tinycode: Instructions file for Codex

AGENTS.md

tinycode AGENTS.md is an instructions file for Codex, OpenCode from bobbyjohnstx/tinycode. It costs 1,460 tokens per session, scanned A, original, MIT.

Repository instructions for the tinycode project, covering commit and pull-request naming, coding style, and JavaScript SDK regeneration. A pull request is a proposed code change for review.

In plain words
What is it for?
Writing commits and pull requests, choosing variables and functions, avoiding unwanted complexity, and rebuilding the JavaScript SDK.
Why use it?
They keep contributions consistent and explain the project’s preferred patterns for maintainable code and generated SDK updates.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md.

This is bobbyjohnstx/tinycode's own configuration. It tells Codex and OpenCode how to work on tinycode itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tinycode configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bobbyjohnstx/tinycode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bobbyjohnstx/tinycode/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/bobbyjohnstx/tinycode

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for tinycode AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bobbyjohnstx/tinycode/agents-md/github.svg)](https://agentmods.dev/instructions/bobbyjohnstx/tinycode/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/bobbyjohnstx/tinycode/agents-md"><img src="https://agentmods.dev/badge/instructions/bobbyjohnstx/tinycode/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.

agentmods 80×15 button for tinycode AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bobbyjohnstx/tinycode/agents-md"><img src="https://agentmods.dev/badge/instructions/bobbyjohnstx/tinycode/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,460 This file is loaded in full into every session.
When invoked 1,460 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01460 $0.01460
Opus 5.5 $0.00584 $0.00584
Sonnet 5.5 $0.00292 $0.00292
Haiku 4.5 $0.00146 $0.00146

Measured 17d ago against content hash 2e2f23a6a15d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tinycode 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 17d 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shared project rules for coding agents. Keep this file in sync with CLAUDE.md. CLAUDE.md also has a Claude-only agent delegation section.

Commands

# Build
make build                      # builds dist/tinycode

# Run
./dist/tinycode                 # TUI mode
./dist/tinycode <directory>     # TUI against a different directory
./dist/tinycode serve           # headless API proxy
./dist/tinycode acp             # Agent Client Protocol (IDE integration, stdio)

# Tests
go test ./... -count=1          # all tests (or: make test)
go test ./internal/tui/... -count=1   # single package

# Lint
make lint                       # go vet + staticcheck (make test-race for -race)

# Embed web app into binary (requires packages/app built first)
make embed-webapp

Commits and PR Titles

Use conventional commit-style messages and PR titles: type(scope): summary.

Valid types are feat, fix, docs, chore, refactor, and test. Scopes: tui, server, llm, session, provider, config, tool, plugin, acp, permission, mcp, vcs, bus, storage, agent, skill, command, project.

Style Guide

  • Follow standard Go conventions (gofmt, go vet)
  • Prefer early returns over else blocks
  • Keep functions focused and small; extract helpers when they name a real concept
  • Use slog for structured logging (already used throughout)
  • Error handling: return errors up the stack with fmt.Errorf("context: %w", err). Don't swallow errors silently.
  • Prefer value receivers for bubbletea Update/View methods (required by the tea.Model interface)
  • Use pointer receivers for methods that mutate state (e.g. resize(), setFocus())
  • Test files live next to source: foo.go / foo_test.go

Testing

  • Use table-driven tests where appropriate
  • Test names: TestFunctionName_ScenarioDescription
  • Run from repo root: go test ./... or target a package: go test ./internal/tui/...

Pitfalls

Things that break silently if you guess wrong.

Read the full file on GitHub · 70 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.

  1. 17d ago Changed · +32 tokens per session 2e2f23a6a15d
  2. 25d ago Changed · -3 tokens per session b9ef737ff5e7
  3. 29d ago Changed · +40 lines · +1,020 tokens per session a571404ff9cc
  4. 1mo ago Changed · +7 lines · +104 tokens per session 55c6f96df613
  5. 1mo ago Changed · -110 lines · -686 tokens per session 9626a985cf56
  6. 2mo ago First seen · 133 lines · 993 tokens per session scan A cebd7192459e

Subscribe to this mod's changes

tinycode AGENTS.md is an instructions file published in the GitHub repository bobbyjohnstx/tinycode (3 stars, last pushed 2d ago), licensed MIT. It adds 1,460 tokens to every session, about $0.0058 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.

Related

tinycode AGENTS.md compared with instructions from other repositories

tinycode AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tinycode AGENTS.mdbobbyjohnstx/tinycodeInstructions file32d agoMITA1,460Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode