scan-contradictions

scan-contradictions is a skill for Claude Code from ayeshakhalid192007-dev/graph-engineering-crash-course. It costs 47 tokens per session (952 once invoked), scanned A, original, MIT.

A standalone check for contradictory facts in a graph, where information is stored as subject–predicate–object relationships. It compares claims about the same subject and relationship.

In plain words
What is it for?
Use it to scan the default filings or another supplied graph for conflicting values attached to the same subject and predicate.
Why use it?
It flags pairs of claims that cannot both be true while ignoring unrelated facts.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code.

Good fit Use it to scan the default filings or another supplied graph for conflicting values attached to the same subject and predicate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ayeshakhalid192007-dev/graph-engineering-crash-course/scan-contradictions
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.

Any agent
npx skills add ayeshakhalid192007-dev/graph-engineering-crash-course --skill scan-contradictions
Clone the repo
git clone --depth 1 https://github.com/ayeshakhalid192007-dev/graph-engineering-crash-course

Made for: Claude Code.

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 scan-contradictions

README.md
[![agentmods](https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/scan-contradictions/github.svg)](https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/scan-contradictions)
Your own site
<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/scan-contradictions"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/scan-contradictions/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 scan-contradictions

Your own site · 80×15
<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/scan-contradictions"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/scan-contradictions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 952 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 $0.00047 $0.00952
Opus 5 $0.00023 $0.00476
Sonnet 5 $0.00009 $0.00190
Haiku 4.5 $0.00005 $0.00095

Measured 9d ago against content hash 4d87c87a1e32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

scan-contradictions 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 9d 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.

starters/contradiction-detector/.claude/skills/scan-contradictions/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

scan-contradictions

Reads every edge in the graph (or the portion touched by a recent write), groups edges by subject and predicate, and checks each group for object values that can't all be true of the same subject at once — flagging those pairs and only those pairs.

Instructions

You are a Claude Code skill implementing the contradiction-detector pattern. Follow these steps in order:

  1. Read the full set of edges to scan. Default to the filings in this kit's README.md unless the user gives you a different graph or subset. Do not scope the scan to any particular task's needs — this skill runs standalone, independent of what any task currently wants from the graph.
  2. Group edges by (subject, predicate) pair. Two edges can only possibly contradict each other if they name the same subject and the same predicate — an edge about a segment's material and an edge about the same segment's installation-year are never in tension with each other, no matter how different their values look, because they aren't asserting anything about the same fact.
  3. Within each group, compare the object values pairwise. For each pair of edges sharing a subject and predicate:
    • If the object values are the same (or state-compatible — e.g., two independent readings that agree), this is corroboration, not a contradiction. Do not flag it.
    • If the object values assert mutually exclusive states of the same subject at the same predicate (a segment cannot be both structurally-sound and requires-replacement at once), this is a contradiction. Flag the pair.
  4. Do not infer contradictions across different predicates or different subjects, even when the two edges come from the same source document or the same contractor. Same-source proximity is not evidence of contradiction — only a shared subject and predicate with opposed values is.
  5. Do not resolve the contradiction. This skill's job stops at flagging the pair — it never decides which reading is correct, drops either edge, or picks a "more trustworthy" source. That decision belongs to whatever process consumes the flag.
  6. Report every flagged pair with both edges' full detail (subject, predicate, object, source), and separately confirm which groups were checked and found to corroborate rather than conflict, so a reader can tell "checked, no contradiction" apart from "never checked."

Read the full file on GitHub · 92 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. 9d ago First seen · 92 lines · 47 tokens per session scan A 4d87c87a1e32

Subscribe to this mod's changes

scan-contradictions is a skill published in the GitHub repository ayeshakhalid192007-dev/graph-engineering-crash-course (5 stars, last pushed 14d ago), licensed MIT. It adds 47 tokens to every session and 952 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.

Related

Other skills, from other repositories

animate

Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…

ericrisco/rsc-harness · 75 tokens

building-agents

Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…

ericrisco/rsc-harness · 85 tokens

postgresdb

Use when PostgreSQL engine behaviour decides the answer — schema and type design, index choice, reading EXPLAIN on a slow query, zero-downtime DDL and backfills, or ops (roles, RLS, pooling, vacuum, partitioning, PITR). PG16, ORM-agnostic. NOT portable query logic (that is sql), NOT a managed provider's platform…

ericrisco/rsc-harness · 91 tokens

author-skill

Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its evals, auditing it against the rubric. NOT building a product feature (that is specify) and NOT designing an agent loop…

ericrisco/rsc-harness · 79 tokens

community

Use when building or running a persistent two-way community space — Discord, Telegram, Circle: platform choice, structure, onboarding, native→bot→human moderation, rituals, growth loops, health metrics. NOT churn of paying product customers (that is retention), NOT broadcast email (that is newsletter), NOT one live…

ericrisco/rsc-harness · 77 tokens

cpp

Use when writing, reviewing, modernizing, building, or debugging C++ - RAII and resource lifetime, smart-pointer ownership, move semantics and the Rule of Zero/Five, target-based CMake with FetchContent, and killing undefined behavior with ASan/UBSan/TSan plus clang-tidy. NOT borrow-checker / Result-Option / cargo…

ericrisco/rsc-harness · 81 tokens