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/wangsiyi7/codex-reasoning-reactorWrote 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/mcp/wangsiyi7/codex-reasoning-reactor/reasoning-budget-reasoning-budget)<a href="https://agentmods.dev/mcp/wangsiyi7/codex-reasoning-reactor/reasoning-budget-reasoning-budget"><img src="https://agentmods.dev/badge/mcp/wangsiyi7/codex-reasoning-reactor/reasoning-budget-reasoning-budget/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/mcp/wangsiyi7/codex-reasoning-reactor/reasoning-budget-reasoning-budget"><img src="https://agentmods.dev/badge/mcp/wangsiyi7/codex-reasoning-reactor/reasoning-budget-reasoning-budget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
reasoning-budget 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 10d 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
{
"reasoning-budget": {
"command": "node",
"args": [
"${PLUGIN_ROOT}/scripts/mcp-server.mjs"
],
"env": {
"REASONING_BUDGET_HOME": "${CODEX_HOME}/reasoning-budget"
}
}
}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.
- 10d ago First seen · 11 lines scan A 3406eee09b9f
reasoning-budget is an MCP server published in the GitHub repository wangsiyi7/codex-reasoning-reactor (0 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
memorywhale
MCP server "memorywhale" as configured in wuisabel-gif/MemWhale. Launched with mw-mcp.
th-memory-mcp
Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor. Runs locally from the th-memory-mcp npm package.
pdf-card-mcp
Local-first MCP server and CLI for turning PDFs into source-linked HTML readers with notes, highlights, and static publishing. Runs locally from the pdf-card-mcp Python package.
otito
Deterministic local repository context, impact analysis, and merge-readiness evidence for AI agents. Runs locally from the @bashbop/otito npm package.
acr
ACRCms is an open source Python web content management system based on Turbogears and libacr. Runs locally from the acr Python package.
repogrammar
Local implementation-pattern context for coding agents. Runs locally from the @sioyooo/repogrammar npm package.