duckduckgo

duckduckgo is a skill for Claude Code, Codex from Stahl-G/briefloop. It costs 55 tokens per session (1,808 once invoked), scanned A, original, MIT.

A DuckDuckGo search worker for BriefLoop research tasks. It finds public sources, saves readable source text through the workspace tools, and passes source IDs and evidence to the next research stage.

In plain words
What is it for?
Use it to scout events, identify important entities, locate original announcements, verify facts, and repair specific evidence gaps in a research run.
Why use it?
It provides a recorded route from search results to checked source material instead of treating snippets or search rankings as proof. It also follows shared budgets and stops when the allowed research capacity is exhausted.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to scout events, identify important entities, locate original announcements, verify facts, and repair specific evidence gaps in a research run.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stahl-g/briefloop/duckduckgo
Install

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.

Any agent
npx skills add Stahl-G/briefloop --skill duckduckgo
Clone the repo
git clone --depth 1 https://github.com/Stahl-G/briefloop

Made for: Claude Code, Codex.

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 duckduckgo

README.md
[![agentmods](https://agentmods.dev/badge/skills/stahl-g/briefloop/duckduckgo/github.svg)](https://agentmods.dev/skills/stahl-g/briefloop/duckduckgo)
Your own site
<a href="https://agentmods.dev/skills/stahl-g/briefloop/duckduckgo"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/duckduckgo/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 duckduckgo

Your own site · 80×15
<a href="https://agentmods.dev/skills/stahl-g/briefloop/duckduckgo"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/duckduckgo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,808 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 $0.00055 $0.01808
Opus 5.5 $0.00022 $0.00723
Sonnet 5.5 $0.00011 $0.00362
Haiku 4.5 $0.00006 $0.00181

Measured 1mo ago against content hash 0434d16b731c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

duckduckgo 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 1mo 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.

src/briefloop/skill_assets/duckduckgo/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DuckDuckGo 来源检索

你是承担检索任务的 Scout。围绕分配的主题、主体、时间窗口和证据缺口,自主决定查询、筛选和阅读顺序。调用下面的工作区 CLI,由 Python 完成网页访问和来源保存;DuckDuckGo 免密钥,不需要读取、输出或传递任何 API Key,也不要绕开本工具手写 HTTP 请求。

共享预算

本轮各 Scout 共用同一份受控工具硬预算。web-search 请求在调用前扣额,失败也计次数;候选 URL 按去重 URL 累计;全文抓取按唯一 URL 计页,同 URL 回退与缓存不重复扣页。每次结果中的 budget/remaining 是共享当前状态。

收到 status=budget_exhausted 时停止新增检索,保留已经核对的证据并简短说明缺口,不重复尝试绕过。并发搜索响应超出剩余候选名额时,工具会明确给出 unadmitted_urls 和完整 discovery_path;这些是待扩额后检查的发现记录,不自行打开并当作已准入候选继续扩大研究。不要绕到原生搜索或手写 HTTP 请求避开预算。

检索节奏:侦察 → 聚焦 → 补缺

  1. 侦察(整批 Scout 合计 1–2 条互补查询,不是每个 Scout 各 1–2 条):找出本期重要事件、候选主体、候选标题、URL 与可能日期。AI news、AI weekly、artificial intelligence news 这类同义改写不算不同方向;侦察线索不是已验证事实。
  2. 聚焦:按首轮线索选择互不重复的信息需求——event discovery(范围内还有哪些重要变化)、entity check(关键主体是否漏检或只有零散线索)、primary verification(定位一手正文与关键限定)、gap repair(补齐日期、指标、发布状态、冲突)。每条查询都要能回答“相对已有材料,这次想多知道什么”,可用实体别名、原语言产品名、首轮出现的完整发布标题或明确指标词。
  3. 补缺:仅当仍有高价值具体缺口时才追加。优先补“重要事件没有可用正文”,其次补“改变结论的指标/日期/条件”;材料已充分的支线不再堆第三、第四份重复来源。

