What is bt AGENTS.md?

Project instructions for the Braintrust Data codebase, including rules for configuration, application URLs, BTQL queries, tools, and privacy. BTQL is the project's query language for accessing Braintrust data and logs.

Use it when modifying Braintrust Data code, adding command-line configuration, working with application URLs, or writing BTQL queries over project logs.

It helps an agent follow the repository's safety and configuration rules instead of making undocumented assumptions. It also requires log queries to include limits that reduce unnecessary data scanning.

bt AGENTS.md — Instructions file by braintrustdata

Install

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.

agentmods

npx agentmods add instructions/braintrustdata/bt/agents-md

Clone the repo

git clone --depth 1 https://github.com/braintrustdata/bt

Made for: Codex, OpenCode.

Per session 607 This file is loaded in full into every session.

When invoked 607 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00607	$0.00607
Opus 5	$0.00303	$0.00303
Sonnet 5	$0.00121	$0.00121
Haiku 4.5	$0.00061	$0.00061

Measured 2d ago against content hash 12bcb8b44604, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bt 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.

AGENTS.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines

Configuration Policy

Do not introduce new ad-hoc configuration reads via std::env::var(...) / process.env / os.getenv(...) in command logic.
All user-facing/runtime configuration must be defined in clap arguments:
- a CLI flag, and
- for persistent configuration, a corresponding environment variable (#[arg(env = ...)]).
Entry points/runners should receive configuration from the CLI layer (via args/env that the CLI owns), not from independent, undocumented env lookups.
Extreme edge-case exceptions are allowed only when a flag is not feasible (for example, process-internal plumbing), and must be:
- documented inline with a short rationale, and
- minimized in scope.
Do not infer/transform app URLs from API URLs (for example, replacing api. with www.). Treat --app-url / BRAINTRUST_APP_URL as the source of truth for app URLs.

BTQL Safety

BTQL queries over project_logs(...) or the combined project(...) source must include a useful segment-elimination constraint:
- a selective range on created, _xact_id, or _pagination_key; or
- scoping to specific root_span_id or id values.
This requirement does not apply to other object sources such as project_functions(...), project_prompts(...), dataset(...), or experiment(...).

Tooling

This repo is managed with mise and pre-commit; prefer using the repo-defined toolchain and hooks when running local validation.

Privacy and Test Data

Do not add real customer, organization, profile, project, function, dataset, experiment, or user names/IDs to tests, fixtures, docs, examples, snapshots, or committed files.
Use synthetic placeholders instead, for example test-profile, test-org, test-project, fn_test_topic_map, or UUIDs clearly marked as fake.
If a user-provided command includes real identifiers, do not copy them into code or tests; translate them to synthetic values before writing files.

CLI Implementation Conventions

Read the full file on GitHub · 40 lines

Changes

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 · 40 lines · 607 tokens per session scan A 12bcb8b44604

Subscribe to this mod's changes

bt AGENTS.md is an instructions file published in the GitHub repository braintrustdata/bt (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 607 tokens to every session, about $0.0030 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.

Testing Writing and docs

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

bt AGENTS.md