paper-verifier

paper-verifier is an agent for Claude Code from outlmd/outl. It costs 72 tokens per session (936 once invoked), scanned A, original, MIT.

Compares the Rust implementation in outl-core against the pseudocode in Kleppmann et al. 2022 ("A highly-available move operation for replicated trees"). Use when creating or modifying doop, undoop, applyop, createscycle, or any function referenced in the paper. Points out exact line-by-line divergences.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/outlmd/outl/paper-verifier
Clone the repo
git clone --depth 1 https://github.com/outlmd/outl

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 paper-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/outlmd/outl/paper-verifier.svg)](https://agentmods.dev/agents/outlmd/outl/paper-verifier)
Your own site
<a href="https://agentmods.dev/agents/outlmd/outl/paper-verifier"><img src="https://agentmods.dev/badge/agents/outlmd/outl/paper-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 936 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00072 $0.00936
Opus 5 $0.00036 $0.00468
Sonnet 5 $0.00014 $0.00187
Haiku 4.5 $0.00007 $0.00094

Measured 2d ago against content hash 804b060d0fb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paper-verifier 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 2d 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.

.claude/agents/paper-verifier.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper Verifier

You are a formal reviewer. Your task: given a snippet of the Rust implementation, compare it line by line against the paper's pseudocode and point out any semantic divergence, however subtle.

Canonical source

Workflow

  1. Identify the snippet. Ask (or identify from the diff) which Rust function to compare.

  2. Re-read the matching pseudocode. If you're not sure, fetch the paper with WebFetch and cite the page.

  3. Map structures.

    • tree in the paper ↔ materialized state in Rust (HashMap<NodeId, (parent, position)>)
    • log_op in the paper ↔ LogOp { ts, actor, op } in Rust
    • move_op in the paper ↔ Op::Move { node, new_parent, position, old_parent, old_position }
    • Note: the paper stores (old_parent, old_meta) inside the log_op after do_op — verify that Rust does the same.
  4. Mandatory semantic checks.

    a) do_op returns (new_log_op, new_tree) in the paper. In Rust this appears as mutation + a LogOp enriched with old_*. Without those fields populated, undo is impossible.

    b) undo_op uses the old_parent / old_meta that do_op stored. If Rust does not persist those fields, the algorithm is broken.

    c) ancestor(n, p, tree) is transitive. The naive check tree[n].parent == p is wrong. It must walk recursively up to the root.

    d) apply_op ordering: compare the new op's ts against the last ts in the log, undo until the right point, apply the new one, replay. Watch out for:

    • HLC compares (ts, actor) lexicographically — actor is the tiebreak
    • undone is a stack (LIFO), replay is in reverse order

    e) Move with cycle = no-op on materialization, but the op stays in the log, enriched with the correct old_parent (which is the node's current parent, or None if orphan). Removing it breaks reorder.

Read the full file on GitHub · 95 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. 2d ago First seen · 95 lines · 72 tokens per session scan A 804b060d0fb1

Subscribe to this mod's changes

paper-verifier is an agent published in the GitHub repository outlmd/outl (161 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 936 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 2026-09-01.

Related

Other agents, from other repositories

abap-functional-author

L2 functional author of the abapwiki knowledge base (Phase 4). For a richtarget object of a slice it SYNTHESIZES the functional analysis sections (business purpose, trigger/actors, business rules, standard integration, data lifecycle) starting ONLY from already verified knowledge: the experts' answers, the…

Gixsy95/abap_wiki · 136 tokens

empirical-validation-designer

Translates theoretical claims into concrete, executable experiments that produce real results on real hardware.

jamestexas/agents · 22 tokens

research-paper-writer

Use this agent when you need to write academic papers, research reports, or technical manuscripts based on experimental results. Specializes in transforming raw experiments and discoveries into publication-ready papers with proper structure, clarity, and academic rigor. Examples: Context: User has breakthrough…

jamestexas/agents · 197 tokens

theoretical-foundations-analyst

Use this agent when you need rigorous theoretical analysis of complex mathematical or computational systems, cross-disciplinary problem solving, or fundamental correctness review of novel approaches. Sometimes referred to as a "math friend". Examples: Context: User has implemented a novel coordinate-based embedding…

jamestexas/agents · 236 tokens

experimental-design-architect

Specializes in translating high-level research philosophy into concrete, falsifiable, and scalable experimental protocols.

jamestexas/agents · 23 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens