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/jthingelstad/mb/agents-mdgit clone --depth 1 https://github.com/jthingelstad/mbWhat 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 | $0.02299 | $0.02299 |
| Opus 5 | $0.01149 | $0.01149 |
| Sonnet 5 | $0.00460 | $0.00460 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
mb 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in mb.
Project Overview
mb is a command-line client for micro.blog, designed for agent and script use.
Core priorities:
- Agent output by default
- Agent output is the primary product surface
- No interactive prompts
- Composable, pipeable commands
- Clear structured errors
- Minimal dependencies
Local Skills
Project-local skills live under skills/:
skills/mb-cli/SKILL.md: corembcommand usage and workflow guidanceskills/mb-for-user-delegation/SKILL.md: guidance for acting on behalf of a human userskills/mb-agent-blogger/SKILL.md: guidance for an agent managing its own blog identity
When working on skill-related requests, keep the command workflow in mb-cli separate from the social/voice rules in the two behavior skills.
Repository Layout
src/mb/cli.py Typer entrypoint and global options
src/mb/api.py HTTP client for micro.blog APIs
src/mb/config.py Config loading/saving and profile support
src/mb/formatters.py json | human | agent output modes
src/mb/commands/catchup.py New timeline posts since catchup checkpoint
src/mb/commands/inbox.py Attention-oriented mention triage
src/mb/commands/post.py Post create/get/edit/reply/delete/list
src/mb/commands/timeline.py Timeline, discover, check, checkpoint
src/mb/commands/conversation.py Conversation thread formatting
src/mb/commands/user.py User and social graph commands
src/mb/commands/blog.py Read own posts, categories, search
src/mb/commands/upload.py Image uploads from local files or URLs
tests/ Unit and CLI integration tests
API Split
Use the correct API family for the job:
- Micropub: write operations and own-post management
- JSON API: timeline, user, conversation, and other read operations
Default base URL is https://micro.blog. MicroblogClient accepts base_url for tests.
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 · 336 lines · 2,299 tokens per session scan A 602121bcfcbc
mb AGENTS.md is an instructions file published in the GitHub repository jthingelstad/mb (4 stars, last pushed 4d ago), licensed MIT. It adds 2,299 tokens to every session, about $0.0115 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
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
python-cheatsheet copilot-instructions.md
Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.
autoharness AGENTS.md
Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…
cookiecutter-mlops-package AGENTS.md
Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
martex-quant CLAUDE.md
Instructions for martex-dev/martex-quant, covering session start — read these first, project instructions, ai trading bot project - master instructions, role and project objective.
ZipAgent AGENTS.md
Instructions for JiayuXu0/ZipAgent, covering repository guidelines, project structure & module organization, build, test & development commands, coding style & naming conventions and testing guidelines.