Borrowing it
Nothing to install: this file belongs to tompassarelli/nisp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tompassarelli/nisp/main/AGENTS.mdgit clone --depth 1 https://github.com/tompassarelli/nispWrote 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/instructions/tompassarelli/nisp/agents-md)<a href="https://agentmods.dev/instructions/tompassarelli/nisp/agents-md"><img src="https://agentmods.dev/badge/instructions/tompassarelli/nisp/agents-md/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/instructions/tompassarelli/nisp/agents-md"><img src="https://agentmods.dev/badge/instructions/tompassarelli/nisp/agents-md.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 | $0.02309 | $0.02309 |
| Opus 5.5 | $0.00924 | $0.00924 |
| Sonnet 5.5 | $0.00462 | $0.00462 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
nisp AGENTS.md 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 2mo 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent context for nisp
Targeted at AI coding agents (Claude Code, Cursor, Codex, Aider, etc.) working on the nisp project itself — not on configs that consume nisp. For consumer-facing usage, see README.md.
What this repo is
A Racket #lang for writing Nix as s-expressions, plus the toolchain
that makes it useful: schema-driven validator, importer, LSP server,
programmatic editor.
Repo layout
.
├── main.rkt the DSL — AST nodes, surface forms, emitter
├── lang/reader.rkt #lang-reader hook
├── info.rkt Racket package metadata + version
├── validate.rkt validation library (AST walk, infer, type-check)
├── validate-cache.rkt schema loading + lazy submodule expansion
├── lsp.rkt LSP server (consumes validate)
├── edit.rkt programmatic source-edit library (set/unset)
├── cli/ per-subcommand modules; each provides `main`
│ ├── validate.rkt schema-driven .rkt validation
│ ├── extract-schema.rkt dump options tree → JSON cache
│ ├── import.rkt .nix → .rkt (calls Rust shim)
│ ├── schema.rkt query schema (lookup/children/search)
│ ├── rename.rkt rename option path across .rkt files
│ └── edit.rkt programmatic set/unset/enable-add/remove
├── bin/
│ ├── nisp dispatcher: `nisp <subcommand> [args...]`
│ └── nisp-lsp LSP launcher (separate so editors spawn by name)
├── nix-parser/ Rust crate wrapping rnix-parser
│ ├── src/main.rs parses Nix, emits JSON AST + comments
│ └── Cargo.toml cargo build --release before `nisp import` works
├── tests/ rackunit suite
│ ├── emit-test.rkt covers every AST node + surface form
│ ├── validate-test.rkt covers validation library
│ ├── edit-test.rkt covers edit primitives
│ ├── cli-test.rkt dispatcher + subcommand smoke tests
│ └── lsp-test.rkt subprocess JSON-RPC tests for nisp-lsp
└── examples/ runnable .rkt examples
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.
- 2mo ago First seen · 194 lines · 2,309 tokens per session scan A 2b25b7c749a6
nisp AGENTS.md is an instructions file published in the GitHub repository tompassarelli/nisp (11 stars, last pushed 5mo ago), licensed MIT. It adds 2,309 tokens to every session, about $0.0092 per session on Opus 5.5. 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.
nisp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nisp AGENTS.mdtompassarelli/nisp | Instructions file | 11 | 5mo ago | MIT | A | 2,309 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |