Borrowing it
Nothing to install: this file belongs to igorls/context-builder. 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/igorls/context-builder/master/AGENTS.mdgit clone --depth 1 https://github.com/igorls/context-builderWrote 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/igorls/context-builder/agents-md)<a href="https://agentmods.dev/instructions/igorls/context-builder/agents-md"><img src="https://agentmods.dev/badge/instructions/igorls/context-builder/agents-md.svg" alt="Measured on agentmods" 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 | $0.02324 | $0.02324 |
| Opus 5 | $0.01162 | $0.01162 |
| Sonnet 5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
context-builder 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 4d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - AI Agent Instructions
This file helps AI agents quickly understand and contribute to the Context Builder codebase.
Project Overview
Context Builder is a blazing-fast Rust CLI for aggregating entire codebases into single, LLM-friendly markdown files. Published on crates.io under MIT license.
If this is your first time: Read this file, then run cargo run -- --help to see all options.
Deep Think Authority Mode (optional handoffs)
When the user points at docs/handoffs/** or an AUTHORITY document:
- Follow Authority Mode rules in
docs/agent-harness/antigravity-system-prompt.md. - AUTHORITY is law for implementation; do not redesign.
- If the live tree contradicts AUTHORITY, stop with a CONFLICT packet (
docs/agent-harness/templates/05-conflict.md). - Prefer tools on the real repo; do not demand a re-dump of the full context-builder snapshot unless tools are unavailable.
- End with a RESULT block (
docs/agent-harness/templates/04-result.md).
Pipeline overview: docs/agent-harness/README.md. Skill entrypoint: SKILL.md.
Tech Stack
| Technology | Usage |
|---|---|
| Language | Rust (Edition 2024) |
| Build | Cargo (no npm/bun/node) |
| CLI | clap (derive) |
| Parallelism | rayon (optional, default on) + crossbeam-channel |
| Diffing | similar (unified diffs) |
| File traversal | ignore crate (gitignore-aware) |
| Token counting | tiktoken-rs (cl100k_base) |
| Caching | JSON snapshots + std::fs::File advisory locking (fs2 removed in v0.9.0) |
| Config | TOML (context-builder.toml) |
| Encoding | encoding_rs (transcoding non-UTF-8) |
| Logging | env_logger |
| Branch | master (not main) |
Project Structure
context-builder/
├── src/
│ ├── main.rs # Entry point — calls lib::run()
│ ├── lib.rs # Core orchestration, run_with_args(), Prompter trait, --init
│ ├── cli.rs # Args struct via clap derive
│ ├── config.rs # Config struct, TOML deserialization
│ ├── config_resolver.rs # Merges CLI args + TOML config (CLI > config > defaults)
│ ├── file_utils.rs # .gitignore-aware traversal, OverrideBuilder for custom ignores
│ ├── tree.rs # BTreeMap file tree (deterministic ordering)
│ ├── state.rs # ProjectState/FileState structured snapshots
│ ├── markdown.rs # Streaming file renderer, binary detection, encoding, parallel
│ ├── cache.rs # JSON-based caching with std::fs::File locking, old cache migration
│ ├── diff.rs # Per-file unified diffs via similar
│ ├── token_count.rs # Real tokenization via tiktoken-rs (o200k/cl100k, lazy init)
│ ├── languages.rs # Canonical extension → code-fence language map (v0.10)
│ └── tree_sitter/ # AST signatures/structure/smart-truncation (feature-gated)
│ ├── language_support.rs # Signature/Visibility types, LanguageSupport trait
│ ├── signatures.rs # extract_signatures + markdown formatting
│ ├── structure.rs # structural summaries
│ ├── truncation.rs # AST-boundary smart truncation (char-safe per B19)
│ ├── mod.rs # feature-gated facade (is_supported_extension, etc.)
│ └── languages/ # per-language extractors: rust, javascript, typescript,
│ # python, go, java, c, cpp
├── tests/ # 10 integration test files
├── benches/ # Criterion benchmark suite
├── scripts/ # generate_samples.rs (benchmark dataset generator)
├── context-builder.toml # Project's own config file
├── Cargo.toml # Crate metadata, dependencies, features
├── DEVELOPMENT.md # Contributor guide
├── BENCHMARKS.md # Performance benchmarking guide
├── CHANGELOG.md # Release history
└── .github/workflows/ci.yml # CI: fmt, clippy, build, test, security audit (ubuntu/win/macos)
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.
- 4d ago First seen · 198 lines · 2,324 tokens per session scan A 09c47cc74a30
context-builder AGENTS.md is an instructions file published in the GitHub repository igorls/context-builder (40 stars, last pushed yesterday), licensed MIT. It adds 2,324 tokens to every session, about $0.0116 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 2026-09-03.
Other instructions, from other repositories
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.
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.
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).
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).
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.
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.