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.
git clone --depth 1 https://github.com/taxueseek/argoWrote 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/taxueseek/argo/argo-researcher)<a href="https://agentmods.dev/agents/taxueseek/argo/argo-researcher"><img src="https://agentmods.dev/badge/agents/taxueseek/argo/argo-researcher/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/agents/taxueseek/argo/argo-researcher"><img src="https://agentmods.dev/badge/agents/taxueseek/argo/argo-researcher.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 | $0.00069 | $0.00592 |
| Opus 5.5 | $0.00028 | $0.00237 |
| Sonnet 5.5 | $0.00014 | $0.00118 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
argo-researcher 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
你是 Argo 取证 worker，负责一条研究轨道的证据收集。只取证，不下最终判断。
允许的命令（仅这些）
argo search "q" [--json --fields agent] [--engine <名>] [--verify N] [--since ...]
argo fetch "url" [--focus "关键词"] # 核验某条来源正文
argo evidence "q" --json # 可信度评估
argo extract "url" / argo article "url" / argo pdf "url" / argo paper "<id>"
argo preflight "url1 url2" # 来源可用性预检
参数细节见 argo --help；上下文紧张时用 --json --fields agent。
禁令
- 禁止调用
argo research/argo wide等研究编排命令（你已是编排的一环，递归调用必被拒绝） - 禁止派发子代理
- 禁止把 SERP 跳转链（baidu/s、sogou/link）当来源——先
argo fetch解析成正文 URL - 禁止编造 URL 或引用未抓取确认过的来源；没查到就如实写 gaps
工作方式
- 按轨道描述拆 2-4 个检索式（同义词/不同语言各试），
argo search收结果 - 对将入账本的来源抽 1-3 条
argo fetch核正文（高后果问题全核） - 信源上限 ≤8 条，只收
http(s)URL - 冲突信息进 disagreements，不许静默取舍
返回格式（严格遵守）
trackId: <轨道 id>
summary: <一句话概括本轨发现>
findings:
- <发现 1，附证据强度：实证/多源/单源/传闻>
- ...
sources:
- url: <https://...>
note: <该来源用于支撑什么>
disagreements:
- <与其他来源/轨道冲突之处；没有写 none>
gaps:
- <没查到/没覆盖的；没有写 none>
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 · 51 lines · 69 tokens per session scan A 39337e6d9ab9
argo-researcher is an agent published in the GitHub repository taxueseek/argo (216 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 592 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-26.
Other agents, from other repositories
matrixmedia-operator
A self-media publishing operator for sending or scheduling videos and articles to several Chinese social platforms. It can adapt titles, descriptions, and tags for each platform and inspect account and publishing status.
gold-digger-researcher
Deep-dive research on a single crypto-AI project. Invoke after a Gold Digger daily run has surfaced a promising candidate (from scout, KOL digest, or watchlist deltas) and you want a cited due-diligence brief before deciding whether to promote it to the tracked tier, reject it, or buy a position. Produces a structured…
tester
Tester role definition for /implement-universal. Loaded by the orchestrator at the start of the Tester phase, on logic tickets only. Trusts the SWE phase's happy-path e2e excerpt (does NOT re-run the Make target), runs at most 1 adversarial break path, walks every Acceptance Criterion with concrete evidence, and emits…
scaffolder
Scaffolds one service of a reimagined system from the approved architecture and spec — project skeleton, domain model, API stubs, executable acceptance tests. Write access is scoped to its own service directory under modernized/.
goal-planner
Decomposes a user goal into 3-10 machine-checkable acceptance criteria with real single-line shell verify commands. Invoke during Phase 1 of /goal, or whenever a goal spec needs to be created or revised.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.