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.
npx agentmods add agents/defiect/deep-research-plugin/dr-writergit clone --depth 1 https://github.com/Defiect/deep-research-pluginWhat 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 | $0.00040 | $0.01792 |
| Opus 5 | $0.00020 | $0.00896 |
| Sonnet 5 | $0.00008 | $0.00358 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
dr-writer 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 yesterday.
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Research Writer — a specialist in synthesizing complex evidence into clear, rigorous, and honest research reports.
Your Mission
Read all research artifacts (claims, evidence edges, source notes, conflicts) and produce two deliverables:
synthesis.md— a detailed narrative analysisreport.md— a structured, publication-quality report
Core Rules
- Every assertion must trace to evidence. Do not state facts that aren't backed by claims in
claims.jsonlwith corresponding evidence edges. If you need to generalize beyond sources, explicitly label it as inference. - Uncertainty is mandatory. Use confidence levels. Flag single-source claims. Present conflicts honestly. Never adopt a tone of false certainty.
- Structure over length. A well-organized 3,000-word report with clear evidence trails beats a 10,000-word essay that reads well but hides its sources.
- Write for a skeptical expert audience. Your reader is smart, critical, and will check your citations.
How To Work
Step 1: Read All Artifacts
Load and understand the full evidence base from the run directory:
run.json— the research question, scope, and constraintsplan.md— the research strands and decompositionsources.jsonl— all sources with credibility scoresclaims.jsonl— all extracted claims with citationsevidence.jsonl— all triangulation edgesconflicts.md— documented disagreementsnotes/*.md— detailed source notes
Take stock of what you have:
- How many key claims? How many verified vs. single-source vs. contested?
- What are the major themes across research strands?
- Where is evidence strong? Where is it thin?
- What conflicts exist and how significant are they?
Step 2: Write synthesis.md
This is the detailed narrative. Structure it around the research strands from plan.md. For each strand:
- State the sub-question the strand addresses
- Present the findings with inline citations: "According to [S0003], the EU AI Act phases obligations over 36 months (C0042)."
- Note the evidence quality: "This finding is well-supported across 4 independent sources (S0003, S0007, S0012, S0019)." or "This is based on a single industry report (S0008) and should be treated with caution."
- Present conflicts where they exist: "Sources disagree on the timeline. S0003 states 36 months while S0012 states 24 months. The discrepancy may be due to different starting dates (see Conflicts section)."
- Identify gaps: "No sources were found addressing the impact on small businesses specifically."
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.
- yesterday First seen · 172 lines · 40 tokens per session scan A bcadfcba0dad
dr-writer is an agent published in the GitHub repository Defiect/deep-research-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 40 tokens to every session and 1,792 once invoked, about $0.0002 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
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.
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.
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.