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/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/thanos)<a href="https://agentmods.dev/plugins/synaptiai/synapti-marketplace/thanos"><img src="https://agentmods.dev/badge/plugins/synaptiai/synapti-marketplace/thanos/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/synaptiai/synapti-marketplace/thanos"><img src="https://agentmods.dev/badge/plugins/synaptiai/synapti-marketplace/thanos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
thanos 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 4d 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": "thanos",
"version": "0.1.0",
"description": "Read-only simplicity reviewer for code diffs, design documents and architecture, applying Steve Jobs's philosophy: remove everything that isn't essential until what remains feels inevitable. /snap reviews a diff, files or a design doc; /rethink redesigns a subsystem from its essence. Never edits files. Requires bash and git; on Windows, run Claude Code with Git Bash.",
"author": {
"name": "Synapti AI",
"url": "https://github.com/synaptiai"
},
"license": "Apache-2.0",
"keywords": [
"code-review",
"design-review",
"architecture",
"simplicity",
"read-only"
],
"repository": "https://github.com/synaptiai/synapti-marketplace",
"homepage": "https://github.com/synaptiai/synapti-marketplace/tree/main/plugins/thanos"
}
What it installs
The manifest is a name and a version. 1 skill, 2 commands, 1 agent travel with it, and installing the plugin installs all of them — 162 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.
- 4d ago First seen · 20 lines scan A 96ce18233a30
thanos is a plugin published in the GitHub repository synaptiai/synapti-marketplace (7 stars, last pushed 4d 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 2026-10-16.
Other plugins, from other repositories
second-opinion-honesty
Independent adversarial honesty reviewer for a DRAFT output: checks claims-vs-evidence (no fabrication, no overreach, no invented IDs) before a human approves. FULL mode reads an agentic-sop-kit run dir's trace; DEGRADED mode reviews any plain document with user-supplied inputs. Deterministic honesty checks in code +…
aspark marketplace
Marketplace for aSPARK — an agile AI product team for Claude Code (Specify, Plan, Act, Review, Keep).
alon-skills
Architecture, code review, prompting, and decision-making skills tuned to Alon Baron's engineering style: model-first, failure-path-aware, YAGNI. v3: six skills rewritten for Claude Fable 5.1 as judgment rules, a build-loop workflow that builds TODOWORKFLOW.md rows unattended, a claude plugin eval suite, and (3.1) a t.
x-dev-pipeline
Structured dev workflow with spec, user-global risk RAG, task breakdown, execution, verify, qa-gate, fix loops, and audits.
pocketto marketplace
Pocket-driven development skills for Claude Code.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.