Borrowing it
Nothing to install: this file belongs to bitdriftlabs/blob-stream. 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/bitdriftlabs/blob-stream/main/AGENTS.mdgit clone --depth 1 https://github.com/bitdriftlabs/blob-streamWrote 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/bitdriftlabs/blob-stream/agents-md)<a href="https://agentmods.dev/instructions/bitdriftlabs/blob-stream/agents-md"><img src="https://agentmods.dev/badge/instructions/bitdriftlabs/blob-stream/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/bitdriftlabs/blob-stream/agents-md"><img src="https://agentmods.dev/badge/instructions/bitdriftlabs/blob-stream/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 | $0.00893 | $0.00893 |
| Opus 5.5 | $0.00357 | $0.00357 |
| Sonnet 5.5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
blob-stream 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 15d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
- DEVELOPMENT.md is the canonical human workflow reference.
- Use bitdriftlabs/ai-instructions for shared
language and style guidance. Resolve Rust commands from the command-owning checkout root: a
standalone Blob Stream checkout uses Cargo by default; a nested monorepo checkout follows the
enclosing monorepo's Bazel execution profile and its
AGENTS.md. The rules below apply in both contexts unless marked as monorepo-specific.
Architecture Changes
- Read the Design overview before changing architecture-sensitive behavior.
- Update the owning document in
docs/design/in the same change when altering wire protocol, partitioning or routing, lease or sequence behavior, durable storage layout, delivery or cursor guarantees, consumer coordination, or an operational contract. - Use Infrastructure setup and Operations as the sources for deployment and runbook documentation. Do not duplicate those contracts elsewhere.
- Write documentation as a current-state reference. Do not retain migration history, removed controls, or impossible configuration paths in current configuration and operations documents.
Rust Assertions
- Do not use
assert!in production code. Conditions reachable from configuration, network data, user input, or external state must return an error or be rejected at the earliest normal boundary. - Use
debug_assert!freely for internal invariants whose violation indicates a programming defect. In hot or locked code, validate and construct errors before entering the path, then keep a nearby debug assertion to document the proven invariant. - Test code may use ordinary assertions.
Deterministic Integration Tests
Follow plans/TEST_AUDIT.md. In addition:
- For
ManualTimeProvider, advance logical time only after a lifecycle gate or registered logical sleep. Never make a test pass by adding a wall-clock sleep or extending a wall-clock deadline.
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.
- 15d ago First seen · 77 lines · 893 tokens per session scan A e74823c72d77
blob-stream AGENTS.md is an instructions file published in the GitHub repository bitdriftlabs/blob-stream (54 stars, last pushed 3d ago), licensed Apache-2.0. It adds 893 tokens to every session, about $0.0036 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 2026-10-14.
Other instructions, from other repositories
flow-like copilot-instructions.md
Copilot instructions for Rheosoph/flow-like, covering flow-like wasm node development — rust, project overview, build & test, architecture and pin types.
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).