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 skills/droxer/synapse/deep-researchnpx skills add droxer/Synapse --skill deep-researchgit clone --depth 1 https://github.com/droxer/SynapseWhat 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 | $0.00058 | $0.01209 |
| Opus 5 | $0.00029 | $0.00605 |
| Sonnet 5 | $0.00012 | $0.00242 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
deep-research 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research Methodology
You are conducting deep research — not a quick lookup. Your goal is to produce a thorough, well-sourced analysis that the user can trust and act on.
Phase 1: Decompose the Question
Before searching, break the user's question into 3–6 sub-questions that together cover the full scope. Write them out explicitly.
Example — user asks "Should we migrate from REST to GraphQL?":
- What are the current technical limitations of REST for our use case?
- What performance and developer-experience benefits does GraphQL offer?
- What are the known operational costs and pitfalls of GraphQL at scale?
- What do teams who migrated back from GraphQL report?
- What is the current industry adoption trend and tooling maturity?
This decomposition guides all subsequent searches.
Phase 2: Broad Search (Round 1)
For each sub-question, run a targeted web_search query. Use diverse query formulations:
- Factual query — direct question phrased for search engines
- Authoritative query — target official docs, research papers,
.gov,.edu,.org - Contrarian query — "problems with X", "X criticism", "X vs Y disadvantages"
- Recent query — append current year or "2025" / "2026" for fast-moving topics
Request 5 results per query. Track all URLs seen — discard duplicates across queries.
After completing all broad searches, use user_message to send the user a brief progress update (e.g., "Completed broad search across 5 sub-questions. Found 18 unique results. Moving to deep dive on top 5 sources.").
Phase 3: Deep Dive (Round 2)
From Round 1 results, select the top 3–5 most promising URLs and fetch their full content with web_fetch. Prioritize:
- Primary sources (official documentation, research papers, data sets)
- In-depth technical posts with benchmarks or case studies
- Sources that represent opposing viewpoints
When reading fetched content:
- Extract specific data points: numbers, dates, benchmarks, quotes
- Note the publication date and author credentials
- If a page fails to load or is paywalled, note it and search for an alternative
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 · 123 lines · 58 tokens per session scan A d54884447e0d
deep-research is a skill published in the GitHub repository droxer/Synapse (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,209 once invoked, about $0.0003 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 skills, from other repositories
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.