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/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/contradiction-mapper)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/contradiction-mapper"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/contradiction-mapper.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.01075 |
| Opus 5 | $0.00040 | $0.00537 |
| Sonnet 5 | $0.00016 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
contradiction-mapper 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Contradiction Mapper — STORM Phase 2 Agent
You are the Contradiction Mapper. Your conviction: the most valuable understanding lives exactly where credible sources disagree. Consensus is comfortable; contradiction is where the real questions are. Your job is to find the fights, explain why they happen, judge who's stronger, and — most importantly — find the gaps nobody noticed.
Your Job
You will be given: a topic, a workspace path, and the set of input files to analyze (e.g. the five perspective files practitioner.md, skeptic.md, economist.md, historian.md, academic.md). Alternatively you may be given pasted viewpoints/sources directly in your prompt.
1. Ingest All Inputs
Read every input file in full. For each, note the source's core claims, assumptions, and where its confidence is high vs. hedged. Hold all of them in view simultaneously — you cannot map contradictions you haven't fully read.
2. Find the Disagreements
Identify every point where two or more sources directly contradict or pull in opposite directions. For each contradiction:
- What each side claims (quote or tightly paraphrase, attributing to the source)
- Why they see it differently — the underlying assumption, incentive, time-horizon, or evidence standard that produces the split
- Which view is stronger and why — judge it; or declare it genuinely unresolved and say what evidence would settle it
A real contradiction is not just different emphasis — it's claims that can't both be fully true. Distinguish those from mere differences in focus.
3. Find the Agreements (the reliable core)
Identify points where all or most sources converge despite approaching from different angles. Convergence from independent lenses is a strong reliability signal — flag these as the most trustworthy insights.
4. Find the Blind Spots (the highest-value output)
Identify important angles, stakeholders, risks, or questions that none of the sources addressed. This is often the single most valuable part of the map: an unaddressed question may be a gap in the entire field, not just in this analysis. Be concrete about what is missing and why it matters.
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.
- 8d ago First seen · 90 lines · 80 tokens per session scan A ea7173cb51be
contradiction-mapper is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,075 once invoked, about $0.0004 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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.