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 agentmods add skills/deeflect/dory/dory-searchnpx skills add deeflect/dory --skill dory-searchgit clone --depth 1 https://github.com/deeflect/doryWrote 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/deeflect/dory/dory-search)<a href="https://agentmods.dev/skills/deeflect/dory/dory-search"><img src="https://agentmods.dev/badge/skills/deeflect/dory/dory-search.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 | $0.00034 | $0.00381 |
| Opus 5 | $0.00017 | $0.00191 |
| Sonnet 5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
dory-search 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.
What it actually says
Dory Search
Use dory search before answering factual questions about people, projects, decisions, dates, or prior sessions.
Workflow:
- If the task asks for a fast recent recap, use
dory_digestfirst instead of searching for adigesttag. - Start normal fact retrieval with
uv run dory --corpus-root <corpus> --index-root <index> search "<query>" - If needed, follow with
dory get <path>on the best hit - If a result has
stale_warning, treat it as possibly outdated and look for fresher evidence
Rules:
- Prefer retrieval over guessing
- Use search even if wake seems related; wake is cached context, search is live evidence
- Do not assume digest files have a searchable
digesttag;dory_digestresolvesdigests/daily,digests/weekly, and legacylogs/**paths directly - Use
mode=exactfor cleanup markers, unique strings, and artifact existence checks - Use
mode=text,mode=keyword, ormode=lexicalwhen you want BM25-only search; all three normalize tobm25 - Use
mode=semanticwhen you want vector-only search; it normalizes tovector - Hybrid search is deterministic by default; LLM-assisted planning, expansion, and reranking require explicit
DORY_QUERY_*server flags - Use
rerank="false"for baseline deterministic search,rerank="true"to force the configured reranker, andrerank="auto"to follow server defaults
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 First seen · 25 lines · 34 tokens per session scan A b8165ff09532
dory-search is a skill published in the GitHub repository deeflect/dory (11 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 381 once invoked, about $0.0002 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 skills, from other repositories
deep-research
深度研究编排方法论：澄清范围、拆解规划、并行调度子智能体调研、对抗式核验、综合成带引用的结构化报告。当任务需要多来源、可追溯、需事实核查的深度研究时使用此技能。.
mysql reporter
生成 MySQL 查询报表并生成可视化图表。当用户需要查询 MySQL 数据库并以报表形式展示结果时使用此技能，包括：统计销售数据、分析用户行为、生成业务报表、查询业务指标等。.
knowledge-base
使用 Yuxi 知识库进行检索、打开文档、文档内定位和查看思维导图。当用户需要基于已配置知识库回答问题、核验资料或引用文档内容时使用此技能。.
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
pytest-suite
Write or extend the backend test suite following this project's conventions. Use when adding tests for a new service/route/repository, when coverage is missing, or when asked to test a feature. Knows the mocked-session + httpx AsyncClient setup so tests run with no database.