Neva is a statically typed programming language in which programs are message-passing graphs: nodes exchange data through ports and run concurrently by default. It is for developers building compiled programs with dataflow control, visual editing, and interoperability with Go. The catalogue includes skills and instructions for working with Neva.
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 skills/nevalang/neva/papercutnpx skills add nevalang/neva --skill papercutgit clone --depth 1 https://github.com/nevalang/nevaWrote 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/nevalang/neva/papercut)<a href="https://agentmods.dev/skills/nevalang/neva/papercut"><img src="https://agentmods.dev/badge/skills/nevalang/neva/papercut.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 5.1 | $0.00024 | $0.00351 |
| Opus 5 | $0.00012 | $0.00176 |
| Sonnet 5 | $0.00005 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
papercut 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 4d 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
Papercut
Use this skill when a person or agent encounters minor friction while doing other Neva work: a flaky command, stale cache, misleading error, obsolete script, or documentation that contradicts observed behavior.
The journal is .codex/papercuts.md.
It is not an issue tracker. Product, language, compiler, and runtime defects
belong in their owning GitHub issue or change; already-tracked work stays there.
Capture
-
Keep working on the original task unless the friction blocks it.
-
Add one entry directly below the journal marker, newest first:
## YYYY-MM-DD HH:MM TZ — author or model What I was doing -> what got in the way. Include the relevant command or error, workaround, and likely cause or fix when known. -
Record only evidence already observed. Never put credentials, access tokens, or private data in an entry.
Triage
- Read the full journal and group duplicate symptoms.
- Reproduce or otherwise verify each candidate before assigning a cause.
- Convert a meaningful item into the smallest durable outcome: a test, automation, documentation update, or GitHub issue.
- Link that outcome in the pull request or issue, then remove the triaged entry from the journal. Leave unverified entries intact.
Do not silently broaden the current task to implement a separate fix. Ask for direction when the remediation is material and not already in scope.
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.
- 4d ago First seen · 42 lines · 24 tokens per session scan A de2856d60075
papercut is a skill published in the GitHub repository nevalang/neva (1,079 stars, last pushed 13d ago), licensed MIT. It adds 24 tokens to every session and 351 once invoked, about $0.0001 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.
Other skills, from other repositories
external-model-selection
Choose optimal external AI models for code analysis, bug investigation, and architectural decisions. Use when consulting multiple LLMs via claudish, comparing model perspectives, or investigating complex Go/LSP/transpiler issues. Provides empirically validated model rankings (91/100 for MiniMax M2, 83/100 for Grok…
lsp-hover-testing
Automated LSP hover validation for Dingo transpiler. Use when testing hover functionality, validating position mappings, checking for hover drift, or debugging LSP issues after sourcemap changes.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
nightly-test-debugger
Analyze and debug failing nightly acceptance tests in this Go CLI repository. Use this skill whenever the user mentions nightly tests failing, CI failures in nightly.yml, acceptance test failures, or wants to investigate why a test failed in the nightly CI run. This includes diagnosing test failures, understanding…
reduce-unoptimized-query-oracle
Reduce an unoptimized-query-oracle test failure log to the simplest possible reproduction case. Use when you have unoptimized-query-oracle.log files from a failed roachtest and need to find the minimal SQL to reproduce the bug.
mma-investigator
Expert system for investigating MMA (Multi-Metric Allocator) behavior on CockroachDB clusters. Helps oncall engineers diagnose load imbalances, understand rebalancing decisions, and identify why MMA did or didn't act.