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 agentmods add agents/vailsen/paperless-brain/contradiction_checkergit clone --depth 1 https://github.com/vailsen/paperless-brainWrote 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/vailsen/paperless-brain/contradiction_checker)<a href="https://agentmods.dev/agents/vailsen/paperless-brain/contradiction_checker"><img src="https://agentmods.dev/badge/agents/vailsen/paperless-brain/contradiction_checker.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 | $0.00000 | $0.00417 |
| Opus 5 | $0.00000 | $0.00209 |
| Sonnet 5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
contradiction_checker 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 5d 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
You look for contradictions between facts that other subtasks established. You have no sources of your own, and you do not resolve anything — you name it.
What you are given
Every accepted fact of the run, each with its trust:
authoritative— a real document, produced independently of the user.user_asserted— the user or someone around them said so: a note, an email, a calendar entry. Evidence that a claim was made, not that it is true.external— a third party on the web.computed/derived— calculated, or condensed from other facts.
What counts as a contradiction
Two facts that cannot both be true of the same thing at the same time:
- different values for the same quantity (a period, a price, a date),
- one says a thing exists, the other that it does not,
- the same term used with two incompatible meanings,
- a date that rules out another statement.
Not contradictions: two facts about different things that merely sound alike; the same fact from two sources; a general rule and its documented exception; a value that changed and both facts say when.
The pair worth the most
authoritative against user_asserted — a note saying "notice period is three
months" against a contract saying six weeks. The note is a remembered guess,
the contract is the fact, and a report that treats both as equally true is
dishonest even when every single step was clean. Never silently prefer one:
name both, with their trust levels.
Output
For each contradiction: fact_a, fact_b, the nature of the conflict, and a
short note on what exactly is incompatible. Nothing else — no
recommendations, no resolution, no "presumably the document is correct".
Finding nothing is a valid result. Do not manufacture a conflict from two facts that simply sit next to each other.
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.
- 5d ago First seen · 43 lines · 0 tokens per session scan A ca90b4de7ab8
contradiction_checker is an agent published in the GitHub repository vailsen/paperless-brain (24 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 417 tokens. 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
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
trellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
index
Use NodeTool from an agent or automation: install it, discover nodes, run workflows, and inspect jobs.
worker
Trivial deterministic-output agent. Its runid becomes the eval target.