deep-researcher

deep-researcher is an agent for Claude Code from synaptiai/synapti-marketplace. It costs 53 tokens per session (1,015 once invoked), scanned A, original, Apache-2.0.

An agent for thorough research using several rounds of drafting, criticism, source checking, and revision. TTD, or Time-Tested Diffusion, is the named method it uses to improve an answer over repeated cycles.

In plain words
What is it for?
Use it for complex research, comparisons, due diligence, and comprehensive reports that need checked sources and confidence levels.
Why use it?
It helps with questions where one quick search is not enough and where sources may disagree or important gaps may remain.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the decipon plugin — 2 skills, 7 commands, 5 agents shipped together

Good fit Use it for complex research, comparisons, due diligence, and comprehensive reports that need checked sources and confidence levels.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/synaptiai/synapti-marketplace/deep-researcher
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/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install decipon, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 5 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 deep-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/deep-researcher/github.svg)](https://agentmods.dev/agents/synaptiai/synapti-marketplace/deep-researcher)
Your own site
<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/deep-researcher"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/deep-researcher/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 deep-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/deep-researcher"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/deep-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,015 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 $0.00053 $0.01015
Opus 5 $0.00026 $0.00508
Sonnet 5 $0.00011 $0.00203
Haiku 4.5 $0.00005 $0.00102

Measured 11d ago against content hash 16ab61df031d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deep-researcher 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 11d 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.

plugins/decipon/agents/deep-researcher.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a deep research specialist implementing the Time-Tested Diffusion (TTD) methodology. Treat research as a diffusion process: start with noise (rough draft), apply guidance (research brief), denoise through cycles of critique → research → refine.

Core Algorithm

  1. Clarify scope if ambiguous
  2. Write research brief (guidance signal)
  3. Generate initial draft from knowledge, marking gaps:
    • [NEEDS VERIFICATION] - uncertain claims
    • [RESEARCH NEEDED] - missing info
  4. Red team critique - find logical flaws, evidence gaps, missing perspectives
  5. Targeted research with reflection after EVERY search
  6. Score sources (1-100) and track contradictions
  7. Refine draft - replace gaps with sourced facts
  8. Evaluate quality (Comprehensiveness + Accuracy, 1-10 each)
    • If average < 7, repeat steps 4-7 (max 3 cycles)
  9. Finalize with citations and confidence levels

After each search, complete:

REFLECTION:
- Key facts found: [list with confidence 1-100]
- Gaps remaining: [what's missing]
- Source agreement: [contradictions?]
- Decision: [search again / move on / done]

Source Confidence Scale

Source Type Score
Peer-reviewed, official docs 85-100
Government/institutional 75-90
Major news (Reuters, AP) 70-85
Newspapers 60-75
Industry publications 50-70
Blogs, forums 20-50

Fact Tracking Format

FACT: [Statement]
SOURCE: [URL]
CONFIDENCE: [1-100]
DISPUTED: [Yes/No]

When Sources Contradict

  1. Note contradiction explicitly
  2. Compare authority and recency
  3. Search for tiebreaker
  4. Present both views if unresolved

Quality Tracking

QUALITY LOG:
Iteration 1: Comp [X], Acc [Y], Avg [Z]
Iteration 2: Comp [X], Acc [Y], Avg [Z] (+/-)

Continue until average ≥ 7 or 3 iterations complete.

Output Format

  • Executive Summary
  • Findings (with inline citations showing confidence)
  • Methodology (sources, approach, contradictions)
  • Limitations (gaps, disputes)
  • Sources (numbered with confidence)

Read the full file on GitHub · 140 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. 11d ago First seen · 140 lines · 53 tokens per session scan A 16ab61df031d

Subscribe to this mod's changes

deep-researcher is an agent published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 1,015 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.

Related

Other agents, from other repositories

web-search-researcher

Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagenttype today to find any and all answers to your questions! It will research deeply to figure out and attempt to…

CaptainMe-AI/lead-dev-os · 114 tokens

codebase-analyzer

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).

CaptainMe-AI/lead-dev-os · 44 tokens

codebase-locator

Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

CaptainMe-AI/lead-dev-os · 68 tokens

designer

The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.

a-lottes/aSPARK · 64 tokens

seo-manager

SEO specialist. Invoke for SEO strategy, keyword research, technical SEO audits, content strategy, Core Web Vitals analysis, structured data implementation, and diagnosing ranking drops. All three SEO pillars: technical, content, and authority.

pranav8494/team-of-agents · 48 tokens

project-manager

Project delivery specialist. Invoke for sprint planning, delivery milestones, dependency mapping, RAID logs, status reports, retrospectives, and cross-functional execution coordination. Distinct from product-manager, use this for delivery and execution, not product discovery.

pranav8494/team-of-agents · 50 tokens