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/nrslib/faceted-prompting/claude-mdgit clone --depth 1 https://github.com/nrslib/faceted-promptingWrote 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/nrslib/faceted-prompting/claude-md)<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>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 | $0.00660 | $0.00660 |
| Opus 5 | $0.00330 | $0.00330 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
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.
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 aFacetSet+ComposeOptions→ComposedPrompt(systemPrompt + userMessage). Default user-message order is knowledge → instructions → output-contracts → policies. Policy and knowledge are truncated viatruncation.tswhen exceedingcontextMaxChars.data-engine.ts—DataEngineinterface for facet retrieval.FileDataEngineresolves{root}/{kind}/{key}.md.CompositeDataEnginechains 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.mdextension 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.
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.
- 5d ago First seen · 47 lines · 660 tokens per session scan A ffe0455e745b
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.
Other instructions, from other repositories
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.
Awesome-Prompt-Engineering AGENTS.md
Instructions for natnew/Awesome-Prompt-Engineering, covering agents.md, repository north star, agent role, trust boundary and read order.
pydantic-ai-gepa AGENTS.md
AGENTS.md instructions for indexedlabs/pydantic-ai-gepa, covering repository guidelines, mighty workflow, project structure & module organization, build, test, and development commands and coding style & naming conventions.
SkillOpt AGENTS.md
Instructions for mitkox/SkillOpt, covering agent instructions for skillopt, project identity, default example workflow, documentation expectations and repo hygiene.
vscode-copilot-chat model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.
comfy-prompt-studio AGENTS.md
Instructions for yxhpy/comfy-prompt-studio, covering agents.md - ai 代理配置文档, ai 提供商, 1. ollama (默认), 2. gemini and 提示词生成服务.