eide-rebuild

eide-rebuild is an agent for Claude Code, Codex from gaoguobin/codex-eide-rebuild. It costs 19 tokens per session (268 once invoked), scanned A, original, MIT.

A delegated build worker for rebuilding Embedded IDE for VS Code projects. It runs the project rebuild and returns a short JSON result while keeping detailed results in a separate file.

In plain words
What is it for?
Use it to rebuild a specified Embedded IDE for VS Code workspace or project and inspect detailed logs only when needed.
Why use it?
It keeps lengthy compiler output out of the main conversation and gives the parent agent the key build facts first.

Agent for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions Codex.

Install

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.

agentmods
npx agentmods add agents/gaoguobin/codex-eide-rebuild/eide-rebuild
Clone the repo
git clone --depth 1 https://github.com/gaoguobin/codex-eide-rebuild

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for eide-rebuild

README.md
[![agentmods](https://agentmods.dev/badge/agents/gaoguobin/codex-eide-rebuild/eide-rebuild.svg)](https://agentmods.dev/agents/gaoguobin/codex-eide-rebuild/eide-rebuild)
Your own site
<a href="https://agentmods.dev/agents/gaoguobin/codex-eide-rebuild/eide-rebuild"><img src="https://agentmods.dev/badge/agents/gaoguobin/codex-eide-rebuild/eide-rebuild.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 268 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00268
Opus 5 $0.00010 $0.00134
Sonnet 5 $0.00004 $0.00054
Haiku 4.5 $0.00002 $0.00027

Measured 6d ago against content hash ff2aec01b8af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

eide-rebuild 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 6d 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.

integrations/claude-code/agents/eide-rebuild.md · 23 lines

What it actually says

You are a focused EIDE rebuild worker.

  • Resolve the workspace or project path from the user request.
  • Run the shared Python runner:
python ~/.codex/codex-eide-rebuild/runtime/python/eide_rebuild.py rebuild <workspace-or-project-path> --stdout minimal
  • Return the minimal JSON stdout and keep your own summary short and factual.
  • Return only low-noise build facts: ok, exitCode, errorCode, summary, targetNames, failure count, diagnostic count, artifact count, and resultPath.
  • Do not paste the full result JSON, full logs, or long artifact lists into the parent conversation.
  • Preserve the resultPath from stdout so the parent can inspect the full JSON, compilerLog, steps, artifacts, and transcript only when needed.
  • Treat artifact hashes as identity/provenance data only. Do not infer build success or failure from hash differences across rebuilds unless the parent explicitly asks for deterministic rebuild analysis.
  • Do not run multiple rebuild workers against the same project/build directory concurrently.
Changes

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.

  1. 6d ago First seen · 23 lines · 19 tokens per session scan A ff2aec01b8af

Subscribe to this mod's changes

eide-rebuild is an agent published in the GitHub repository gaoguobin/codex-eide-rebuild (5 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 268 once invoked, about $0.0001 per session on Opus 5. 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.