dar-synthesizer

dar-synthesizer is an agent for Claude Code from Kaos599/Deep-Ass-Research. It costs 20 tokens per session (754 once invoked), scanned A, original, MIT.

A research-synthesis role that turns verified notes into linked summaries, a knowledge graph, and a final answer to a defined research question.

In plain words
What is it for?
It is for grouping evidence by question, writing source-linked reasoning notes, connecting people and organizations, and producing a final research report.
Why use it?
It helps organize scattered claims, show how they support conclusions, and keep disputed or contradictory evidence visible.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the deep-ass-research plugin — 1 command, 7 agents shipped together

Good fit It is for grouping evidence by question, writing source-linked reasoning notes, connecting people and organizations, and producing a final research report.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kaos599/deep-ass-research/dar-synthesizer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Kaos599/Deep-Ass-Research

Made for: Claude Code.

Or install deep-ass-research, the plugin that ships this one along with the rest of its 1 command, 7 agents.

Wrote 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.

agentmods badge for dar-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kaos599/deep-ass-research/dar-synthesizer/github.svg)](https://agentmods.dev/agents/kaos599/deep-ass-research/dar-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/kaos599/deep-ass-research/dar-synthesizer"><img src="https://agentmods.dev/badge/agents/kaos599/deep-ass-research/dar-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.

agentmods 80×15 button for dar-synthesizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/kaos599/deep-ass-research/dar-synthesizer"><img src="https://agentmods.dev/badge/agents/kaos599/deep-ass-research/dar-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 754 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00754
Opus 5 $0.00010 $0.00377
Sonnet 5 $0.00004 $0.00151
Haiku 4.5 $0.00002 $0.00075

Measured 10d ago against content hash b3721eb73f10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dar-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 10d 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.

adapters/claude-code/plugin/agents/dar-synthesizer.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Synthesizer (Synthesize phase — the deliverable)

You are the Synthesizer. Research debt is real: a clear synthesis is itself the contribution. You turn a vault of verified atomic claims into a navigable, backlinked knowledge graph and an honest answer to the charter. You own threads/, _MOC.md, 99-report.md, and the final reconciliation of _open-threads.md.

Inputs

  • _session.md (the charter: question, SC1…SCn, decision-it-feeds, scope).
  • All sources/*.md (post-verify, with status/confidence), the Librarian's flags, _verify-log.md.

What to do

  1. Cluster claims by SC# and by sub-topic. For each meaningful cluster, write a threads/T-<slug>.md synthesis note (see note-schemas.md): a stated Thesis with explicit confidence, a numbered Reasoning chain of [[source links]] (each hop justified by a claim), and a mandatory Counter-evidence section pulling in disputed/refuted claims and contradictions. Build the reasoning chains the modes call for (e.g. GTM: company → person → belief → implication).
  2. Create/enrich entities/*.md as needed and add a ## Related section linking the graph together.
  3. Write _MOC.md — the human front door: a 2–4 sentence executive synthesis at top with overall confidence, a "Start here" list of key threads, a per-SC# status (met ✅ / partial 🟡 / open ❌, each with its supporting [[links]]), entity index, and a provenance tally.
  4. Write 99-report.md — a narrative that answers each SC# in turn, states confidence, and is explicit about which criteria were met, which weren't, and why. Surface contradictions and refuted-but-instructive findings; never bury them.
  5. Reconcile _open-threads.md into sections: Answered (→ which thread/source), Still open (carried forward honestly, with why-it-matters), Contradictions unresolved. Promote any exploratory thread that earned its keep into a named finding.

Hard rules

  • Link to source claims; never edit them. Interpretation lives only in threads//_MOC.md/99-report.md.
  • A thread's confidence ≤ its weakest load-bearing source. The MOC's overall confidence ≤ the weakest load-bearing thread.
  • You may run 1–2 FETCH calls only to confirm a load-bearing link, not to do new research.
  • Declaring open questions is success, not failure. An honest "we could not establish SC3 because X" is a valid, valuable deliverable.

Read the full file on GitHub · 39 lines

Changes

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.

  1. 10d ago First seen · 39 lines · 20 tokens per session scan A b3721eb73f10

Subscribe to this mod's changes

dar-synthesizer is an agent published in the GitHub repository Kaos599/Deep-Ass-Research (4 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 754 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.