Borrowing it
Nothing to install: this file belongs to themoment-team/datagsm-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/themoment-team/datagsm-server/master/.claude/agents/contradiction-finder.mdgit clone --depth 1 https://github.com/themoment-team/datagsm-serverWrote 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/themoment-team/datagsm-server/contradiction-finder)<a href="https://agentmods.dev/agents/themoment-team/datagsm-server/contradiction-finder"><img src="https://agentmods.dev/badge/agents/themoment-team/datagsm-server/contradiction-finder/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/themoment-team/datagsm-server/contradiction-finder"><img src="https://agentmods.dev/badge/agents/themoment-team/datagsm-server/contradiction-finder.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 | $0.00231 | $0.02236 |
| Opus 5.5 | $0.00092 | $0.00894 |
| Sonnet 5.5 | $0.00046 | $0.00447 |
| Haiku 4.5 | $0.00023 | $0.00224 |
Grade A, and why
contradiction-finder scanned grade A with 1 finding 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 19d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find .claude/rules -name "*.md" 2>/dev/null Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only consistency auditor. Your job is to find contradictions across four layers and output a structured report. You never edit files.
Layer Overview
| Layer | What is checked |
|---|---|
| L1: doc↔doc | .claude/rules/** vs AGENTS.md vs .gemini/styleguide.md vs CONTRIBUTING.md vs copilot-instructions.md |
| L2: doc↔code | Documented rules vs actual .kt file patterns (full codebase, grep-based) |
| L3: doc↔agent/skill | AGENTS.md + .claude/rules/** rules vs agent .md and skill SKILL.md definitions |
| L4: agent↔agent | Trigger condition overlap and scope conflict between agent definitions |
Independence rule: The Claude side (.claude/) and the Codex side (.agents/, .codex/) are independent systems. Differences between equivalent files across these two sides are NOT contradictions and must not be reported as such.
Step 1 — Collect All Source Material
Rule Files (discover dynamically)
find .claude/rules -name "*.md" 2>/dev/null
Read every file returned. These files are the primary rule source.
Documentation
Read these files in full:
AGENTS.mdCONTRIBUTING.md.gemini/styleguide.md.github/copilot-instructions.md
Agent and Skill Definitions
Use Glob to collect and Read:
.claude/agents/*.md.claude/skills/**/*.md.agents/skills/**/*.md
Kotlin Source File List (for L2)
find . -name "*.kt" -not -path "*/build/*" -not -path "*/test/*" -not -path "*/.gradle/*"
Collect the file list. Do NOT read every file — use targeted Grep queries in Step 3.
Step 2 — Layer 1: doc↔doc
After reading all rule files in Step 1, extract the topics they define (e.g., DTO annotations, logging format, exception messages). For each topic found, cross-check the same rule across all documentation files and look for contradictions.
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.
- 19d ago Changed · -1 lines · -2 tokens per session 38c02cf8afb3
- 29d ago First seen · 165 lines · 233 tokens per session scan A 04fd86d76eee
contradiction-finder is an agent published in the GitHub repository themoment-team/datagsm-server (29 stars, last pushed yesterday), licensed MIT. It adds 231 tokens to every session and 2,236 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
contradiction-finder compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| contradiction-finderthemoment-team/datagsm-server | Agent | 29 | yesterday | MIT | A | 231 | Claude Code |
| aws-architecture-review-expertgiuseppe-trisciuoglio/developer-kit | Agent | 367 | 1mo ago | MIT | A | 76 | Claude Code |
| langchain4j-ai-development-expertgiuseppe-trisciuoglio/developer-kit | Agent | 367 | 1mo ago | MIT | A | 65 | Claude Code |
| spring-boot-unit-testing-expertgiuseppe-trisciuoglio/developer-kit | Agent | 367 | 1mo ago | MIT | A | 58 | Claude Code |
| spring-code-reviewerloiane/specs-driven-development-spring-angular | Agent | 62 | yesterday | MIT | A | 41 | Claude Code |
| prompt-engineering-expertgiuseppe-trisciuoglio/developer-kit | Agent | 367 | 1mo ago | MIT | A | 70 | Claude Code |
| m3-expressive-guideahmed3elshaer/everything-claude-code-mobile | Agent | 66 | 4mo ago | MIT | A | 54 | Claude Code |