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 instructions/nevalang/neva/agents-mdgit clone --depth 1 https://github.com/nevalang/nevaWhat 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 | $0.01227 | $0.01227 |
| Opus 5 | $0.00613 | $0.00613 |
| Sonnet 5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
neva AGENTS.md scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Use `gh` for GitHub context before falling back to `curl`. How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neva Engineering Guide
This file is the repository's high-level engineering map for humans and robots. Read the canonical document for the subsystem before changing it. Keep this guide concise: it routes work; it does not duplicate documentation.
Project Model
Neva is a statically typed, compiled dataflow language. Programs are explicit node-and-connection graphs, and concurrency is the default execution model.
Compiler pipeline:
parser -> analyzer -> desugarer -> IR generator -> Go backend
The standard library combines Neva components with native runtime-backed
components declared through #extern.
Repository Map
.
|- cmd/ CLI entrypoint.
|- internal/
| |- compiler/ Frontend, lowering, IR, and code-generation backends.
| `- runtime/ Messages, ports, program execution, and native functions.
|- std/ Public standard-library packages and component contracts.
|- e2e/ Isolated regression modules with Go test harnesses.
|- examples/ User-facing executable examples in one shared module.
|- benchmarks/ Explicit runtime and language performance scenarios.
|- docs/
| |- user/ Language behavior, APIs, style, and learning material.
| `- developer/ Compiler, runtime, test, and contributor guidance.
`- .codex/ Repository-local skills, plans, and agent automation.
The language server lives in nevalang/neva-lsp, not in this repository.
Documentation
Documentation is organized by primary reader, not by a one-way dependency graph. Keep each topic canonical in one place.
- Public language behavior, API semantics, and Neva style belong in
docs/user/. - Compiler, runtime, standard-library implementation, and test strategy belong
in
docs/developer/. - User documentation must be self-contained and must not link to developer documentation. Developer documentation may link to user documentation, since contributors are expected to know the public language behavior.
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.
- yesterday First seen · 127 lines · 1,227 tokens per session scan A 9187956ade86
neva AGENTS.md is an instructions file published in the GitHub repository nevalang/neva (1,080 stars, last pushed 10d ago), licensed MIT. It adds 1,227 tokens to every session, about $0.0061 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other instructions, from other repositories
compiler-explorer AGENTS.md
Instructions for compiler-explorer/compiler-explorer, covering agents.md, build & test commands, important workflow requirements, style guidelines and architecture guidelines.
compiler-explorer copilot-instructions.md
Instructions for compiler-explorer/compiler-explorer: For each answer to the user, evaluate your level of confidence in the correctness of the answer on a scale from 1 to 10, where 1 is very uncertain and 10 is absolutely certain. If your confidence level is below 8, state so and suggest ways to verify the answer.
sky CLAUDE.md
Instructions for anzellai/sky, covering claude.md, claude code — operational rules, 0. goal fidelity in autonomous loops — inviolable, 0.1 remote-push discipline — minimize ci noise and 1. memory safety — scripts/mem-guard.sh must run during dev.
sky AGENTS.md
Instructions for anzellai/sky, covering agents.md, what sky is, language essentials, writing a sky app — interview first, then architect and question 0 — what is this for? (the tier drives everything).
dingo CLAUDE.md
Claude Code instructions for MadAppGang/dingo, covering claude ai agent instructions - dingo project, 🚨🚨🚨 stop: read this before any implementation 🚨🚨🚨, the architectural principle (understand this first), why this rule exists and ✅ required approaches (the only correct ways).
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.