bitty-mcp: Instructions file for Codex

AGENTS.md

bitty-mcp AGENTS.md is an instructions file for Codex, OpenCode from bitty-terminal/bitty-mcp. It costs 1,172 tokens per session, scanned A, original, MIT.

Repository instructions for bitty-mcp, an independent project that connects other systems through the Model Context Protocol. They describe the repository's ownership, documentation authority, current pre-implementation status, and limits on adding product code.

In plain words
What is it for?
They guide repository work, Git and validation commands, CarryCtx task handling, documentation use, and the boundary between this adapter and the terminal core.
Why use it?
They prevent contributors from treating proposals or empty files as working features or from adding code before the project's required design and security decisions are accepted.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is bitty-terminal/bitty-mcp's own configuration. It tells Codex and OpenCode how to work on bitty-mcp 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 bitty-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bitty-terminal/bitty-mcp. 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/bitty-terminal/bitty-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/bitty-terminal/bitty-mcp

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 bitty-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bitty-terminal/bitty-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bitty-terminal/bitty-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,172 This file is loaded in full into every session.
When invoked 1,172 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 $0.01172 $0.01172
Opus 5.5 $0.00469 $0.00469
Sonnet 5.5 $0.00234 $0.00234
Haiku 4.5 $0.00117 $0.00117

Measured 1mo ago against content hash cd9f7e899308, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bitty-mcp 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 1mo 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 · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bitty MCP repository guidance

Repository and authority

  • This is the independent bitty-mcp repository. Its canonical remote is https://github.com/bitty-terminal/bitty-mcp.
  • The Bitty umbrella directory and bitty-plugins directory are grouping only; neither owns this repository's Git or CarryCtx state.
  • Enter this repository before running Git, CarryCtx, validation, or toolchain commands.
  • bitty-docs is the canonical source for product architecture, security, interface, protocol, and public-behavior contracts.
  • The project is pre-implementation. Do not describe an empty repository, configuration file, example, or design proposal as working product behavior.

Current scope

  • Documentation and repository governance may be initialized when the active CarryCtx task permits it.
  • Do not add product code until a separately authorized task has accepted protocol, security, and interoperability gates.
  • bitty-mcp is an adapter and integration boundary; it must not silently become the terminal core, plugin host, or source of Terminal Truth.
  • Keep exact transports, schemas, authentication mechanisms, client support, and write-capable operations open until accepted by reviewable contracts.

CarryCtx and agents

  • Use this repository's CarryCtx state for tasks, teams, dependencies, scopes, sessions, progress, decisions, checkpoints, handoffs, and review.
  • Install the carryctx CLI globally for local development (recommended): cargo install carryctx or npm i -g carryctx; the npm package is also declared in package.json for discovery.
  • The commander coordinates. Delegate substantial scoped work to focused agents and require an independent reviewer for acceptance.
  • Every agent reads its persona and applicable rules, binds a named session to the task, and stays within explicit scopes.
  • After the first commit, prefer a dedicated branch and Git worktree for each independent task. Before it, shared-checkout initialization is allowed only for disjoint scopes with CI-equivalent local checks.
  • Branch and worktree naming follows ctx-XXXX/<type>-<short-slug> and .worktrees/ctx-XXXX-<type>-<short-slug> (one branch per task; cmd/<slug> is reserved for commander housekeeping).
  • Preserve unrelated changes. Do not commit, push, release, or mutate remote state without explicit authorization.
  • Fresh clones have no CarryCtx state DB. Restore the local DB from the in-repo snapshot branch with just workflow-import (validate-only: just workflow-import-dry). It fetches refs/heads/carryctx-snapshots, refuses to replace a non-empty local DB without --force, and prints provenance and restored counts. Snapshots are redacted publication artifacts from carryctx export --publication: never merge them back, and rotate at the source any secret that leaked before rotation.

Read the full file on GitHub · 100 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. 1mo ago Changed · +2 tokens per session cd9f7e899308
  2. 1mo ago Changed · +10 lines · +161 tokens per session 52c3a4941632
  3. 2mo ago First seen · 90 lines · 1,009 tokens per session scan A 2e36a4e4d56b

Subscribe to this mod's changes

bitty-mcp AGENTS.md is an instructions file published in the GitHub repository bitty-terminal/bitty-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,172 tokens to every session, about $0.0047 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 2026-08-31.

Related

bitty-mcp AGENTS.md compared with instructions from other repositories

bitty-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
bitty-mcp AGENTS.mdbitty-terminal/bitty-mcpInstructions file01mo agoMITA1,172Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot