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 skills add taxueseek/argo --skill local-seekgit 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/skills/taxueseek/argo/local-seek)<a href="https://agentmods.dev/skills/taxueseek/argo/local-seek"><img src="https://agentmods.dev/badge/skills/taxueseek/argo/local-seek/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/skills/taxueseek/argo/local-seek"><img src="https://agentmods.dev/badge/skills/taxueseek/argo/local-seek.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.02020 |
| Opus 5.5 | $0.00034 | $0.00808 |
| Sonnet 5.5 | $0.00017 | $0.00404 |
| Haiku 4.5 | $0.00008 | $0.00202 |
Grade A, and why
local-seek 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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
local-seek — 本地高效搜索（v1.6.0）
搜本机文件和内容就从这里开始。工具的输出就是答案，不用再自己翻一遍。 与 Argo（联网搜索）分工：Argo 搜网络，本技能搜本机。
三层递进：先定位、再看上下文、最后精读
不要一上来就读文件。一层层往里走，每层的结果都不多：
| 层 | 干什么 | 命令 | 输出量 |
|---|---|---|---|
| L1 定位 | 找到「在哪个文件」 | seek.py "词" --count 或 --filename | 每文件一行 |
| L2 上下文 | 看命中位置附近 | seek.py "词" --context 2 | 每命中 3 行 |
| L3 精读 | 读关键段落 | read_file 按行号局部读取 | 按需 |
每次搜索先想清楚停在哪一层，默认只做第一层。
统一入口
统一走 scripts/seek.py（相对 argo 根：sub-skills/local-seek/scripts/seek.py），
由它选工具，不要自己拼 rg/fd 参数：
# 以下以 argo 安装根为 cwd；或写死 $ARGO_HOME/sub-skills/local-seek/scripts/seek.py
python3 sub-skills/local-seek/scripts/seek.py "查询词" # 默认：当前目录全文
python3 sub-skills/local-seek/scripts/seek.py "查询词" --path ~/notes # 指定目录
python3 sub-skills/local-seek/scripts/seek.py "词" --path ~/.agents --dot # 连 . 开头目录与软链一起搜；搜 ~/.agents、~/.zcode 要加（Spotlight 收不到）
python3 sub-skills/local-seek/scripts/seek.py "词" --path . --include-noise # repos/、tests/ 等与真源平权（默认排真源之后，仍搜得到）
python3 sub-skills/local-seek/scripts/seek.py "查询词" --count # 先数命中，再决定是否深入
python3 sub-skills/local-seek/scripts/seek.py "查询词" --filename # 按文件名
python3 sub-skills/local-seek/scripts/seek.py "查询词" --spotlight # 全盘兜底（PDF/邮件/笔记）
python3 sub-skills/local-seek/scripts/seek.py "查询词" --type py,ts
python3 sub-skills/local-seek/scripts/seek.py "查询词" --json # 结构化输出
python3 sub-skills/local-seek/scripts/seek.py "查询词" --exact # 关闭中文扩展，精确匹配
python3 sub-skills/local-seek/scripts/seek.py "查询词" --exclude 某文件 # 额外排除（可重复）
python3 sub-skills/local-seek/scripts/seek.py --outline 文件路径 # 文件结构（def/class/标题/顶层key）
python3 sub-skills/local-seek/scripts/seek.py --lines 10-50 文件路径 # 按行读取，替代 read_file 全文
python3 sub-skills/local-seek/scripts/seek.py "裸except" --structural # 结构搜索（空catch/裸except/装饰函数等）
python3 sub-skills/local-seek/scripts/seek.py --git-log 文件路径 # 文件的最近提交历史
python3 sub-skills/local-seek/scripts/seek.py --git-blame 12 文件路径 # 第 12 行的提交归属
内置智能行为（固定字符串回退、中文 2-gram 扩展、PCRE2 检测、结构搜索、 git 联动等）自动生效，明细见 references/auto-behaviors.md。
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- config/domains.yaml 545 B
- references/auto-behaviors.md 1.8 KB
- references/fd-mdfind-recipes.md 1.5 KB
- references/git-integration.md 2.2 KB
- references/remote-handoff.md 1.9 KB
- references/rg-recipes.md 2.1 KB
- references/strategies.md 2.0 KB
- references/structural-search.md 2.8 KB
- scripts/eval_rank.py 9.9 KB runs code
- scripts/eval_seek.py 8.3 KB runs code
- scripts/seek_frecency.py 4.4 KB runs code
- scripts/seek_fts.py 19 KB runs code
- scripts/seek_rank.py 9.6 KB runs code
- scripts/seek.py 67 KB runs code
- tests/test_content_rank.py 9.3 KB runs code
- tests/test_determinism_20261006.py 6.5 KB runs code
- tests/test_noise_tier.py 4.1 KB runs code
- tests/test_pcre2_probe.py 5.4 KB runs code
- tests/test_rank_pinyin.py 2.4 KB runs code
- tests/test_regression_20261003.py 6.5 KB runs code
- tests/test_regression_20261006.py 5.9 KB runs code
- tests/test_seek_degradation.py 4.5 KB runs code
- tests/test_seek_fts.py 13 KB runs code
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.
- 10d ago Changed · +4 lines 6b8da3b9534a
- 18d ago Changed 963735a337ef
- 20d ago Changed eac6c2f6523c
- 25d ago Changed · +1 lines 40a28db9502b
- 1mo ago Changed · +1 lines 2d13f0998e93
- 1mo ago Changed · +6 lines · +84 tokens per session e8424ba4c4e1
- 1mo ago Changed 3c9c189d38d4
- 1mo ago First seen · 99 lines · 0 tokens per session scan A 497757d25579
local-seek is a skill published in the GitHub repository taxueseek/argo (205 stars, last pushed 2d ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,020 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 2026-08-30.
Other skills, from other repositories
aident-loadout
Run multi-step work across apps the user connected in Aident Loadout: live action schemas, connection checks, cost preflight, and approval before side effects.
vs-user-onboarding
Guide a brand-new SearchCLI/vs user from first-time usage questions to sign-up, purchase of Viking AI Search, AK/SK setup, and a working authenticated CLI. Use when the user says they downloaded or installed SearchCLI/vs and asks how to use it, how to start, sign up, buy, or onboard.
daily-report
Compile timestamped conversation logs, agent sessions, IM messages, collaborative documents, meeting notes, task records, and similar OpenViking materials into concise, evidence-grounded daily reports. Use with ov compile when the user asks for a daily work report, end-of-day digest, 日报, or reports for one or more…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
cron
Schedule reminders and recurring tasks.
checkpoint-and-recover
Checkpoint state before risky operations, detect anomalies, and recover gracefully.