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.
npx skills add sisibeloved/cpython-optimize-skill --skill cinderx-ab-run-slotgit clone --depth 1 https://github.com/sisibeloved/cpython-optimize-skillWrote 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/skills/sisibeloved/cpython-optimize-skill/cinderx-ab-run-slot)<a href="https://agentmods.dev/skills/sisibeloved/cpython-optimize-skill/cinderx-ab-run-slot"><img src="https://agentmods.dev/badge/skills/sisibeloved/cpython-optimize-skill/cinderx-ab-run-slot/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/skills/sisibeloved/cpython-optimize-skill/cinderx-ab-run-slot"><img src="https://agentmods.dev/badge/skills/sisibeloved/cpython-optimize-skill/cinderx-ab-run-slot.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.00771 |
| Opus 5 | $0.00023 | $0.00385 |
| Sonnet 5 | $0.00009 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
cinderx-ab-run-slot 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 9d 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
CinderX A/B Run Slot
给 orchestrator 和 pyperformance runners 使用。它只负责 A/B 资源切分,不解释性能结果。
Slot 内容
- baseline slot:commit、容器线、Python、CPU affinity、结果目录、日志路径。
- candidate slot:commit、容器线、Python、CPU affinity、结果目录、日志路径。
- 互斥资源:CPU set 不重叠,tmux pane 不共享,build dir 不共享,
run.json输出不覆盖。
Baseline Source 门禁
- 先读取
../using-cpython-optimize/references/baseline-source-contract.md。 - baseline slot 必须绑定
baseline_source_verified:口径 baseline、提交 baseline、source path、commit/ref、git status --short、patchlevel.h、SOABI和容器 bind mount 都已确认。 - 远程环境、容器线或 tmux pane 可用不等于 baseline 源码可信;不能把远程 workspace 当前源码直接当 baseline。
- 若 baseline ref 不明、dirty 状态未解释、bind mount 指向不明或混入 candidate editable install,返回
baseline_source_untrusted,不分配正式 A/B slot。
并行前检查
- verifier 已确认环境可复用或已 bootstrap。
- verifier 已确认 baseline source verified;只有执行环境 reusable 不够。
- baseline/candidate 只在目标变量上不同。
- 先读取
../using-cpython-optimize/references/pyperformance-affinity-guidance.md,确认--affinity/taskset使用当前可用 CPU,而不是逐字照抄用户命令里的不可用高核号。 - 绑核策略写清,例如
--affinity=0-7与--affinity=8-15,或taskset -c 0-7与taskset -c 8-15。 - 分配前查
nproc、lscpu、taskset -pc $$和容器 cpuset;baseline/candidate 的 CPU set 数量尽量一致且不重叠。 - 可用 CPU 不足以并行隔离时,改为串行执行,并让 baseline/candidate 复用同一实际 affinity。
cinderx-test与cpython-baseline使用场景明确。
反问 Gate
- baseline/candidate 的唯一差异轴不明确时,询问要比较的变量。
- baseline source 不是
baseline_source_verified时,询问用户指定 baseline、创建干净 worktree 或重建cpython-baseline。 - CPU set、tmux pane、结果目录或容器线无法安全分离时,询问串行执行还是重新分配资源。
- 用户给出的真实命令 affinity 在当前环境不可用,且无法自动映射出可比 CPU set 时,询问是否接受重映射或换环境。
- 用户要求并行但环境 verifier 未确认可并行时,询问是否先做环境审计。
输出
返回两个 run slot、baseline source 状态、原始/实际 affinity、可用 CPU 证据和是否允许并行。无法保证 baseline 可信或资源隔离时,要求修复 baseline 或串行执行。
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.
- 9d ago First seen · 45 lines · 47 tokens per session scan A 4a95b8a46932
cinderx-ab-run-slot is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 11d ago), licensed MIT. It adds 47 tokens to every session and 771 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 skills, from other repositories
verify
Build the computer-use-demo image and drive the Streamlit UI headlessly to verify changes end-to-end.
test-locally
Build and deploy a full local OpenMetadata stack with Docker to test your connector in the UI. Handles code generation, build optimization, health checks, and guided testing.
redamon-testing
How RedAmon tests actually run and how to author them: the per-file Docker gate, the unit/integration/live tiers, and the failure modes that make a green run a lie. Trigger: editing any test.py, .test.ts(x) or tests/.sh; a test that is red, skipped or xfailed; a request to "run the tests", "make it green" or check…
zero-script-qa
Zero Script QA — test without scripts using structured JSON logging and Docker monitoring. Triggers: zero-script-qa, log testing, docker logs, QA.
local-test
Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.
testcontainers-integration-tests
Write integration tests using TestContainers for .NET with xUnit. Covers infrastructure testing with real databases, message queues, and caches in Docker containers instead of mocks.