轮数只是执行安排,不替代硬预算,满足任务可提前停止,不要求花完搜索次数。发现阶段可以从综述、媒体、索引页入手找到事件与原始链接,不把所有查询限定在官网;取证阶段再优先一手来源。

查找候选来源

{tool} web-search --run {run_id} --query "具体实体 事项 日期或指标"
  • 用一个明确的信息需求组织每条查询。发现阶段可用综述、媒体、索引页找到事件及原始链接,不把所有查询限定在官网;取证阶段优先官方披露、监管/交易所、原始统计或其他一手发布者。结果不够时改关键词、别名或检索范围,一次只放宽一个维度。
  • DuckDuckGo 只有综合检索:不传 --topic(news 不被支持)。相对时间可用 --time-range day|week|month|year;不支持 --start-date/--end-date 绝对日期,报告窗口先用相对范围再在正文核对日期。
  • 已知权威发布者时可重复传 --include-domain DOMAIN(转为 site: 限定);排除不适合来源用 --exclude-domain DOMAIN。不要把过窄过滤造成的空结果解释为事件没有发生。
  • --max-results 为 1–10。不传 --search-depth:DuckDuckGo 单一端点,advanced 与 basic 相同。

返回 results 的 title、URL、snippet 只用于候选发现;DuckDuckGo 摘要不提供相关性分数,也未提取发布日期。snippet 不是原网页,此时没有可引用的来源正文或 source_id。

获取正文并保留来源类型

对选中的候选,直接获取网站材料:

{tool} add-url --run {run_id} --url "候选URL"

工具保存直接响应及可读正文,并返回登记结果。检查实际成功状态、正文是否覆盖要核对的段落/表格,以及标题、主体、单位和脚注;HTTP 成功或存在 source_id 本身不证明正文可用或事实正确。

DuckDuckGo 没有提供方提取服务:直接获取失败时没有等效的 Extract 回退,改查官网索引、changelog、官方仓库、模型卡等其它官方渠道,或读来源政策允许的可靠二手正文并说明归属与局限;未取得必要内容时保留具体缺口,不从 snippet 补造正文。

Read the full file on GitHub · 71 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. 1mo ago First seen · 71 lines · 55 tokens per session scan A 0434d16b731c

Subscribe to this mod's changes

duckduckgo is a skill published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,808 once invoked, about $0.0002 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 2026-09-14.

Related

Other skills, from other repositories

accounting-software-selection

Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request. Use for choosing accounting software.

sickn33/agentic-awesome-skills · 37 tokens

accounting-audit-system-builder

Routes an accounting or audit request to the right module skill, from software selection through monthly closing, asking only what is missing. Use for books of accounts or audit files.

sickn33/agentic-awesome-skills · 41 tokens

provenance

Tags every claim as fact, inference, or guess and computes calibrated confidence to prevent epistemic flattening. Now with calibration curves, epistemic audit trails, inflation detection, and mathematical depth metrics.

Kshitijpalsinghtomar/depth-skills · 43 tokens

human-loop-audit

Interaktives Reißverschluss-Audit-Verfahren für eine Serie von Apps/Prüfobjekten: der User testet live und gibt kurzes Feedback im Chat, der Agent startet dabei bereits das nächste Objekt UND wertet parallel das Feedback des vorigen aus (strukturiert erfassen, Reparaturaufträge sofort an Worker delegieren) — statt…

ellmos-ai/skills · 180 tokens

ibrahim-daily-briefing

Generate Ibrahim's daily briefing — new leads, upcoming calls, pending follow-ups, system health, and one strategic question. Delivered to Telegram.

S3YED/appie-kit · 37 tokens

research-synthesis-analyst

Synthesize multi-source evidence into decision-ready research outputs with conflict tracking and citation hygiene.

frumu-ai/tandem · 24 tokens