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/krazyjakee/agents.db/agents-mdgit clone --depth 1 https://github.com/krazyjakee/AGENTS.dbWhat 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 | $0.00565 | $0.00565 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
AGENTS.db 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 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure
crates/contains the Rust workspace crates:crates/agentsdb-core/: shared types, errors, embedding utilities.crates/agentsdb-format/:AGENTS.dbfile reader/writer.crates/agentsdb-query/: query engine across one or more layers.crates/agentsdb-mcp/: MCP-facing library for search/write semantics.crates/agentsdb-cli/:agentsdbCLI binary (src/main.rs).
docs/: design docs, includingdocs/RFC.md.target/: Cargo build output (ignored).
Build, Test, and Development Commands
cargo build: build the full workspace.cargo test: run all unit tests (inline#[cfg(test)]modules).cargo test -p agentsdb-format: run tests for a single crate.cargo run -p agentsdb-cli -- --help: run the CLI help locally.cargo fmt --all: format code with rustfmt.cargo clippy --all-targets --all-features: lint with Clippy (aim for clean output).
Coding Style & Naming Conventions
- Rust edition: 2021 (see crate
Cargo.tomlfiles). - Formatting: rustfmt defaults; keep diffs minimal and idiomatic.
- Naming: crates/modules/functions in
snake_case, types/traits inPascalCase, constants inSCREAMING_SNAKE_CASE. - Prefer explicit error context (
anyhow::Context) at binary boundaries (CLI).
Testing Guidelines
- Tests live next to code in
#[cfg(test)] mod testsblocks. - Prefer small unit tests per feature (reader/writer/query invariants).
- Use deterministic inputs (avoid timestamps/randomness unless explicitly tested).
Commit & Pull Request Guidelines
- Git history is not established yet; use Conventional Commits:
feat: ...,fix: ...,docs: ...,chore: ...
- PRs should include: a short rationale, key commands run (e.g.,
cargo test), and any relevant CLI examples (e.g.,agentsdb compile,agentsdb search).
Building
Use ./scripts/install-local.sh to build
Agent-Specific Notes
This repository includes a compiled documentation database/knowledgebase at AGENTS.db.
For context for any task, you MUST use MCP agents_search to look up context including architectural, API, and historical changes.
Treat AGENTS.db layers as immutable; avoid in-place mutation utilities unless required by the design.
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 · 51 lines · 565 tokens per session scan A c89e5e826e1a
AGENTS.db AGENTS.md is an instructions file published in the GitHub repository krazyjakee/AGENTS.db (44 stars, last pushed 5mo ago), licensed MIT. It adds 565 tokens to every session, about $0.0028 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.