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 skills add ayeshakhalid192007-dev/graph-engineering-crash-course --skill scan-contradictionsgit clone --depth 1 https://github.com/ayeshakhalid192007-dev/graph-engineering-crash-courseWrote 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/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/scan-contradictions)<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.
<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>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 | $0.00047 | $0.00952 |
| Opus 5 | $0.00023 | $0.00476 |
| Sonnet 5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
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.
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:
- Read the full set of edges to scan. Default to the filings in this
kit's
README.mdunless 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. - 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
materialand an edge about the same segment'sinstallation-yearare never in tension with each other, no matter how different their values look, because they aren't asserting anything about the same fact. - 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-soundandrequires-replacementat once), this is a contradiction. Flag the pair.
- 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.
- 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.
- 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."
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.
- 9d ago First seen · 92 lines · 47 tokens per session scan A 4d87c87a1e32
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.
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…
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…
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…
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…
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…
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…