jsn: Instructions file for Codex

AGENTS.md

jsn AGENTS.md is an instructions file for Codex, OpenCode from jacebenson/jsn. It costs 1,931 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents working on jsn. They explain the technology stack, project layout, domain terms, design decisions, and how to add a command.

In plain words
What is it for?
Use them when exploring jsn, changing its code, or adding a command.
Why use it?
They help an agent make changes that fit the project’s structure and existing terminology.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is jacebenson/jsn's own configuration. It tells Codex and OpenCode how to work on jsn itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything jsn configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jacebenson/jsn. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jacebenson/jsn/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jacebenson/jsn

Made for: Codex, OpenCode.

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 jsn AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jacebenson/jsn/agents-md/github.svg)](https://agentmods.dev/instructions/jacebenson/jsn/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jacebenson/jsn/agents-md"><img src="https://agentmods.dev/badge/instructions/jacebenson/jsn/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.

agentmods 80×15 button for jsn AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jacebenson/jsn/agents-md"><img src="https://agentmods.dev/badge/instructions/jacebenson/jsn/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,931 This file is loaded in full into every session.
When invoked 1,931 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01931 $0.01931
Opus 5.5 $0.00772 $0.00772
Sonnet 5.5 $0.00386 $0.00386
Haiku 4.5 $0.00193 $0.00193

Measured 7d ago against content hash 94ff763877a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jsn 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 7d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `test/` — `*.test.js`, `node:test` + `spawnSync` for CLI-level tests
AGENTS.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — working on the jsn codebase

For AI agents (and humans) building jsn itself. If you want to use jsn against a ServiceNow instance, see the bundled skill (jsn skill show, source in skills/) or README.md.

Stack

Current Node.js LTS (CI follows lts/*; no fixed minimum-version promise), ESM ("type": "module"), no build step, no TypeScript. The npm package lives in cli/. Paths in the CLI layout below are relative to cli/. Entry: cli/bin/jsn.js → cli/src/cli.js.

Runtime deps — keep this list short, every addition needs a reason:

Package Why it's here
src/cli-adapter.js Local yargs-compatible command API backed by Node's node:util argument parser
@inquirer/prompts + @inquirer/core Interactive pickers (TTY list views, setup wizard)
better-sqlite3 jsn docs search index — native module, needs build tools on git installs (node:sqlite lacks FTS5 on some platforms)
js-yaml YAML frontmatter parsing and serialization for docs markdown
saxes Strict, entity-safe XML inspection before native update-set upload
turndown HTML → markdown for docs ingestion

The docs site is a separate npm project in docs/; its Eleventy dependency belongs in docs/package.json, not this project.

Tests: node:test runner + eslint.

Layout

  • bin/jsn.js — entry, handles closed pipes, calls cli.parse()
  • src/cli.js — buildCLI(): global options, middleware, command registration
  • src/app.js — App: instance resolution, SDK handle, output controller
  • src/config.js — profile config (XDG config dir)
  • src/commands/ — one file per command family; _simple.js builds the many simple table CRUD commands, commands/_ticket.js builds ticket-style CRUD (incidents/changes/requests/tasks)
  • src/helpers.js, src/output.js, src/errors.js, src/mutations.js
  • skills/ — the agent skill shipped in the npm package
  • test/ — *.test.js, node:test + spawnSync for CLI-level tests

Read the full file on GitHub · 152 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. 7d ago Changed · +17 lines · +202 tokens per session 94ff763877a1
  2. 8d ago Changed · +3 lines · +77 tokens per session 9f4514938e68
  3. 10d ago Changed · +34 lines · +412 tokens per session 811a54994345
  4. 1mo ago Changed · -1 lines · -24 tokens per session 44875030ebd7
  5. 1mo ago Changed · +1 tokens per session b3ea9a17fbc5
  6. 1mo ago Changed · +3 lines · +41 tokens per session 642684c944c8
  7. 2mo ago Changed · -9 tokens per session c80e349d0f1e
  8. 2mo ago First seen · 96 lines · 1,231 tokens per session scan A 139db291251f

Subscribe to this mod's changes

jsn AGENTS.md is an instructions file published in the GitHub repository jacebenson/jsn (16 stars, last pushed today), licensed MIT. It adds 1,931 tokens to every session, about $0.0077 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

jsn AGENTS.md compared with instructions from other repositories

jsn AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
jsn AGENTS.mdjacebenson/jsnInstructions file16todayMITA1,931Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot