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-wakenpx skills add deeflect/dory --skill dory-wakegit clone --depth 1 https://github.com/deeflect/doryWhat 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 | $0.00043 | $0.00438 |
| Opus 5 | $0.00022 | $0.00219 |
| Sonnet 5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
dory-wake 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 2d 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 Wake
Dory wake is the default session-start memory read for all projects, not only
the Dory repo. Use dory wake once at the start of a new agent session, after
context compaction, or at a real task switch before doing substantive work.
Do not rerun wake just because a new user turn arrived when the current wake
block is still in context.
Workflow:
- Choose the wake profile from the task:
codingfor software/project implementation,writingfor content/copy/voice work, andprivacyfor boundary-sensitive questions. - If a suitable wake block is already present in the current context and no compaction/task switch happened, reuse it instead of calling wake again.
- Run
dory_wake(profile="<chosen-profile>", budget_tokens=1200)when MCP tools are available. - If the current task or repo maps to a known Dory project, pass
project="<name-or-slug>". - If MCP is unavailable but the local CLI is available, run
uv run dory --corpus-root <corpus> --index-root <index> wake --agent <agent> --profile <chosen-profile>. - Treat the returned block as frozen startup context, not as editable memory.
- If the wake block looks stale, use targeted search/get before rerunning wake.
Rules:
- Use
profile=codingfor project/agent work,profile=writingfor voice/content work, andprofile=privacyfor boundary-sensitive questions - Wake responses include the selected profile; verify it when debugging agent setup
- Do not call wake repeatedly inside one uncompacted conversation; it bloats context and repeats stale summaries
- Never write directly to
core/just because wake surfaced something important - Wake is a hot-start summary, not a substitute for search on factual questions
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.
- 2d ago First seen · 29 lines · 43 tokens per session scan A b6cead15306e
dory-wake is a skill published in the GitHub repository deeflect/dory (11 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 438 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。.
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。.
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。.
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.