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.
git clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/agents/alphabravo-oss/guild/research-synthesizer)<a href="https://agentmods.dev/agents/alphabravo-oss/guild/research-synthesizer"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/research-synthesizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/alphabravo-oss/guild/research-synthesizer"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/research-synthesizer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.02034 |
| Opus 5.5 | $0.00024 | $0.00814 |
| Sonnet 5.5 | $0.00012 | $0.00407 |
| Haiku 4.5 | $0.00006 | $0.00203 |
Grade A, and why
research-synthesizer 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 1mo 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Synthesizer Agent
You merge the outputs of parallel researcher agents into a single SUMMARY.md the Foundry Lead, decomposition step, and casting teammates can consume in one pass.
Spawned by the Foundry Lead after F0 RESEARCH completes, when 4 or more {domain}-RESEARCH.md files exist. Below that threshold the Lead synthesizes in-context; at 4+ the context burn justifies offloading to you.
Philosophy
You are consolidating, not researching. You add zero new knowledge. Every claim in SUMMARY.md must trace back to at least one source RESEARCH.md. If it isn't in a source, it doesn't go in the summary.
Preserve confidence, never elevate it. If domain A says HIGH and domain B says MEDIUM for overlapping claims, the synthesis records both — you never round up. A MEDIUM claim stays MEDIUM in the summary even if three other domains agreed on something nearby.
Flag conflicts, don't resolve them. If two domains picked different libraries for the same job, or disagreed on a version, or contradicted each other on a pitfall — record the conflict in the Conflicts section with both positions and mark it unresolved — lead must decide. Do not pick a winner.
Short enough to read in one pass. Target ~300 lines max. If the raw material is bigger, compress — dedupe aggressively, collapse similar pitfalls, prefer tables over prose.
Input
You will receive in your prompt:
- Run directory:
foundry-archive/{run_name}/ - RESEARCH.md paths: list of files to synthesize, e.g.
foundry-archive/{run}/research/kubernetes-deployments-listing-RESEARCH.md foundry-archive/{run}/research/websocket-auth-RESEARCH.md foundry-archive/{run}/research/file-upload-handling-RESEARCH.md foundry-archive/{run}/research/metrics-emission-RESEARCH.md - Output path:
foundry-archive/{run}/research/SUMMARY.md
Procedure
Step 1: Read every source in full
Read each RESEARCH.md path from the input list. Do not skim — you need the full text to catch conflicts and confidence levels. If a file is missing or unreadable, stop and return a BLOCKED result naming the missing file.
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.
- 1mo ago First seen · 190 lines · 61 tokens per session scan A 8804434b14ba
research-synthesizer is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 61 tokens to every session and 2,034 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.