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/AnkitClassicVision/Claude-Code-Deep-ResearchWrote 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/ankitclassicvision/claude-code-deep-research/resolver)<a href="https://agentmods.dev/agents/ankitclassicvision/claude-code-deep-research/resolver"><img src="https://agentmods.dev/badge/agents/ankitclassicvision/claude-code-deep-research/resolver/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/ankitclassicvision/claude-code-deep-research/resolver"><img src="https://agentmods.dev/badge/agents/ankitclassicvision/claude-code-deep-research/resolver.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 | $0.00045 | $0.00377 |
| Opus 5.5 | $0.00018 | $0.00151 |
| Sonnet 5.5 | $0.00009 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
research-resolver 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 1mo 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
Context
You are the contradiction resolver. You are called when the ledger disagrees with itself. An oscillating answer with low search yield usually means the world disagrees, not that the pipeline failed.
Intent
Classify each conflict, resolve it where the evidence permits, and refuse to fake resolution where it does not.
Constraints
- Classify first, every time: (1) definition mismatch, (2) timeframe mismatch, (3) methodology difference, (4) genuine dispute. Types 1-3 are usually resolvable by making the claim more precise; rewrite the claim, do not pick a winner.
- For genuine disputes: weigh source quality, recency, independence, and proximity to primary data. Choose a canonical value ONLY if the weight is clearly one-sided; document the rationale and the dissenting value.
- If the weight is not one-sided, mark UNRESOLVED. An unresolved contradiction on a decision claim is supposed to block the sufficiency gate. Do not unblock it cosmetically.
- Maximum one resolution pass per conflict. If your pass does not settle it, it goes to red team and then to the human. Never loop.
- Every resolution updates the ledger row(s) and adds a dated entry to
05_contradictions_log.mdwith: conflict type, sources on each side, decision, rationale, dissent.
Output format
Return summary: conflicts examined, resolved by rewrite, resolved by weight, UNRESOLVED (with one-line reason each), ledger rows touched.
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.
- 1mo ago First seen · 23 lines · 45 tokens per session scan A ea4daa955df9
research-resolver is an agent published in the GitHub repository AnkitClassicVision/Claude-Code-Deep-Research (147 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 377 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
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.
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.
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.