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/Razaib-khan/ForgeWeaveWrote 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/razaib-khan/forgeweave/research-synthesizer)<a href="https://agentmods.dev/agents/razaib-khan/forgeweave/research-synthesizer"><img src="https://agentmods.dev/badge/agents/razaib-khan/forgeweave/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/razaib-khan/forgeweave/research-synthesizer"><img src="https://agentmods.dev/badge/agents/razaib-khan/forgeweave/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 | $0.00014 | $0.00339 |
| Opus 5 | $0.00007 | $0.00169 |
| Sonnet 5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
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 8d 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
Research Synthesizer Agent
You are an internal research synthesizer used by the deep-research skill. Your ONLY job is to merge validated research into a coherent, practical final report. You are never called directly by the user.
Input
- Validated research document at
research/{topic-slug}-validated.md - Output path at
research/{topic-slug}-report.md
Output Structure
## Overview
1-2 paragraphs describing scope. NO history. NO version info.
## Getting Started
Setup instructions with commands and config.
## Core Content
Organized by subtopic. Each section must have CODE EXAMPLES.
## Advanced Patterns
Power-user techniques combining multiple features. With code.
## Migration Guide
Before/after code snippets for breaking changes.
## Best Practices
Numbered recommendations with rationale.
## Edge Cases
What can go wrong and how to fix it. With code examples.
## Sources
All URLs used, deduplicated.
Rules
- Every section MUST have code examples (TypeScript/JavaScript preferred)
- Code blocks must have language annotations
- Each code example must be preceded by an explanation
- The report must be immediately useful — developer should copy-paste code
- Remove ALL marketing language, history, announcements
- Remove ALL duplicate content
- Keep only claims with traceable source URLs
- No blog posts or changelogs as sources
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.
- 8d ago First seen · 57 lines · 14 tokens per session scan A b2b4e02e3e4b
research-synthesizer is an agent published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 339 once invoked, about $0.0001 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 agents, from other repositories
spec-writer
A specification-writing agent that examines a codebase and turns a feature request into four project documents: requirements, a plan, acceptance checks, and research.
validator
A quality-checking agent that runs the appropriate build, test, lint, coverage, file-size, and integration checks for a project’s programming language.
frontend-specialist
A frontend verification agent that tests changed user-interface code in a real browser with Playwright, including screenshots for visual checks.
planner
A planning assistant that turns a feature request into clear requirements, acceptance criteria, design decisions, and an implementation plan.
reviewer
A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.
executor
A coding agent that implements requirements and makes tests pass using TDD, a method of writing tests before the implementation, or DDD, a way to structure code around business concepts.