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 instructions/deeflect/dory/agents-mdgit 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 | $0.01205 | $0.01205 |
| Opus 5 | $0.00602 | $0.00602 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
dory AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
This is the public Dory repository. Dory is a local-first memory daemon for agents: markdown is the source of truth, SQLite is the disposable index sidecar, and clients talk to it through CLI, HTTP, MCP, Hermes, and OpenClaw integrations.
First Principles
- Keep the public tree clean. Never add private corpus files, real personal memories, direct contact details, private hostnames, tokens, or local absolute paths.
- Use synthetic examples in tests, docs, fixtures, and evals. Do not use real user biography, finance, health, private life events, or private relationship details as fixtures.
- Prefer the smallest correct diff. Avoid broad refactors unless the task explicitly calls for them.
- Do not invent new framework layers when the existing
src/dory_core,src/dory_http,src/dory_mcp,src/dory_cli,plugins/, andpackages/boundaries already fit. - Keep generated artifacts intentional.
packages/openclaw-dory/dist/index.jsis tracked because OpenClaw loads it; most other build output is not.
Repository Map
src/dory_core/- memory model, search, wake, active memory, semantic writes, indexing, operations.src/dory_http/- FastAPI daemon and HTTP contract.src/dory_mcp/- native MCP server and tool schemas.src/dory_cli/- Typer CLI.plugins/hermes-dory/- Hermes provider.packages/openclaw-dory/- OpenClaw memory plugin package. Rebuilddist/index.jsafter TypeScript changes.docs/,references/,eval/,examples/- public documentation, runbooks, public evals, and safe sample corpus material.scripts/release/check-public-safety.py- public leak guard for obvious secrets, private paths, and configured private terms.
Dory Memory Policy
Use Dory as the shared memory layer for agent work in this repo.
- At a new session start, after context compaction, or when switching to a genuinely new task, call
wakewith the right profile. Do not rerun wake on every user turn while the current wake block is still in context. - Before making factual claims about memory, projects, people, priorities, decisions, or current environment, use Dory first.
- Preferred read flow:
wake, thensearch, then exactget, thenlinkonly when graph context is useful. - Cite exact Dory source paths when an answer depends on Dory memory.
- If evidence is weak, stale, private, or conflicting, say that directly instead of guessing.
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 · 94 lines · 1,205 tokens per session scan A a7f9f836564c
dory AGENTS.md is an instructions file published in the GitHub repository deeflect/dory (11 stars, last pushed 2mo ago), licensed MIT. It adds 1,205 tokens to every session, about $0.0060 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 instructions, from other repositories
microsandbox AGENTS.md
AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.
Yuxi AGENTS.md
AGENTS.md instructions for xerrors/Yuxi, covering yuxi agent 开发约定, 每次任务先加载什么, 任务与决策, 不能破坏的系统事实 and 证据规则.
full-stack-ai-agent-template CLAUDE.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering claude.md, project overview, commands, install dependencies and run tests.
full-stack-ai-agent-template AGENTS.md
Instructions for vstorm-co/full-stack-ai-agent-template, covering agents.md, project overview, commands, cli and architecture.
MultiGen CLAUDE.md
Instructions for lingyuanli/MultiGen, covering claude.md, architecture, development commands, full stack (docker) and api (local).
txtify CLAUDE.md
Instructions for lkmeta/txtify, covering txtify — agent guide, architecture (read this before touching job flow), commands, invariants & known traps and conventions.