PR Lens is a tool that turns a pull request into animated diagrams showing the software components it affects and the data flowing between them. Developers use it through GitHub, a command-line interface, or a coding agent to understand changes before reviewing code. The catalogue entries provide instructions and skills for using PR Lens with coding agents.
Borrowing it
Nothing to install: this file belongs to coldteadotai/pr-lens. 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/coldteadotai/pr-lens/main/AGENTS.mdgit clone --depth 1 https://github.com/coldteadotai/pr-lensWrote 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/coldteadotai/pr-lens/agents-md)<a href="https://agentmods.dev/instructions/coldteadotai/pr-lens/agents-md"><img src="https://agentmods.dev/badge/instructions/coldteadotai/pr-lens/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/coldteadotai/pr-lens/agents-md"><img src="https://agentmods.dev/badge/instructions/coldteadotai/pr-lens/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 | $0.01494 | $0.01494 |
| Opus 5.5 | $0.00598 | $0.00598 |
| Sonnet 5.5 | $0.00299 | $0.00299 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
pr-lens 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 1mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Lens — Agent Instructions
Hard rules for anyone (human or agent) working in this repo. Read fully before writing code.
Hard requirements
- No secrets in this repo, ever. This repo needs no credentials. Do not read
~/Documents/dev/pr-lens-secrets/. - Verify before claiming done: tests green,
pnpm build+ typecheck clean, and visual output verified in a real browser when the change affects rendered SVGs. - No AI attribution in commits or pull requests. No
Co-Authored-Byline for a model, no "Generated with" footer, no session link, no bot listed as an author. Whoever opened the pull request is the author of every commit in it. Coding agents add these by default:.claude/settings.jsonin this repo turns them off for Claude Code, and if you use another tool, find its switch before your first commit. A squash merge carries a co-author trailer over from the branch, so check the merge box too. - Pass user-facing words through the humanizer before shipping them. Anything a person reads — comments, captions, tips, README prose, share pages, cards, terminal output — goes through the humanizer skill first. Copy that reads as machine-written spends trust the diagrams then have to earn back.
General
Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
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.
- 1mo ago Changed · +1 lines · +116 tokens per session 2ffcf3bddf19
- 2mo ago First seen · 116 lines · 1,378 tokens per session scan A aa38c1aa872b
pr-lens AGENTS.md is an instructions file published in the GitHub repository coldteadotai/pr-lens (2,280 stars, last pushed yesterday), licensed MIT. It adds 1,494 tokens to every session, about $0.0060 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 2026-08-30.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.