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.
npx agentmods add instructions/bitty-terminal/bitty-mcp/agents-mdgit clone --depth 1 https://github.com/bitty-terminal/bitty-mcpWrote 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/bitty-terminal/bitty-mcp/agents-md)<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="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 | $0.01009 | $0.01009 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
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 3d 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 — 90 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-mcprepository. Its canonical remote is https://github.com/bitty-terminal/bitty-mcp. - The Bitty umbrella directory and
bitty-pluginsdirectory are grouping only; neither owns this repository's Git or CarryCtx state. - Enter this repository before running Git, CarryCtx, validation, or toolchain commands.
bitty-docsis 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-mcpis 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.
- 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.
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.
- 3d ago First seen · 90 lines · 1,009 tokens per session scan A 2e36a4e4d56b
bitty-mcp AGENTS.md is an instructions file published in the GitHub repository bitty-terminal/bitty-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 1,009 tokens to every session, about $0.0050 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.