faceted-prompting CLAUDE.md

faceted-prompting CLAUDE.md is an instructions file for coding agents from nrslib/faceted-prompting. It costs 660 tokens per session, scanned A, original, MIT.

Repository instructions for a TypeScript library that builds prompts from separate parts such as identity, rules, background knowledge, tasks, and answer formats.

In plain words
What is it for?
Use them when changing prompt composition, facet types, exported APIs, tests, linting, or the package build.
Why use it?
They explain how the prompt parts are organized and where the public library interface lives.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/nrslib/faceted-prompting/claude-md
Clone the repo
git clone --depth 1 https://github.com/nrslib/faceted-prompting

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 faceted-prompting CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nrslib/faceted-prompting/claude-md.svg)](https://agentmods.dev/instructions/nrslib/faceted-prompting/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nrslib/faceted-prompting/claude-md"><img src="https://agentmods.dev/badge/instructions/nrslib/faceted-prompting/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 660 This file is loaded in full into every session.
When invoked 660 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00660 $0.00660
Opus 5 $0.00330 $0.00330
Sonnet 5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 5d ago against content hash ffe0455e745b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

faceted-prompting CLAUDE.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 5d 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.

CLAUDE.md · 47 lines

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.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

npm run build          # TypeScript compile (tsc) → dist/
npm run test           # Run all tests (vitest)
npm run test -- src/__tests__/compose.test.ts  # Run a single test file
npm run test:watch     # Watch mode
npm run lint           # ESLint on src/

Architecture

This is a TypeScript ESM library ("type": "module") that implements the Faceted Prompting pattern — structured prompt composition for LLMs. It is designed to be consumed as an npm package (faceted-prompting). All public API is re-exported from src/index.ts.

Core Concept: Facets

Prompts are decomposed into five facet kinds (FacetKind), each with a defined role and placement:

Facet Placement Purpose
Persona System prompt WHO — agent identity
Policy User message HOW — rules/standards
Knowledge User message WHAT TO KNOW — domain context
Instruction User message WHAT TO DO — the task
Output contracts User message HOW TO ANSWER — output/report format

Key Modules

  • compose.ts — Core composition: takes a FacetSet + ComposeOptionsComposedPrompt (systemPrompt + userMessage). Default user-message order is knowledge → instructions → output-contracts → policies. Policy and knowledge are truncated via truncation.ts when exceeding contextMaxChars.
  • data-engine.tsDataEngine interface for facet retrieval. FileDataEngine resolves {root}/{kind}/{key}.md. CompositeDataEngine chains engines with first-match-wins.
  • resolve.ts — Facet reference resolution: resolves names/paths/inline content from candidate directories and section maps. Supports ~, ./, ../, / path prefixes and .md extension detection.
  • scope.ts@{owner}/{repo}/{facet-name} scope reference parsing/validation for repertoire packages.
  • template.ts — Minimal template engine: {{variable}} substitution and {{#if var}}...{{else}}...{{/if}} conditionals (no nesting).
  • truncation.ts — Trims content to char limit, appends truncation markers and source-path metadata.
  • escape.ts — Escapes {} to full-width Unicode equivalents to prevent template injection.

Read the full file on GitHub · 47 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. 5d ago First seen · 47 lines · 660 tokens per session scan A ffe0455e745b

Subscribe to this mod's changes

faceted-prompting CLAUDE.md is an instructions file published in the GitHub repository nrslib/faceted-prompting (23 stars, last pushed 2mo ago), licensed MIT. It adds 660 tokens to every session, about $0.0033 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.