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/lutra-fs/sift/agents-mdgit clone --depth 1 https://github.com/Lutra-Fs/siftWhat 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 | $0.01126 | $0.01126 |
| Opus 5 | $0.00563 | $0.00563 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
sift 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repo is a Rust workspace. Core logic lives under crates/: sift-core hosts domain and orchestration code, while sift-cli/sift-tui/sift-gui provide entrypoints. sift-core modules live in crates/sift-core/src/ and are split by area (commands/, orchestration/, config/, registry/). Cross-crate integration tests are in tests/, and core integration tests are in crates/sift-core/tests/. Shared configuration lives in sift.toml, and design/reference docs are in design.md, mcp-docs/, and skill-docs/.
Build, Test, and Development Commands
cargo build: Build the entire workspace.cargo test: Run all tests.cargo test -p sift-core: Run only core tests.cargo run -p sift-cli -- <args>: Run the CLI locally.cargo run -p sift-tui/cargo run -p sift-gui: Run the TUI/GUI.
Coding Style & Naming Conventions
Follow Rust 2024 edition conventions and use rustfmt and clippy. Prefer snake_case; keep type and module names clear and concise. Organize code by area under crates/sift-core/src/<area>/ and avoid cross-layer dependencies. Before committing, run:
cargo fmt
cargo clippy --all-targets --all-features
Testing Guidelines
Tests use the Rust test framework with #[test] and #[tokio::test]. Prefer behavior tests in crates/sift-core/tests/ with descriptive filenames (e.g., install_command.rs, *_spec.rs). New features should cover main paths and error branches; add boundary cases for parsing or config merging.
Commit & Pull Request Guidelines
Commit messages follow Conventional Commits (e.g., feat: ..., refactor(scope): ..., fix: ...). PRs should include a summary, motivation/impact, and the test commands run. For TUI/GUI changes, include screenshots or recordings; link related issues when applicable.
Architecture & Docs Notes
Design assumptions and behavior contracts live in design.md; protocol and our supported client docs are in mcp-docs/ and skill-docs/. Review these before making changes that could affect semantics.
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 · 61 lines · 1,126 tokens per session scan A f57835ae5d4e
sift AGENTS.md is an instructions file published in the GitHub repository Lutra-Fs/sift (2 stars, last pushed 7mo ago), licensed MIT. It adds 1,126 tokens to every session, about $0.0056 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 2026-08-31.
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.