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/bit2me-devs/bit2me-mcp/agents-mdgit clone --depth 1 https://github.com/bit2me-devs/bit2me-mcpWhat 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 | $0.06289 | $0.06289 |
| Opus 5 | $0.03145 | $0.03145 |
| Sonnet 5 | $0.01258 | $0.01258 |
| Haiku 4.5 | $0.00629 | $0.00629 |
Grade A, and why
bit2me-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 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.
How it starts
The opening of the file, as written. The whole thing — 657 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Rules for Bit2Me MCP Server Repository
Canonical map of all docs (generated vs hand-edited, EN vs ES): docs/README.md.
This document contains conventions for implementing in this repository.
📋 Table of Contents
- Commit Conventions
- Versioning & Releases
- API Response Mapping
- Testing
- CI/CD Workflows
- NPM Publishing
- Code Structure
- Dependencies Management
- Git Hooks
- Troubleshooting
- Adding a New Tool
Commit Conventions
Rules
- ALWAYS use Conventional Commits format
- Format:
<type>(<scope>): <subject> - Types that trigger releases:
feat:→ Minor version bump (1.1.0 → 1.2.0)fix:→ Patch version bump (1.1.0 → 1.1.1)perf:→ Patch version bump
- Types that DON'T trigger releases:
chore:- Build/dependency changesci:- CI/CD changesdocs:- Documentation onlystyle:- Code style changesrefactor:- Code refactoringtest:- Test changes
- CRITICAL: All commit messages MUST be written in English
- Subject line must be in English
- Body (if present) must be in English
- No exceptions - this ensures consistency and compatibility with tools
- Commitlint validates all commits via Husky pre-commit hook
Examples
feat: add optional raw_response support in mapped responses
fix: correct wallet address mapper and add pocket details mapper
ci: improve semantic-release npm configuration
docs: add NPM badge and link to README
chore(deps): bump zod from 4.1.12 to 4.1.13
Versioning & Releases
Semantic Release Configuration
- Automated versioning via Semantic Release
- Configuration file:
.releaserc.json - Release rules: Defined in
releaseRulesarray - Branches: Only
mainbranch triggers releases - Node.js version: Requires Node.js 22+ (Semantic Release requirement)
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 · 657 lines · 6,289 tokens per session scan A cc233103ed4a
bit2me-mcp AGENTS.md is an instructions file published in the GitHub repository bit2me-devs/bit2me-mcp (5 stars, last pushed 3d ago), licensed MIT. It adds 6,289 tokens to every session, about $0.0314 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
wanaku CLAUDE.md
Instructions for wanaku-ai/wanaku, covering wanaku, core guidelines, quick start, build info and architecture.
mcp AGENTS.md
Instructions for Teamwork/mcp, covering agents.md, this repository is public, project overview, setup commands and build and run.
hk-climate-mcp-server GEMINI.md
Instructions for hkopenai/hk-climate-mcp-server: This table serves as a reference for current and future development, ensuring that each tool's API interaction and error handling approach is aligned with the defined principles.
openrouter-deep-research-mcp CLAUDE.md
Instructions for wheattoast11/openrouter-deep-research-mcp, covering agent zero: isomorphic protocol bridge (v2.0.0), system identity, operational paradigms, database persistence (v2.0.0+) and core commands.
openrouter-deep-research-mcp AGENTS.md
Instructions for wheattoast11/openrouter-deep-research-mcp, covering agents.md, isomorphic 5-layer architecture alignment, layer correspondence (axon architecture), resilience & production status and quick commands.
hk-food-mcp-server GEMINI.md
Gemini CLI instructions for hkopenai/hk-food-mcp-server: This table serves as a reference for current and future development, ensuring that each tool's API interaction and error handling approach is aligned with the defined principles.