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/gaoguobin/codex-eide-rebuildWrote 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/commands/gaoguobin/codex-eide-rebuild/eide-rebuild)<a href="https://agentmods.dev/commands/gaoguobin/codex-eide-rebuild/eide-rebuild"><img src="https://agentmods.dev/badge/commands/gaoguobin/codex-eide-rebuild/eide-rebuild.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.00310 |
| Opus 5 | $0.00016 | $0.00155 |
| Sonnet 5 | $0.00006 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
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 7d 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
Run the shared EIDE rebuild runner for the provided path. Default to direct execution for normal single-project requests because the runner returns minimal JSON and writes full logs to resultPath.
- If an argument is present, use it as the workspace or project path.
- If no argument is present, infer the current project path only when the current working directory contains exactly one
.code-workspacefile. - For normal single-project requests, execute:
python ~/.codex/codex-eide-rebuild/runtime/python/eide_rebuild.py rebuild $ARGUMENTS --stdout minimal
- Use the
eide-rebuildsubagent only when the user explicitly asks for subagent/delegated/background work, or explicitly asks to run independent projects in parallel. - Never run multiple rebuild workers against the same project/build directory concurrently.
- Return only a low-noise summary from minimal JSON:
ok,exitCode,errorCode,summary,targetNames, failure count, diagnostic count, artifact count, andresultPath. - Do not paste full logs or long artifact lists on success. Read
compilerLog,steps,artifacts, andtranscriptfromresultPathonly on failure or explicit request.
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.
- 7d ago First seen · 20 lines · 32 tokens per session scan A 6f6c7f4c1282
eide-rebuild is a command published in the GitHub repository gaoguobin/codex-eide-rebuild (5 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 310 once invoked, about $0.0002 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.
Other commands, from other repositories
spec-bugfix
Start a new bugfix spec with structured bug analysis, design, and tasks.
debug
Systematic debugging — 4-phase root cause process with defense-in-depth verification.
zoom-out
Zoom out and provide a high-level map of modules and callers for unfamiliar code.
orient-trace
Trace one execution path — entry point to edges — with file:line refs.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
fix
Universal debugging and fix application with semantic code analysis.