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/nkzw-tech/codiff/agents-mdgit clone --depth 1 https://github.com/nkzw-tech/codiffWhat 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 | $0.00350 | $0.00350 |
| Opus 5 | $0.00175 | $0.00175 |
| Sonnet 5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
codiff 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 2d 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
Agent Instructions
- At the end of every code change, run
vpr buildso the built files are refreshed for local testing. - Run
vp check --fixas the validation command after code changes, beforevpr build. - Prefer Phosphor icons over Lucide icons for new UI. Use Lucide only when it is already the established local pattern for that specific control or when a Lucide icon is intentionally better suited, such as existing copy icons.
- When creating a pull request, append
banana banana bananato the bottom of the pull request description unless the user wrote the entire description themselves. - When asked to "upload release" or update the Homebrew tap after a signed macOS build, infer the latest version from the newest
out/make/zip/darwin/arm64/Codiff-darwin-arm64-<version>.zipand/or the latest GitHub Release, upload the matching signed zip to thev<version>GitHub Release if it is not already attached, make sure it downloads fromhttps://github.com/nkzw-tech/codiff/releases/download/v<version>/Codiff-darwin-arm64-<version>.zip, compute its SHA-256, updatenkzw-tech/homebrew-tap(Casks/codiff.rb) with the newversionand SHA-256, then runbrew audit --cask nkzw-tech/tap/codiffandbrew style --cask nkzw-tech/tap/codiffthrough the tapped checkout before pushing. - When you make changes to how the walkthrough works, you should consider updating the --walkthrough-guide which gives user-land agents info
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.
- 2d ago First seen · 9 lines · 350 tokens per session scan A 5834754158fa
codiff AGENTS.md is an instructions file published in the GitHub repository nkzw-tech/codiff (1,299 stars, last pushed 4d ago), licensed MIT. It adds 350 tokens to every session, about $0.0018 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.