better-context, also called btca, helps coding agents answer questions about project libraries and frameworks by searching their actual source code instead of relying only on documentation. It is for developers who need current technical context during coding, and the catalogue entries package its agent skill, rule, command, and instruction.
Borrowing it
Nothing to install: this file belongs to davis7dotsh/better-context. 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/davis7dotsh/better-context/main/AGENTS.mdgit clone --depth 1 https://github.com/davis7dotsh/better-contextWrote 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/davis7dotsh/better-context/agents-md)<a href="https://agentmods.dev/instructions/davis7dotsh/better-context/agents-md"><img src="https://agentmods.dev/badge/instructions/davis7dotsh/better-context/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/davis7dotsh/better-context/agents-md"><img src="https://agentmods.dev/badge/instructions/davis7dotsh/better-context/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 | $0.00452 | $0.00452 |
| Opus 5.5 | $0.00181 | $0.00181 |
| Sonnet 5.5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
better-context 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 2mo 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.
What it actually says
AGENTS.md
Critical Rules
- ONLY use
bun- never npm/yarn - NEVER run dev/build commands (
bun dev,bun build)
Source of Truth
When working on this project, apps/docs is the documentation for the server and cli. Make sure when changing something about how an endpoint or command works, you update the documentation in apps/docs. And if you change something that makes it different from the docs, ask me about it. This does not apply to apps/web or apps/sandbox.
Commands
Root Commands
- Type check all:
bun run check:all - Format all:
bun run format:all
Package-Specific Commands
After making changes in a specific package, run its check script:
| Package | Check Command | Format Command |
|---|---|---|
apps/cli |
bun run check:cli |
bun run format:cli |
apps/web |
bun run check:web |
bun run format:web |
apps/server |
bun run check:server |
bun run format:server |
apps/sandbox |
bun run check:sandbox |
bun run format:sandbox |
apps/server-simple |
bun run check:server-simple |
bun run format:server-simple |
packages/shared |
bun run check:shared |
bun run format:shared |
Code Style
- Runtime: Bun only. No Node.js, npm, pnpm, vite, dotenv.
- TypeScript: Strict mode enabled. ESNext target.
- Imports: External packages first, then local. Use
.tsextensions for local imports. - Bun APIs: Prefer
Bun.file,Bun.serve,bun:sqlite,Bun.$over Node equivalents. - Testing: Use
bun:testwithimport { test, expect } from "bun:test".
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.
- 2mo ago First seen · 39 lines · 452 tokens per session scan A 3d8ad16487fa
better-context AGENTS.md is an instructions file published in the GitHub repository davis7dotsh/better-context (1,151 stars, last pushed 6mo ago), licensed MIT. It adds 452 tokens to every session, about $0.0018 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.
better-context AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| better-context AGENTS.mddavis7dotsh/better-context | Instructions file | 1.2k | 6mo ago | MIT | A | 452 | Codex, OpenCode |
| pudo-code-system pudo-api.instructions.mdDongDuong2001/pudo-code-system | Instructions file | 5 | 14d ago | MIT | A | 182 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |