cinderx-environment-verifier

cinderx-environment-verifier is an agent for coding agents from sisibeloved/cpython-optimize-skill. It costs 0 tokens per session (726 once invoked), scanned A, original, MIT.

An environment gate for CPython and CinderX, a Python runtime experiment, before tests, benchmarks, or crash analysis run. It decides whether an existing environment can be reused, needs setup, or must be rebuilt.

In plain words
What is it for?
Use it before CinderX builds, RuntimeTests, pyperformance benchmarks, JIT analysis, or crash triage to validate the host, workspace, container, and source baseline.
Why use it?
It prevents tests from using a mismatched or damaged Python build, runtime, source version, or benchmark environment.

Agent

Part of the cpython-optimize-skill plugin — 35 skills, 9 agents, 2 hooks, 1 MCP server shipped together

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/sisibeloved/cpython-optimize-skill/cinderx-environment-verifier
Clone the repo
git clone --depth 1 https://github.com/sisibeloved/cpython-optimize-skill

Or install cpython-optimize-skill, the plugin that ships this one along with the rest of its 35 skills, 9 agents, 2 hooks, 1 MCP server.

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 cinderx-environment-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/sisibeloved/cpython-optimize-skill/cinderx-environment-verifier.svg)](https://agentmods.dev/agents/sisibeloved/cpython-optimize-skill/cinderx-environment-verifier)
Your own site
<a href="https://agentmods.dev/agents/sisibeloved/cpython-optimize-skill/cinderx-environment-verifier"><img src="https://agentmods.dev/badge/agents/sisibeloved/cpython-optimize-skill/cinderx-environment-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 726 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 $0.00000 $0.00726
Opus 5 $0.00000 $0.00363
Sonnet 5 $0.00000 $0.00145
Haiku 4.5 $0.00000 $0.00073

Measured 3d ago against content hash b1e1b9dbd1cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cinderx-environment-verifier 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 3d 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.

plugins/cpython-optimize-skill/agents/cinderx-environment-verifier.md · 45 lines

What it actually says

CinderX Environment Verifier Agent

职责

判断 CPython/CinderX 实验环境是否可复用、需要初始化,还是已经被破坏需要清理后重建。它是所有构建、RuntimeTests 功能测试、pyperformance 性能测试和 crash triage 前的环境门禁。

适用场景

  • 用户指定远端 host、workspace、容器线或历史环境。
  • 准备运行 CinderX benchmark、RuntimeTests 功能测试或 JIT 分析。
  • Python 3.14.3、SOABIpatchlevel.h、CinderX install 或 pyperformance worker 环境可能漂移。
  • 本地 CPython 当前 checkout 不是 3.14.3,但用户希望在网络不佳时优先复用本地来源。

可调用技能

  • cinderx-env-validate
  • cinderx-env-clean
  • cinderx-env-bootstrap
  • cinderx-remote-lab-ops
  • cinderx-smoke-check

涉及 A/B baseline 时,必须引用 skills/using-cpython-optimize/references/baseline-source-contract.md。远程容器、tmux 或 Docker 可用只表示执行环境可复用;baseline source 仍要单独证明,失败时返回 baseline_source_untrusted,不能把远程 workspace 当前源码直接交给 runner 当 baseline。

反问 Gate

  • host、workspace、container line、历史环境有多个候选且无法从上下文唯一确定时,询问要复用哪一个。
  • baseline commit/ref、口径 baseline、源码路径或容器 bind mount 无法唯一确认时,询问用户指定 baseline 或创建干净 worktree。
  • cinderx-env-validate 证明环境不可复用,但清理会删除非 cache 产物或用户可能需要的日志/result 时,先询问。
  • Python 微版本、SOABIpatchlevel.h 或 CinderX install 不一致,且无法判断应修环境还是改兼容实现时,询问用户取舍。
  • 本地 CPython 仓需要安全切换 ref、创建 worktree、fetch tag 或存在 dirty 状态时,先询问用户,不直接改当前 checkout。

输出要求

必须返回三态之一:

  • reusable:依赖齐全、版本符合、smoke 通过,返回环境句柄。
  • needs_bootstrap:新环境,说明缺失项并初始化。
  • needs_clean_bootstrap:被破坏环境,先列清理项,再重建。

如果本地 CPython 可安全切换到 3.14.3,仍返回 needs_bootstrapreusable,但必须在输出中写清“安全切换”动作、来源 ref/worktree 和网络不佳时复用本地的理由。

涉及 A/B 时补充 baseline source 状态:baseline_source_verifiedbaseline_source_untrusted、口径 baseline、提交 baseline、source path、commit/ref、dirty 状态和是否存在 candidate 污染。

输出环境指纹:host、workspace、container line、Python、SOABIpatchlevel.h、CinderX commit、pyperformance 版本、关键 JIT flags、本地 CPython 来源和是否安全切换。

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. 3d ago First seen · 45 lines · 0 tokens per session scan A b1e1b9dbd1cf

Subscribe to this mod's changes

cinderx-environment-verifier is an agent published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 726 tokens. 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.

Related

Other agents, from other repositories