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/RoninForge/budgetclawWrote 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/roninforge/budgetclaw/plugin)<a href="https://agentmods.dev/plugins/roninforge/budgetclaw/plugin"><img src="https://agentmods.dev/badge/plugins/roninforge/budgetclaw/plugin/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/roninforge/budgetclaw/plugin"><img src="https://agentmods.dev/badge/plugins/roninforge/budgetclaw/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
budgetclaw 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": "budgetclaw",
"version": "0.1.0",
"description": "Zero-key Claude Code cost tracking, per project and per branch. Budget caps with SIGTERM enforcement, reads your local ~/.claude session logs, and syncs to a hosted team dashboard (Goei).",
"author": {
"name": "RoninForge",
"url": "https://github.com/RoninForge"
},
"homepage": "https://roninforge.org",
"repository": "https://github.com/RoninForge/budgetclaw",
"license": "MIT",
"keywords": [
"spend-monitor",
"budget",
"cost",
"claude-code",
"telemetry",
"claude-ai",
"ccusage",
"cost-tracking",
"usage-tracking",
"token-usage",
"claude-code-analytics",
"claude-tracker",
"claude-max",
"claude-subscription",
"cost-dashboard",
"ai-spend",
"llm-cost",
"multi-machine",
"team",
"burn-rate"
],
"skills": "./skills/",
"hooks": "./hooks/hooks.json"
}
What it installs
The manifest is a name and a version. 1 skill, 1 hook travel with it, and installing the plugin installs all of them — 56 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.
- 1mo ago First seen · 37 lines scan A b246417b86e1
budgetclaw is a plugin published in the GitHub repository RoninForge/budgetclaw (8 stars, last pushed 9d 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
engram
Durable, local-first graph memory for AI coding assistants: decisions with reasons, gotchas, conflicts — inspectable and editable in a graph pane.
fleetline
A hardened statusline for Claude Code — closes two vectors a statusline is structurally exposed to: git core.fsmonitor RCE from a cloned repo, and ANSI/OSC injection from session-derived text, both fixed and verified at the byte level. Every segment is independently repositionable with your own separator (not just…
gpt-image-cookbook
Multi-provider AI image generation cookbook: gallery-first prompt patterns, reference-image editing workflows, and a packaged CLI for OpenAI, Google Imagen, Flux, and other image providers. Built for Claude Code, Codex, OpenClaw, and other skill-capable agent runtimes.
dding-dong
A Claude Code notification plugin that uses sounds and operating-system alerts when work finishes, fails, or needs input.
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
handbook-agent-spec-kit
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation.