Borrowing it
Nothing to install: this file belongs to everyai-com/distillory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/everyai-com/distillory/main/AGENTS.mdgit clone --depth 1 https://github.com/everyai-com/distilloryWrote 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/instructions/everyai-com/distillory/agents-md)<a href="https://agentmods.dev/instructions/everyai-com/distillory/agents-md"><img src="https://agentmods.dev/badge/instructions/everyai-com/distillory/agents-md/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.
<a href="https://agentmods.dev/instructions/everyai-com/distillory/agents-md"><img src="https://agentmods.dev/badge/instructions/everyai-com/distillory/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00443 | $0.00443 |
| Opus 5.5 | $0.00177 | $0.00177 |
| Sonnet 5.5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
distillory 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 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.
What it actually says
distillory — agent notes
Canonical agent file for this repo. Any harness that reads AGENTS.md (Codex,
Cursor, Copilot, Gemini CLI, Zed, Cline, Windsurf, …) gets it directly.
distillory is a local-first memory engine that synthesizes at ingestion — one schema-graded profile per entity, one SQLite file. No server, no Docker.
Commands
make install # editable install with dev + mcp extras
make test # pytest (offline, no key)
make lint # ruff
make serve-mcp # mem serve --mcp --db ./brain.db
mem serve --http # zero-dep HTTP JSON API
- Python ≥3.10;
memCLI is 1:1 with the Python API and the MCP tools. numpyis the only base dependency; vector/embed/LLM/MCP support are extras ([vec],[embed-fastembed],[embed-potion],[llm-anthropic],[llm-openai],[llm-ollama],[mcp]).
Harness support (MCP)
The MCP server is stdio: mem serve --mcp --db ~/brain.db, needs the [mcp]
extra. Works with any MCP client — per-harness config snippets (Claude Code,
Cursor, VS Code, Codex) live in the README under "Plug it into any harness". The
implementation is src/distillory/adapters/mcp_server.py (FastMCP); it exposes
memory_add / search / profile / entities / synthesize / graph plus a
memory://profile/{slug} resource.
Invariants
- One SQLite file is the whole store — never introduce a server dependency for core memory.
- Synthesis is graded against a schema read before every write; a profile is either schema-complete or explicitly partial. Never fabricate a field.
- Tests stay offline and key-free — do not add a network call to the suite.
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.
- 1mo ago First seen · 40 lines · 443 tokens per session scan A 54a5e2cde3e8
distillory AGENTS.md is an instructions file published in the GitHub repository everyai-com/distillory (0 stars, last pushed 1mo ago), licensed MIT. It adds 443 tokens to every session, about $0.0018 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.
distillory AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| distillory AGENTS.mdeveryai-com/distillory | Instructions file | 0 | 1mo ago | MIT | A | 443 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |