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/proposal-tick)<a href="https://agentmods.dev/commands/autoresearch-factory/agon/proposal-tick"><img src="https://agentmods.dev/badge/commands/autoresearch-factory/agon/proposal-tick.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 5.1 | $0.00020 | $0.01650 |
| Opus 5 | $0.00010 | $0.00825 |
| Sonnet 5 | $0.00004 | $0.00330 |
| Haiku 4.5 | $0.00002 | $0.00165 |
Grade A, and why
proposal-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 8d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dispatcher. You run proposal refine loops by delegating all domain work to subagents. 你只负责 dispatch, 不负责任何具体研究、审稿、文献调研或写作工作。
Pipeline
A. 准备
- 调用
env-validatorsubagent. 如果它报告了任何问题, 必须停下来提醒用户. - 阅读 ${CLAUDE_PLUGIN_ROOT}/references/project_manual.md 理解项目结构. 确认用户提供了至少一个 idea slug. 如果没有提供, 停下来提醒用户.
- 阅读 ${CLAUDE_PLUGIN_ROOT}/references/dispatch_manual.md 理解如何用命令行启动 claude/claude-* 和 codex subagent.
- 从 local settings 提取
parallelism/refiner_model/reviewer_model/lit_tick_model, 并告知用户.
B. 续跑检查: 对每个 slug, 若最新版 proposal 已存在但没有 <review ...> 块, 先派一次 proposal-reviewer 补 review (同样受 {parallelism} 限制). review 补完后若尚未满足终止条件, 跑一次 proposal deep-lit (见下方"运行一次 proposal deep-lit"), 让下一轮 refiner 能读到新文献上下文.
C. proposal refine loop, 对所有 slug 并行执行 proposal-refiner -> proposal-reviewer -> deep-lit 循环:
- 循环主体: 先调用
proposal-refinersubagent, 再调用proposal-reviewersubagent. 若尚未满足终止条件, 跑一次 proposal deep-lit, 然后进入下一轮 refiner. - 每个 slug 的终止条件:
current_version >= 3或最新版 proposal 的<review>块## Verdict字段 ==READY - 每个 slug 执行完一次 refine-review(+deep-lit) loop 都要 git add -v / commit / push, 注意不要把不属于自己的更改带进去 (ideas/proposals.xml 是例外, 因为是共享文件, 所以你可以为了 commit 自己的带入别人的更改), commit msg 模板: "mmdd proposal refine: {slug} (v{N}, verdict: {verdict})"
- reviewer 有时候会中道崩殂, 每个 reviewer 完成后你要检查最新版 proposal 文件最后有
<review ...>块并且 proposals.xml 对应条目的 score 已更新. 如果没有完成, 就 resume 原 agent 让它继续干.
循环结束后, 向用户汇总 subagents 抱怨的各种问题.
Refinery Skills
每次 dispatch 前，根据子代理角色从 skills_aris/ 中选 3-5 个最相关的 refinery mindset，将完整路径列表拼入 dispatch message 的 {MANDATORY_SKILLS_LIST}。
派发 subagent 时的提示词
proposal-refiner: 如果 proposal 完全不存在用"Write proposal for idea {slug}. CLAUDE_PLUGIN_ROOT=${CLAUDE_PLUGIN_ROOT}。你必须先 Read 以下 refinery mindset：{MANDATORY_SKILLS_LIST}。此外你可以通过 Skill 工具加载 aris catalog 自行增量。", 否则用"Revise the latest proposal for idea {slug}. CLAUDE_PLUGIN_ROOT=${CLAUDE_PLUGIN_ROOT}。你必须先 Read 以下 refinery mindset：{MANDATORY_SKILLS_LIST}。此外你可以通过 Skill 工具加载 aris catalog 自行增量。"proposal-reviewer:"Review the latest proposal for idea {slug}. CLAUDE_PLUGIN_ROOT=${CLAUDE_PLUGIN_ROOT}。你必须先 Read 以下 refinery mindset：{MANDATORY_SKILLS_LIST}。此外你可以通过 Skill 工具加载 aris catalog 自行增量。"
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.
- 8d ago First seen · 72 lines · 20 tokens per session scan A c716df39db24
proposal-tick is a command published in the GitHub repository AutoResearch-Factory/Agon (46 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 1,650 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
service-check
Request each agent to run a self-diagnostic to validate their runtime setup.
compatibility-audit
Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.
schedules
Quick overview of all schedules across the platform.
stop
Command "stop" from Abilityai/trinity, covering stop agent, usage, instructions, agent stop: {agent-name} and safety checks.
dashboard-session-diff
Show file changes (git diff) for a session by id-prefix. Usage /dashboard:session-diff . Runs locally, no LLM.
dashboard-session-tell
Send a prompt to another session. Usage /dashboard:session-tell.