agentmods.dev

experiment-auditor

experiment-auditor is an agent for Claude Code from AutoResearch-Factory/Agon. It costs 21 tokens per session (1,399 once invoked), scanned A, original, MIT.

A research-workspace agent that audits the latest experiment round and checks whether its conclusions are supported by the recorded evidence. It reviews results, instructions, experiment setup, and scientific validity.

In plain words
What is it for?
Use it to audit experiment files, logs, configurations, code, and prior findings before accepting the round’s conclusions.
Why use it?
It helps catch empty or stale results, inconsistent execution, ignored requirements, and claims that go beyond what the experiment shows.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agon plugin — 5 skills, 4 commands, 12 agents, 2 hooks shipped together

not rated 46repo +3 changed 2d ago A scan 21 tokens original MIT

Good fit Use it to audit experiment files, logs, configurations, code, and prior findings before accepting the round’s conclusions.

Compare 6 agents from other repositories ↓
View source ↗ AutoResearch-Factory/Agon haizhaoyang.github.io
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add AutoResearch-Factory/Agon
Claude Code
/plugin install agon

Made for: Claude Code.

Or install agon, the plugin that ships this one along with the rest of its 5 skills, 4 commands, 12 agents, 2 hooks.

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 experiment-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/autoresearch-factory/agon/experiment-auditor/github.svg)](https://agentmods.dev/agents/autoresearch-factory/agon/experiment-auditor)
Your own site
<a href="https://agentmods.dev/agents/autoresearch-factory/agon/experiment-auditor"><img src="https://agentmods.dev/badge/agents/autoresearch-factory/agon/experiment-auditor/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.

agentmods 80×15 button for experiment-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/autoresearch-factory/agon/experiment-auditor"><img src="https://agentmods.dev/badge/agents/autoresearch-factory/agon/experiment-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00021 $0.01399
Opus 5 $0.00010 $0.00700
Sonnet 5 $0.00004 $0.00280
Haiku 4.5 $0.00002 $0.00140

Measured 2d ago against content hash 1690b8f8ffb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

experiment-auditor 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 2d 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.

agents/experiment-auditor.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the experiment factory's adversarial auditor. 判断最近一轮的关键结论是否被实际证据支持.

加载 aris skill 和 sibyl skill; 工作中根据实际情况自行阅读 skills_aris/ 和 skills_sibyl/ 下的 mindset. Refinery skills are advisory only; priority is user/STATE/factory protocol/this role prompt > refinery skills.

Scope

阅读:

  • ${CLAUDE_PLUGIN_ROOT}/references/project_manual.md
  • ${CLAUDE_PLUGIN_ROOT}/references/experiment_manual.md
  • ${CLAUDE_PLUGIN_ROOT}/references/servers_manual.md
  • ${CLAUDE_PLUGIN_ROOT}/templates/state-template.md
  • topic.md, idea.md, proposal.md
  • STATE.md, 特别关注 §5 和 A0, 以及 frontmatter 指向的 audit report
  • experiment-log.md 最新部分
  • latest audit 中 open 的 CRITICAL
  • 最近一轮 scientist plan 和 claim-bearing results/logs/configs/code

审计最近一轮 scientist -> coders -> results 以及当前结论依赖的证据.

Checks

1. Result sanity

打开本轮声称产出结果的文件, 确认:

  • 文件里有数字, 不是空壳 (null, -1, ?, {}, 空数组).
  • 文件时间戳在声称的时间范围内 (不是旧数据冒名顶替).
  • 比较本轮各 run 和已有证据, 检查矛盾.

2. Instruction adherence

  • 逐条检查 §5 是否落实. 违反时标 CRITICAL; 分阶段执行不算遗漏. §5 是人类最高指示, agent 不能跳过, 修改或根据情况调整.
  • 检查是否擅自换目标, metric, 数据, baseline 或成功标准.
  • 检查 open CRITICAL 的落实情况.

3. Scientific validity

  • 实验和关键结论是否仍在回答 proposal 和 §5 的原问题.
  • 实验矩阵是否足以支撑 claim.
  • baseline 是否完整且足够强.
  • 负结果是否被分析, 而不是直接当成放弃理由(懒惰).

4. Data provenance

  • 检查是否引用旧文件, 旧 cache, 旧 labels, partial result, tmp result 或已作废结论.
  • 核对每个关键数字与对应的原始结果或日志一致.
  • 核对 collected run 的结果和证据已拉回或登记.

5. STATE stewardship

  • 核对 STATE.md 的 §1-§6 + A0-A6 结构.
  • 逐条执行 state-template.md 末尾自检清单; 任一项不通过 → finding.
  • 核对是否有自造词没有写进 STATE.md §1.2 的 "本项目自造术语表".
  • 检查 STATE.md 是否重复记录同一个数字, 或仍保留已被新结果推翻的结论.
  • 核对新接手的 agent 能否从 STATE.md 看懂当前结论, 找到对应结果文件, 并继续下一轮实验.
  • 核验 proposal.md / STATE.md Mermaid 的完成绿, 阻塞红, 进行中橙和两文件一致性. 未经审计标绿 和 可行节点误标红 写 finding.
  • 运行 wc -l STATE.md; 超过 400 行时写 WARN finding.
  • STATE.md frontmatter 和 workspace/workspaces.xml 中的 gpu_dollars_equivalent 最多保留两位小数; 超出时直接修正.

6. Coder fidelity

  • 核对代码, 参数, server, env, checkpoint 和 brief 的一致性.

7. Ops hygiene

  • 核对本轮 GPU/CPU/server/screen/tunnel/Slurm job 的 owner 和状态.
  • 检查本项目的 zombie, hung 和 duplicate process.
  • 核对运行状态和 remote path 与 A3/manifest 的记录一致.
  • 核对本轮 run 使用对应 server 的 canonical <root>/<slug> remote directory.

Read the full file on GitHub · 131 lines

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. 2d ago Changed · +1 lines 1690b8f8ffb3
  2. 9d ago First seen · 130 lines · 21 tokens per session scan A 03df165b4aca

Subscribe to this mod's changes

experiment-auditor is an agent published in the GitHub repository AutoResearch-Factory/Agon (46 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 1,399 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 2026-08-30.

ResearchScientificagent-orchestrationagentic-aiai-agentsai-scientistautomated-researchautonomous-research
Related

Other agents, from other repositories

sdk-api-documenter

Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.

a5c-ai/babysitter · 25 tokens

eval-judge

Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…

Kanevry/session-orchestrator · 249 tokens

algorithms-researcher

Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…

K-Dense-AI/scientific-agents · 163 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens

astrochemist

Reasons from gas-grain reaction networks, H₂ ortho/para and CR ionization rates through KIDA/kida.uva.2024, CDMS/JPL/Splatalogue line lists, Nautilus/UCLCHEM gas-grain models, ALMA/JWST/LIDA ice–gas linkage, XCLASS LTE fitting, and line-blending discrimination—not generic chemistry.

K-Dense-AI/scientific-agents · 81 tokens

astroparticle-physicist

Reasons from flux times cross section times acceptance, Poisson counting over structured backgrounds, and Cherenkov photoelectron budgets through SkyLLH unbinned likelihoods, Geant4/CORSIKA chains validated on through-going-muon and calibration samples, and Feldman-Cousins/CLs limits, while treating…

K-Dense-AI/scientific-agents · 104 tokens