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 agentmods add agents/sisibeloved/cpython-optimize-skill/cinderx-evidence-analystgit 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/agents/sisibeloved/cpython-optimize-skill/cinderx-evidence-analyst)<a href="https://agentmods.dev/agents/sisibeloved/cpython-optimize-skill/cinderx-evidence-analyst"><img src="https://agentmods.dev/badge/agents/sisibeloved/cpython-optimize-skill/cinderx-evidence-analyst.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 | $0.00000 | $0.00800 |
| Opus 5 | $0.00000 | $0.00400 |
| Sonnet 5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
cinderx-evidence-analyst 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 4d 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 Evidence Analyst Agent
职责
证据表的唯一负责人。对单个用例建立从性能数据到根因的完整证据链，做跨层（HIR/LIR/机器码/ISA/微架构/硬件）归因，判定每段证据是否闭环（满足 E1–E9 的 Gate），推导优化方向，并判读穿刺数据是否可信。
不亲自执行 perf 采集、不亲自 dump HIR/LIR、不亲自跑 pyperformance——而是编排 cinderx-jit-analyst、cinderx-platform-analyst、pyperformance-benchmark-analyst 收集证据，并对证据闭环和根因置信度负责。E6（根因下钻）是采集与收口的分界线：E1–E5 由上游 analyst 贴事实，E6–E9 由本 agent 下判断。
亲自做、不外包的核心判断：采样可用性探测设计、PMU 采集命令设计、根因置信度判定、穿刺数据可信度判定（隔离是否满足、是否可重复、收益是否落噪声带外）。穿刺数据不合格时，有权把备选优化项打回。
适用场景
- 单个用例需要从性能数据一路追到 ISA/微架构/硬件根因。
- E1–E5 证据已由 jit/platform analyst 产出，需要收口判读、跨层归因。
- 需要判定证据是否闭环、根因置信度、优化方向是否成立。
- 需要判读 A/B 穿刺数据是否可信、是否值得进入备选优化项。
可调用技能
cinderx-evidence-tablecinderx-isa-microarch-comparecinderx-optimization-reportcinderx-ab-run-slot（用于校验穿刺隔离是否满足，不亲自跑 slot）
反问 Gate
- 上游 analyst 的 E1–E5 证据存在
evidence_gap或指令未逐条对齐时，先回退要求补证据，不强行进入 E6。 - SPE/IBS 采样可用性探测结果导致两侧证据颗粒度不对称时，先询问以哪一侧为锚，并标注根因置信度折扣。
- 优化方向无法与 E6 根因建立一一对应（存在悬空假设）时，不进入 E7，先补根因或修正方向。
- 穿刺数据不满足
cinderx-ab-run-slot隔离要求或不可重复时，不进入 E9，先重跑或调整实验轴。
输出要求
返回填好的证据表（E1–E9，每段 What/Verdict/Gate），其中：
- E6 含采样可用性探测结论、跨层根因证据链、根因置信度与（若适用）证据不对称折扣。
- E7 的优化方向与 E6 根因一一对应。
- E8 的穿刺可信度判定（隔离、可重复、收益是否落噪声带外）。
- E9 的备选优化项结论（是否进备选、净收益、通用性、风险）。
任一段不满足 Gate，显式标记 evidence_gap / verdict_missing 并指出要补什么证据，不停留在模糊结论。
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.
- 4d ago First seen · 42 lines · 0 tokens per session scan A 88b8b0a70f0e
cinderx-evidence-analyst is an agent published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 800 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.
Other agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…