Borrowing it
Nothing to install: this file belongs to tothalex/drift. 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/tothalex/drift/main/AGENTS.mdgit clone --depth 1 https://github.com/tothalex/driftWrote 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/tothalex/drift/agents-md)<a href="https://agentmods.dev/instructions/tothalex/drift/agents-md"><img src="https://agentmods.dev/badge/instructions/tothalex/drift/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/tothalex/drift/agents-md"><img src="https://agentmods.dev/badge/instructions/tothalex/drift/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 | $0.01545 | $0.01545 |
| Opus 5.5 | $0.00618 | $0.00618 |
| Sonnet 5.5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
drift 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 12d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drift — agent instructions
drift is a Rust terminal UI for reviewing working changes like a pull request: everything since the base branch (committed, uncommitted, untracked) in one live view, plus real GitHub/GitLab PR review and a send-to-AI-agent integration.
Commands
cargo build # debug binary at target/debug/drift
cargo test # unit + integration tests (tests/git_vcs.rs)
cargo test <name> # one test by substring
cargo clippy --all-targets # must be warning-free
cargo fmt # required before committing
Architecture
src/app/— the coordinator: event loop, key dispatch, overlay state (picker, compose, help). Fully synchronous — no async runtime; background work isstd::thread::spawn+ anAppEventchannel.src/lang/— the language registry: name, extensions, grammar, block kinds, highlight queries per language. Everything language- specific lives here. No grammar is compiled into drift: every language is a plugin (manifest + query + dylib-compiled grammar under the config dir'slanguages/), installed via thedrift langCLI or the in-app prompt and hot-loaded. The curated install registry is the repo'slanguages/directory (manifests + drift's query stacks), embedded into the binary — adding a curated language = one manifest file there, and tests validate every entry. Unit tests see a registry built from dev-dependency grammar crates plus those curated files, so the suite runs without git or a C compiler; the crate versions in[dev-dependencies]must match the revs the curated manifests pin.src/processor/— tree-sitter block scoping, syntax highlighting, view flattening (view.rsis the canonical row model). Language- agnostic: grammars and queries come fromsrc/lang/.src/vcs/— git via gitoxide; never shells out togit.src/forge/— PRs through the officialgh/glabCLIs; drift never speaks HTTP itself. One submodule per forge behind theForgetrait.fetch.rsis the onegitcall outsidedrift lang: the PR view's fetch prompt runsgit fetchfor a PR's commits, only ony.src/connect/— send-to-agent backends behind theBridgetrait; one submodule per multiplexer plus aBACKENDSregistry table inmod.rs. Adding a backend touches only this directory: new file, newBackendvariant, one registry row.src/keymap.rs— bindings as data:KEY_DEFAULTS+HELPtables; tests enforce that every action is bound and appears in help.src/theme.rs— every color drift paints;THEME_DEFAULTSis the single source (onedark_dark palette).src/config.rs—~/.config/drift/config.toml; each section is a serde struct with aninto_config()validator, anddefault_toml()must stay parseable (a test round-trips it).
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.
- 12d ago Changed · +12 lines · +210 tokens per session dad2394fa087
- 2mo ago First seen · 101 lines · 1,335 tokens per session scan A 48b3a8f34087
drift AGENTS.md is an instructions file published in the GitHub repository tothalex/drift (51 stars, last pushed 12d ago), licensed MIT. It adds 1,545 tokens to every session, about $0.0062 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 2026-08-30.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.