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.
/plugin marketplace add AutoResearch-Factory/Agon/plugin install agonWrote 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/autoresearch-factory/agon/experiment-tick)<a href="https://agentmods.dev/commands/autoresearch-factory/agon/experiment-tick"><img src="https://agentmods.dev/badge/commands/autoresearch-factory/agon/experiment-tick/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/commands/autoresearch-factory/agon/experiment-tick"><img src="https://agentmods.dev/badge/commands/autoresearch-factory/agon/experiment-tick.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 | $0.00025 | $0.03683 |
| Opus 5 | $0.00013 | $0.01842 |
| Sonnet 5 | $0.00005 | $0.00737 |
| Haiku 4.5 | $0.00003 | $0.00368 |
Grade A, and why
experiment-tick 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dispatcher. 你推进一个 scientist -> screener -> coder -> auditor -> scientist -> ... -> reviewer 的实验产线. 你不做领域推理, 不分析实验结果, 不判断代码质量, 不评估论文, 不直接跑远端实验.
Constants
ROOT = ${CLAUDE_PLUGIN_ROOT}
准备
- 确认用户提供了 slug/path; 没有就停下.
- 调用
env-validator: workspace_slug_or_path: {workspace_slug_or_path}. 若报告问题, 停下提醒用户. - 检查
mcp-communicator-telegram是否可用; 若可用, 后续严格执行 "如果 mcp-communicator-telegram 可用" 章节. - 阅读 ${ROOT}/references/project_manual.md 理解项目结构. 阅读 ${ROOT}/references/experiment_manual.md 理解实验工厂规范, 特别是 frontmatter.phase 和 run.phase 两张状态图.
- 阅读 ${ROOT}/references/dispatch_manual.md 理解如何用命令行启动 claude/claude-* 和 codex subagent.
- 如果
workspace/{slug}/STATE.md不存在(第一次启动):- cp/ln -s 四份上游材料到 workspace:
- 对应 topic (从 idea frontmatter
topic:字段读路径) →workspace/{slug}/topic.md - 对应 landscape (从 idea frontmatter
landscape:字段读路径) → 相对 symlink 到workspace/{slug}/landscape.md - 最新 idea (
ideas/{slug}.v*.md) →workspace/{slug}/idea.md - 最新 proposal (
ideas/{slug}-proposal.v*.md) →workspace/{slug}/proposal.md
- 对应 topic (从 idea frontmatter
- 对 idea.md 和 proposal.md 删除末尾
<review ...>块 (review 是上游工厂视角的历史评审, 留在 workspace 里会持续误导 experiment factory) - 分别从
${ROOT}/templates/{state,lessons,experiment-log,lit-feed}-template.md初始化(copy 之后再改)STATE.md,LESSONS.md,experiment-log.md,lit-feed.md(文献 inbox); 后三者的[slug]占位符替换为实际 slug
- cp/ln -s 四份上游材料到 workspace:
- 如果
workspace/{slug}/STATE.md存在, 进入workspace/{slug}后执行git pull, 同步合作者可能已经推送的更新. - 从 local settings 提取
model_routing_policy/scientist_model/screener_model/coder_model/auditor_model/reviewer_model/lit_tick_model, 并告知用户.
执行循环
参照 ${ROOT}/templates/state-template.md 和 ${ROOT}/references/experiment_manual.md 中 dispatcher 的职责推进.
你要积极推进实验进行(虽然你不做任何具体的工作). dispatch subagents 时, 科研层面不要指导 subagent -- subagent 内部的指令已经写得很清楚了. 调度层面 (分 run, 选 server, 定 coder 数) 是你的核心职责, 必须主动做.
每次 auditor 完成时, git add -v workspace/workspaces.xml servers_notes.md 之后 commit + push, 注意不要把不属于自己的更改带进去, commit msg 模板: "mmdd: {slug} auditor finished"
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.
- 3d ago Changed 93963939b5ea
- 9d ago First seen · 146 lines · 25 tokens per session scan A d7bf372a409d
experiment-tick is a command published in the GitHub repository AutoResearch-Factory/Agon (46 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 3,683 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.
Other commands, from other repositories
compatibility-audit
Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.
dashboard-session-diff
Show file changes (git diff) for a session by id-prefix. Usage /dashboard:session-diff . Runs locally, no LLM.
dashboard-session-unhide
Unhide a previously hidden session. Usage /dashboard:session-unhide.
dashboard-session-list
List all pi sessions (id, status, name, cwd). Runs locally, no LLM.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
me-cfd-review
Review thermal-fluid CFD setup, boundary conditions, mesh, wall treatment, convergence, validation, and whether the claims are supported.