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/mongodb-js/kerberos/agents-mdgit clone --depth 1 https://github.com/mongodb-js/kerberosWrote 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/mongodb-js/kerberos/agents-md)<a href="https://agentmods.dev/instructions/mongodb-js/kerberos/agents-md"><img src="https://agentmods.dev/badge/instructions/mongodb-js/kerberos/agents-md.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 | $0.00854 | $0.00854 |
| Opus 5 | $0.00427 | $0.00427 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
kerberos 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 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in this repository. This file is the source of truth. Tool-specific files (e.g. CLAUDE.md) should only import it.
Project Overview
kerberos is a Node.js native addon providing Kerberos/GSSAPI authentication, used primarily by the MongoDB Node.js driver for GSSAPI auth. The C++ addon (node-addon-api / N-API 9) wraps GSSAPI on Unix and SSPI on Windows. On install, prebuild-install looks for a prebuilt addon binary, falling back to a source build via node-gyp rebuild (requires system Kerberos dev headers, e.g. libkrb5-dev, on Unix).
Commands
All scripts from package.json:
npm install— installs deps and compiles the addon.npx node-gyp rebuild— recompile the addon only.npm test— run mocha tests. Requires a compiled addon and a reachable KDC (configured viaKERBEROS_USERNAME/KERBEROS_PASSWORD/KERBEROS_REALM/KERBEROS_HOSTNAMEenv vars).npm run check:lint— lint JS/TS.npm run format-js— eslint --fix.npm run format-cxx— clang-format the C++ sources insrc/.npm run docs— regenerate README.md from JSDoc inlib/index.js(never edit README.md directly, editetc/README.hbsor the JSDoc).npm run precommit—check-clang-format. Verifies C++ formatting, and is invoked by the pre-commit hook.npm run prepare— pointscore.hooksPathat.githooks/so the tracked pre-commit hook is active. Runs automatically onnpm installin a clone. It does not run for downstream consumers installing the published package.npm run prebuild— build prebuilt addon binaries (prebuild --runtime napi --strip --verbose --all). Used by CI and release, rarely run locally.
Structure
src/— C++ addon.kerberos.ccdefines the N-API bindings.src/unix/— GSSAPI implementation.src/win32/— SSPI implementation.lib/index.js— entrypoint: loads the compiled.nodebinary and exports promisified wrappers plus GSS flag/OID constants.index.d.ts— the public types.binding.gyp— node-gyp config. Selects unix vs win32 sources per platform.test/— mocha tests, plustest/bundling/webpackfor bundler compatibility.
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 · 47 lines · 854 tokens per session scan A b30dad3260f6
kerberos AGENTS.md is an instructions file published in the GitHub repository mongodb-js/kerberos (177 stars, last pushed 6d ago), licensed Apache-2.0. It adds 854 tokens to every session, about $0.0043 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 2026-08-30.
Other instructions, from other repositories
js-bson AGENTS.md
Instructions for mongodb/js-bson, covering agents.md, project overview, commands, benchmarks and structure.
sportsdataverse-js CLAUDE.md
Instructions for sportsdataverse/sportsdataverse-js, covering claude.md — sportsdataverse (node.js) development guide, package overview, commit convention, branches and build & development commands.
node-express-boilerplate AGENTS.md
Instructions for KhaledSaeed18/node-express-boilerplate, covering agents.md, read first, skills, working style and stack.
zstd AGENTS.md
Instructions for mongodb-js/zstd, covering agents.md, project overview, commands, structure and code conventions.
sportsdataverse-js copilot-instructions.md
Instructions for sportsdataverse/sportsdataverse-js, covering github copilot instructions — sportsdataverse (node.js), architecture (how the code is generated), conventions and commits / prs.
node-express-boilerplate typescript-assertions.instructions.md
Use when editing TypeScript in src to avoid assertion-related lint/type regressions after merges. Prefer narrowing, type guards, satisfies, and as const/typeof over unsafe casts.