command thoth:tui A 20 tokens
- Command thoth:status A 17 tokens
What ships with it
1 file beside plugin.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.
- 1mo ago First seen · 21 lines scan A 0fea7dcaf7c4
thoth is a plugin published in the GitHub repository SeeleAI/Thoth (51 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 2026-08-30.
Other plugins, from other repositories
agent-taskgraph
Build native Claude Code Agent Teams with goals, roles, task graphs, collaboration protocols, and lifecycles.
sw
The specwright ladder for Claude Code and Codex: init, propose, plan, implement, review, archive, ship, and delivery.
docs-cockpit marketplace
Single-plugin marketplace for docs-cockpit — skill-first project dashboard: skills own the doc-association cognition, a mechanical CLI renders.
orgx
Agent orchestration, decisions, and organizational memory for Cursor. Review pending decisions, scaffold initiatives, assign work to specialist agents, and render live widgets in-line.
workspace-ops
Adds workspace mapping, registry hygiene, plugin packaging, and a workspace-intel MCP bundle.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.