Borrowing it
Nothing to install: this file belongs to businesslens/pdd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/businesslens/pdd/main/AGENTS.mdgit clone --depth 1 https://github.com/businesslens/pddWrote 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/businesslens/pdd/agents-md)<a href="https://agentmods.dev/instructions/businesslens/pdd/agents-md"><img src="https://agentmods.dev/badge/instructions/businesslens/pdd/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.
<a href="https://agentmods.dev/instructions/businesslens/pdd/agents-md"><img src="https://agentmods.dev/badge/instructions/businesslens/pdd/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.05049 | $0.05049 |
| Opus 5.5 | $0.02020 | $0.02020 |
| Sonnet 5.5 | $0.01010 | $0.01010 |
| Haiku 4.5 | $0.00505 | $0.00505 |
Grade A, and why
pdd 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 18d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance
Purpose
This repository is the BusinessLens OSS core: the businesslens npm package
plus the agent skills that build and maintain the .businesslens/ product
map.
Two engineering contracts, each changed before the behavior it governs:
spec/format.md— the authored.businesslens/folder. Change it before changing the parser or the linter.spec/report.md— the Product Report wire contract, its portable projection, and expansion. Change it before changingexport,open,pull,contribute, or anything the catalog server agrees with.
Neither is a docs-site page. The user-facing explanation of the same resource
types lives in the Product Model group under docs/, and the two registers must
not contradict each other.
spec/rejected.md sits beside them and binds nothing: it records shapes that
were costed and then chosen against, so the same argument is not had twice.
Layout
src/cli.ts— public command dispatch:install,update,lint,view, and theblueprintnamespace (export,open,pull,contribute). Only documented commands and options are accepted. Removed spellings use normal usage errors; there are no hidden migration commands or scope aliases. Before launch, publication or installation alone does not require historical behavior. Coordinate current producer and consumer changes together.src/commands/— public command implementations.src/core/providers.ts— supported harness paths and detection.src/core/skill-installation.ts— ownership-safe skill installation.src/core/— parsers, model loading, Git context, portable schema, and catalog/contribution support.layers/nuxt/report-viewer/— the stable Nuxt Product Report, its complete report projection, and its dependency-free topology engine.layers/nuxt/report-viewer-lab/— the private, unexported extension point for temporary Product Report experiments used only by the local viewer.layers/nuxt/theme/— the separately extendable BusinessLens-wide visual foundation and approved identity used across Nuxt hosts, not only report pages.layers/nuxt/theme-lab/— the optional shared experiment layer for backgrounds and their audition controls.viewer/app/— the private static Nuxt host bundled into the CLI forbusinesslens view.skills/businesslens-*/SKILL.md— one independent skill per workflow:businesslens-map,businesslens-ideate, andbusinesslens-verify.test/fixtures/fixture-shop/— the golden lint fixture.pnpm view:fixtureopens it in the local report as its own repository, since its code references resolve only from a Git root of its own.
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.
- 18d ago Changed · +13 lines · +224 tokens per session 94df70bfaa4b
- 22d ago Changed · +7 lines · +116 tokens per session 97f39c0616d9
- 23d ago Changed · +15 lines · +237 tokens per session b987537ff1b9
- 24d ago Changed · +17 lines · +289 tokens per session 9936bf7a2606
- 25d ago Changed · +11 lines · +259 tokens per session 4a7411a343e0
- 1mo ago Changed · +5 lines · +72 tokens per session b4751fba6707
- 1mo ago Changed · +2 tokens per session b8ad5a30a052
- 1mo ago Changed · +11 lines · +148 tokens per session aa8d535380c0
- 1mo ago Changed · +11 lines · +179 tokens per session b9317ff72805
- 1mo ago First seen · 258 lines · 3,523 tokens per session scan A 464d178afcbf
pdd AGENTS.md is an instructions file published in the GitHub repository businesslens/pdd (13 stars, last pushed 18d ago), licensed MIT. It adds 5,049 tokens to every session, about $0.0202 per session on Opus 5.5. 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.