Borrowing it
Nothing to install: this file belongs to JimmyPaolini/codebase. 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/JimmyPaolini/codebase/main/AGENTS.mdgit clone --depth 1 https://github.com/JimmyPaolini/codebaseWrote 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/jimmypaolini/codebase/agents-md)<a href="https://agentmods.dev/instructions/jimmypaolini/codebase/agents-md"><img src="https://agentmods.dev/badge/instructions/jimmypaolini/codebase/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 5.1 | $0.20680 | $0.20680 |
| Opus 5 | $0.10340 | $0.10340 |
| Sonnet 5 | $0.04136 | $0.04136 |
| Haiku 4.5 | $0.02068 | $0.02068 |
Grade C, and why
codebase AGENTS.md scanned grade C with 1 finding 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 today.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- The rule below has to spell out the abbreviations it bans. cspell:ignore req, res --> How it starts
The opening of the file, as written. The whole thing — 1,179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Guidance
Essential Commands
# Run tasks via Nx (always prefer this)
nx run <project>:<target>:<configuration>
nx run-many --target=lint-codebase --all
nx affected --target=vitest --base=main
# Install dependencies
pnpm add --filter <project> <package>
pnpm add -w <package> # Workspace root
# Tools that run directly (not via Nx)
docker build --platform linux/amd64 -t myapp .
kubectl get pods
helm upgrade --install myrelease ./chart
Agent Workflow
Use the mattpocock/skills workflow for non-trivial features, refactors, and bugfixes so the work is clarified, specified, tracked, and implemented in a consistent way.
- Sharpen the request first. Run grill-with-docs when the work needs a domain model or ADRs to come out of the conversation, or grill-me for a plain interview. Unsure which skill fits? Ask ask-matt.
- Capture the outcome with to-spec, then split it with to-tickets when the work spans multiple tasks. Reach for wayfinder when the work is larger than one agent session can hold.
- Build with implement, which drives tdd red-green-refactor. For a multi-task ticket set, orchestrate with subagent-driven-development — one fresh subagent per task — and use dispatching-parallel-agents when tasks are genuinely independent. Debug regressions with diagnosing-bugs.
- Review with code-review, and apply incoming feedback through receiving-code-review rather than agreeing on sight.
- Finish with validate-code, gated by verification-before-completion: never claim done without the command output that proves 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.
- today Changed · +87 lines · +2,506 tokens per session 26477d44f616
- 2d ago Changed · +37 tokens per session d8bd67018512
- 3d ago First seen · 1,092 lines · 18,137 tokens per session scan C bec6636bc0d1
codebase AGENTS.md is an instructions file published in the GitHub repository JimmyPaolini/codebase (0 stars, last pushed today), licensed MIT. It adds 20,680 tokens to every session, about $0.1034 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
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).
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.
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).
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.