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/dedalus-labs/dedalus-mcp-python/agents-mdgit clone --depth 1 https://github.com/dedalus-labs/dedalus-mcp-pythonWhat 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 | $0.01657 | $0.01657 |
| Opus 5 | $0.00829 | $0.00829 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
dedalus-mcp-python 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- dedalus-mcp-python AGENTS.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guidelines for Coding Agents
Dedalus MCP implements the Model Context Protocol. Spec-faithful, minimal surface.
Quick Reference
| What | Where |
|---|---|
| MCP spec | internals/references/modelcontextprotocol/ |
| Reference SDK | internals/references/python-sdk/ |
| Server core | src/dedalus_mcp/server/core.py |
| Versioning | src/dedalus_mcp/versioning.py |
| Types | src/dedalus_mcp/types/ |
| Tests | tests/ |
Before You Code
Scan wide before you write. Search for logic that already does what you need. Search for logic that could help your implementation. Understand where your contribution fits contextually within this codebase. Don't write a single line until you understand these relationships.
- Grep (or rg) the codebase for related functionality. It may already exist!
- Find the spec section for what you're implementing
- Look at similar existing code for patterns and conventions
- Identify code that your implementation should integrate with
Test-Driven Development
Write tests first. This project follows TDD. Don't implement features in a vacuum—define what "correct" looks like before you write production code.
The workflow:
-
Create or update an execspec — For any significant work, maintain a local
EXECSPEC-{topic}.mdindocs/dedalus_mcp/. This is your working document: what you're building, what invariants must hold, what's done, what's next. -
Write a failing test — Before implementing, write a test that captures an invariant from your execspec. The test should fail because the feature doesn't exist yet.
-
Make it pass — Write the minimal code to make the test pass. No more.
-
Refactor — Clean up while tests are green.
-
Repeat — Each passing test is a small victory. Accumulate these toward the full vision.
Example execspec structure:
# EXECSPEC: Elicitation Support
## Goal
Implement client-side elicitation per MCP 2025-06-18.
## Invariants
- [ ] `elicit()` raises if server doesn't advertise elicitation capability
- [ ] Timeout triggers `ElicitationTimeoutError`
- [ ] Response schema is validated against `ElicitationResult`
## Progress
- [x] Basic request/response flow
- [ ] Timeout handling
- [ ] Schema validation
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 · 192 lines · 1,657 tokens per session scan A 41c5315910e6
dedalus-mcp-python AGENTS.md is an instructions file published in the GitHub repository dedalus-labs/dedalus-mcp-python (143 stars, last pushed 7mo ago), licensed MIT. It adds 1,657 tokens to every session, about $0.0083 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
chimp AGENTS.md
Instructions for softwaremill/chimp, covering rules, 1 - protocol conformance, 2 - tests organization, 3 - conformance tests and 4 - documentation.
wet-mcp AGENTS.md
Instructions for n24q02m/wet-mcp, covering agents.md - wet-mcp, cau truc, lenh thuong dung, mise shortcuts and cau hinh quan trong.
luxembourg-mcp CLAUDE.md
Instructions for amirdaraee/luxembourg-mcp, covering claude.md, commands, hard constraint: zero dependencies, architecture and adding or changing a tool touches five places.
plain CLAUDE.md
Claude Code instructions for dropseed/plain, covering claude, after making code changes, commands, scratch directory and testing changes.
datalens-dev-mcp AGENTS.md
Instructions for ADIKANT/datalens-dev-mcp, covering agents.md, scope, read order, local material policy and public change hygiene.
openai-agents-python CLAUDE.md
Instructions for openai/openai-agents-python, a project described as: A lightweight, powerful framework for multi-agent workflows.