What is byo-coding-agent AGENTS.md?

Project instructions for a small Go program that provides a coding-agent harness: the surrounding system that connects an AI model with tools, commands, remote services, and a user interface.

Learning the codebase, adding or modifying tools and commands, connecting remote services, and working on agent conversations, delegation, or context handling.

They map the repository's main components and explain how the harness works, which is important for making changes without breaking its extension points.

byo-coding-agent AGENTS.md — Instructions file by betta-tech

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/betta-tech/byo-coding-agent/agents-md

Clone the repo

git clone --depth 1 https://github.com/betta-tech/byo-coding-agent

Made for: Codex, OpenCode.

Per session 647 This file is loaded in full into every session.

When invoked 647 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	$0.00647	$0.00647
Opus 5	$0.00324	$0.00324
Sonnet 5	$0.00129	$0.00129
Haiku 4.5	$0.00065	$0.00065

Measured 2d ago against content hash 6a06f0cde861, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

byo-coding-agent 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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project context for AI agents

This file is loaded into the system prompt at startup by the harness itself (see loadAgentsContext in main.go) and is also picked up by external agents like Claude Code that follow the AGENTS.md convention.

What this repo is

A small, opinionated coding-agent harness in Go (~1,000 lines), written as a learning project. The README and follow_along/ chapters explain why each piece exists.

Layout

main.go — wiring: provider, tools, MCP servers, AGENTS.md, root agent, TUI.
commands.go — slash command registry. Touches every extension point.
delegate.go — the delegate tool. Lives in main to avoid an import cycle.
internal/api/ — shared message types. No internal deps.
internal/provider/ — Provider interface + Anthropic adapter.
internal/tool/ — Tool interface, Registry, one file per local tool.
internal/mcp/ — wrappers that expose remote MCP server tools as local Tools.
internal/compact/ — compaction strategies (no-op, sliding window, summarize, logging decorator).
internal/agent/ — the agent loop. One Agent per conversation.
internal/subagent/ — Subagent interface + research subagent + active tracker.
internal/ui/ — banner, spinner, the Bubble Tea program that owns the UI.

Conventions

Errors as tool results, not Go errors. When a tool fails, return (message, true) so the model can read and recover. Don't crash the loop.
One file per tool / strategy / subagent. Tools self-register via init(); subagents register explicitly in main because they need a Provider at construction time.
The provider abstraction is real. Anthropic SDK types are only allowed in internal/provider/anthropic.go. If you find them anywhere else, that's a leak.
Comments explain why, not what. Names carry the what.

Build / run

export ANTHROPIC_API_KEY=sk-ant-...
go run .         # launches the TUI
go build ./...   # sanity check
go vet ./...     # before committing

Read the full file on GitHub · 60 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 · 60 lines · 647 tokens per session scan A 6a06f0cde861

Subscribe to this mod's changes

byo-coding-agent AGENTS.md is an instructions file published in the GitHub repository betta-tech/byo-coding-agent (140 stars, last pushed 3mo ago), licensed MIT. It adds 647 tokens to every session, about $0.0032 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.

Data and AI Languages

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

byo-coding-agent AGENTS.md