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/softwaremill/chimp/agents-mdgit clone --depth 1 https://github.com/softwaremill/chimpWhat 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 | $0.00342 | $0.00342 |
| Opus 5 | $0.00171 | $0.00171 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
chimp 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.
What it actually says
Overview
Chimp is an SDK for building MCP (Model Context Protocol) servers and clients in Scala 3 using boilerplate-less, type-safe APIs based on Tapir and sttp, supporting the variety of the Scala ecosystem.
This is public OSS project.
Rules
1 - Protocol Conformance
Supported protocol version are located in chimp.protocol.ProtocolVersion. ALWAYS refer and check your implementation
against the official MCP specification https://modelcontextprotocol.io/specification.
2 - Tests organization
Most MCP behaviour is identical across transports and effect backends, such tests are defined once and run everywhere. When implementing tests ALWAYS place them in shared trait's unless they are somehow specific.
3 - Conformance tests
When working with conformance tests ALWAYS refer to the actual sources https://github.com/modelcontextprotocol/conformance.
For instructions on client conformance refer to /client-conformance/README.md.
For instructions on server conformance refer to /server-conformance/README.md.
4 - Documentation
Document a change ONLY when it is:
- non-obvious to the users
- specific to a particular effect backend
- implementing support for a new protocol feature
For specific instructions on working with the docs refer to /docs/README.md.
5 - Language
ALWAYS use ASD-STE100 Simplified Technical English for documentation, responses and user interactions.
6 - Code comments
NEVER add any comments in the code, unless you're asked to do so.
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 · 46 lines · 342 tokens per session scan A 1de1d60d9ac9
chimp AGENTS.md is an instructions file published in the GitHub repository softwaremill/chimp (102 stars, last pushed 7d ago), licensed Apache-2.0. It adds 342 tokens to every session, about $0.0017 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 2026-08-30.
Other instructions, from other repositories
dedalus-mcp-python AGENTS.md
Instructions for dedalus-labs/dedalus-mcp-python, covering guidelines for coding agents, quick reference, before you code, test-driven development and execspec: elicitation support.
dedalus-mcp-python CLAUDE.md
Instructions for dedalus-labs/dedalus-mcp-python: This file will be deprecated soon (see here).
pup CLAUDE.md
Instructions for DataDog/pup, covering pup - datadog api cli, documentation index, review guidelines, quick start and install via homebrew (recommended).
KtorMonitor AGENTS.md
Instructions for CosminMihuMDC/KtorMonitor, covering agents.md — ktormonitor, 1. project overview, 2. module structure, source-set layout (core) and 3. build, test, run.
openai-scala-client CLAUDE.md
Instructions for cequence-io/openai-scala-client, covering claude.md, project overview, build & test commands, core commands and cross-build.
mail-time AGENTS.md
Instructions for veliovgroup/mail-time, covering agents.md, mission, topology / tuning (read readme for use-cases), multiple instances — encouraged and one mail host: 2–8 servers.