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/pspdfkit-labs/nutrient-dws-client-typescript/agents-mdgit clone --depth 1 https://github.com/PSPDFKit-labs/nutrient-dws-client-typescriptWrote 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/pspdfkit-labs/nutrient-dws-client-typescript/agents-md)<a href="https://agentmods.dev/instructions/pspdfkit-labs/nutrient-dws-client-typescript/agents-md"><img src="https://agentmods.dev/badge/instructions/pspdfkit-labs/nutrient-dws-client-typescript/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 | $0.00431 | $0.00431 |
| Opus 5 | $0.00216 | $0.00216 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
nutrient-dws-client-typescript 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.
What it actually says
AGENTS.md
Agent instructions for this repository. Rules here; detail on demand via the table below.
Rules
1. Never hand-edit src/generated/.
Regenerate instead: npm run generate:types / npm run generate:types:extract.
Enforced by: the generated-types-drift job in CI.
Detail: docs/generated-types.md
2. Never drop the flags from the generate:types* scripts.
--empty-objects-unknown and --default-non-nullable=false look removable and are not.
Enforced by: the same CI job, then npm run typecheck.
Detail: docs/generated-types.md
3. Hand-written types go in src/types/http.ts, and only when the spec cannot express the shape.
"The generated type is awkward" is not the bar. Prefer an alias derived from components/operations.
Enforced by: review.
Detail: docs/generated-types.md
4. This repository is public. No internal ticket ids, tracker paths, repo names, or tool names — in code, comments, docs, or commit messages. Enforced by: review.
Definition of done
npm run typecheck && npm run lint && npm run test:unit
Where to look
| If you are… | Read |
|---|---|
changing an API type, or touching src/generated/ |
docs/generated-types.md |
| adding or changing a client method | docs/METHODS.md |
| working on the workflow builder | docs/WORKFLOW.md |
| making a breaking change | docs/MIGRATION.md |
| setting up, or opening a PR | docs/CONTRIBUTING.md |
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 · 41 lines · 431 tokens per session scan A 22970f0b5f2e
nutrient-dws-client-typescript AGENTS.md is an instructions file published in the GitHub repository PSPDFKit-labs/nutrient-dws-client-typescript (37 stars, last pushed 11d ago), licensed MIT. It adds 431 tokens to every session, about $0.0022 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
docs-to-pdf CLAUDE.md
Claude Code instructions for jean-humann/docs-to-pdf, covering claude development guide for docs-to-pdf, project overview, development environment setup, using mise (recommended) and install mise (if not already installed).
vscode learnings.instructions.md
This document describes how to deal with learnings that you make. (meta instruction).
experiencer AGENTS.md
AGENTS.md instructions for vincentlaucsb/experiencer, covering agents.md, product scope, architecture, resume components and canonical resume document rendering.
pdfnative-mcp AGENTS.md
Instructions for Nizoka/pdfnative-mcp, covering agents.md — pdfnative-mcp, 1. tool catalogue (28 tools), 2. decision tree, 3. token-frugal responses and 4. output modes & environment.
resume-ci AGENTS.md
Instructions for gustavo-ferreira03/resume-ci, covering agents.md, project context, yaml rules, star method and evidence standards.
mcp-arabic-ms-word CLAUDE.md
Claude Code instructions for MarwanDevSpace/mcp-arabic-ms-word, covering guidelines for claude desktop & ide, build & test commands, check typescript types, run test suite and build production distribution.