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-writenpx skills add deeflect/dory --skill dory-writegit 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 | $0.00031 | $0.00418 |
| Opus 5 | $0.00015 | $0.00209 |
| Sonnet 5 | $0.00006 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
dory-write 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 yesterday.
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 Write
Use Dory write surfaces through CLI/MCP/HTTP when durable memory should change.
Workflow:
- Search first to see what already exists
- Prefer semantic
dory_memory_write/memory-writewith actionwrite,replace, orforget - Use
dry_run=truefirst when the subject or target is not obvious - Use exact-path
dory_writeonly through MCP/HTTP when the target path is known and you have read the current hash - Use
dory_purgeonly for exact scratch/test artifact cleanup, and keep its defaultdry_run=trueuntil the target/hash are verified
Rules:
- Do not invent frontmatter
- Do not create
core/files casually - Use
force_inbox=truefor tentative or scratch captures - Use
allow_canonical=trueonly after preview when a semantic write intentionally resolves to canonical memory - Exact-path
dory_writekinds areappend,create,replace, andforget - New exact-path files require
frontmatter.titleandfrontmatter.type; usetype: captureforinbox/**andtype: noteonly underreferences/notes/** - Exact-path
replaceandforgetrequireexpected_hash;forgetalso requiresreason - CLI exposes semantic
memory-writeand guardedpurge; exact-pathdory_writeis an MCP/HTTP surface, not a top-level CLI command - Legacy
add/createwrite actions normalize towrite;remove/deletenormalize toforget, but new instructions should use the canonical action names - Plain-text mentions of known people/projects will create graph edges automatically; wikilinks are optional, not required
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.
- yesterday First seen · 28 lines · 31 tokens per session scan A b1deae98cf85
dory-write is a skill published in the GitHub repository deeflect/dory (11 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 418 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.
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…