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/micaeljarniac/repeaterbook/agents-mdgit clone --depth 1 https://github.com/MicaelJarniac/repeaterbookWrote 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/micaeljarniac/repeaterbook/agents-md)<a href="https://agentmods.dev/instructions/micaeljarniac/repeaterbook/agents-md"><img src="https://agentmods.dev/badge/instructions/micaeljarniac/repeaterbook/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 5.1 | $0.01805 | $0.01805 |
| Opus 5 | $0.00903 | $0.00903 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
repeaterbook 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 5d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT KNOWLEDGE BASE
Generated: 2026-03-05 Commit: 23eae00 Branch: main
OVERVIEW
Python library for querying and caching ham radio repeater data from RepeaterBook.com. Core stack: aiohttp (async HTTP), SQLModel (ORM), attrs (immutable config), pydantic (validation).
STRUCTURE
repeaterbook/
├── src/repeaterbook/ # Library source (6 modules, ~1100 LOC)
│ ├── __init__.py # Public API: Repeater, RepeaterBook, exceptions
│ ├── models.py # SQLModel ORM + TypedDicts for API JSON + query types
│ ├── services.py # API client, HTTP fetching, JSON→model conversion
│ ├── database.py # SQLite persistence via SQLModel/SQLAlchemy
│ ├── queries.py # Geo-spatial query builders (square, radius, band filters)
│ ├── exceptions.py # 5-class hierarchy: RepeaterBookError base
│ └── utils.py # LatLon, Radius, SquareBounds helpers
├── tests/ # Pytest suite (1:1 with src modules)
│ ├── conftest.py # anyio_backend fixture, local aiohttp test server
│ └── integration/ # Live API tests (@pytest.mark.integration)
├── docs/ # MkDocs Material source
├── benchmarks/ # ASV benchmarking (scaffold only)
├── playground/ # Jupyter notebooks for experimentation
└── noxfile.py # Automation: lint, format, type-check, test, docs
WHERE TO LOOK
| Task | Location | Notes |
|---|---|---|
| Add/modify repeater fields | models.py → Repeater class |
SQLModel table + pydantic validators |
| Change API parsing logic | services.py → json_to_model() |
Handle NA vs ROW payload differences |
| Modify API endpoints/routing | services.py → RepeaterBookAPI.urls_export() |
NA vs ROW smart routing |
| Add query filters | queries.py |
Returns ColumnElement[bool] for SQLAlchemy |
| Change caching behavior | services.py → fetch_json() |
Atomic temp→rename write pattern |
| Database operations | database.py → RepeaterBook |
populate(), query() |
| Add new exception types | exceptions.py |
Inherit from RepeaterBookError |
| Geo calculations | utils.py |
Uses haversine library |
| Async test fixtures | tests/conftest.py |
local_server() spins up ephemeral aiohttp |
| CI pipeline | .github/workflows/ci.yml |
Dynamic Nox session matrix |
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.
- 5d ago First seen · 131 lines · 1,805 tokens per session scan A a63c23b68a29
repeaterbook AGENTS.md is an instructions file published in the GitHub repository MicaelJarniac/repeaterbook (3 stars, last pushed yesterday), licensed MIT. It adds 1,805 tokens to every session, about $0.0090 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
mempalace CLAUDE.md
Claude Code instructions for MemPalace/mempalace, covering claude.md, the mission, design principles, contributing and setup.
composio CLAUDE.md
Claude Code instructions for ComposioHQ/composio, a project described as: Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
MemMachine AGENTS.md
AGENTS.md instructions for MemMachine/MemMachine, covering memmachine agent guide, repository orientation, environment setup, build, lint, and test commands and python (repo root).
Test Generation
Comprehensive Pytest conventions, mocking strategies, and model usage rules for OpenWebUI plugins.
Cortex CLAUDE.md
Claude Code instructions for cdeust/Cortex, covering cortex — persistent memory mcp server, problem statement, build & test, releasing and architecture.
basic-memory CLAUDE.md
Claude Code instructions for basicmachines-co/basic-memory, a project described as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN.