Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add drobins25/craft/plugin install craftWrote 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/drobins25/craft/research-synthesizer)<a href="https://agentmods.dev/agents/drobins25/craft/research-synthesizer"><img src="https://agentmods.dev/badge/agents/drobins25/craft/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/drobins25/craft/research-synthesizer"><img src="https://agentmods.dev/badge/agents/drobins25/craft/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 | $0.00275 | $0.03169 |
| Opus 5 | $0.00138 | $0.01584 |
| Sonnet 5 | $0.00055 | $0.00634 |
| Haiku 4.5 | $0.00028 | $0.00317 |
Grade C, and why
research-synthesizer scanned grade C with 1 finding 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Model Rationale (last reviewed: 2026-05-29) The research-synthesizer runs on sonnet. This is a deliberate, locked choice. Before downgrading the model field above, read this block in full and complete the re-validat How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Synthesizer
You are a cross-branch synthesizer. You read every branch file in a research topic folder - each one a factual extraction produced by a researcher agent - and you produce two artifacts: _plan.md (the ranked synthesis the user reads) and _sources.md (the citation index). You replace synthesis work that used to happen in the user's main conversation loop, which is why your output goes straight to disk and you return only a brief summary.
You synthesize. You do NOT launder. The branch files are an honest record, including where they disagree. Your job is to rank, find genuine convergence, and route conflicts faithfully - never to smooth contradictions into a tidy story.
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.
- 9d ago First seen · 242 lines · 275 tokens per session scan C 0da75a1c00a6
research-synthesizer is an agent published in the GitHub repository drobins25/craft (53 stars, last pushed yesterday), licensed MIT. It adds 275 tokens to every session and 3,169 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
claudehut-brainstormer
Generates 2+ genuinely distinct solution options and recommends one; returns the candidate enforcement set. Any problem type. Never writes code.
claudehut-implementer
Executes the plan test-first under the project's conventions, in an isolated worktree. Honors every rule that auto-loads for the files it touches.
claudehut-learner
Extracts candidate learnings for the Learn phase and keeps the reuse + memory indexes current. Carries project-scoped auto-memory.
claudehut-planner
Turns the implementation spec into a file-level, executable, test-first plan. Writes the plan file; never production code.
claudehut-reuse-scanner
Finds existing implementations to adopt or extend before any new code is written, and produces the reuse-scan artifact the write gate requires.
claudehut-reviewer
General code review — correctness, readability, conventions, dead code, over-engineering — against the enforcement set and project rules.