Borrowing it
Nothing to install: this file belongs to hachej/boring-ui. 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/hachej/boring-ui/main/AGENTS.mdgit clone --depth 1 https://github.com/hachej/boring-uiWrote 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/hachej/boring-ui/agents-md)<a href="https://agentmods.dev/instructions/hachej/boring-ui/agents-md"><img src="https://agentmods.dev/badge/instructions/hachej/boring-ui/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 | $0.01470 | $0.01470 |
| Opus 5 | $0.00735 | $0.00735 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade C, and why
boring-ui 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. **No destructive git/filesystem ops without explicit instruction:** no `rm -rf`, `git reset --hard`, `git clean -fd`, `git push --force`. How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Read this first. Re-read after compaction.
This file is intentionally lean: it contains only hard rules and routing pointers.
Detailed coding practices, workflow, architecture, and package docs live under docs/.
Hard rules
- Human override: if the user tells you to do something, listen. The user is in charge.
- No file deletion without explicit written permission.
- No destructive git/filesystem ops without explicit instruction: no
rm -rf,git reset --hard,git clean -fd,git push --force. - No secrets in git/logs. Never paste tokens into commits, comments, or logs.
- Never push directly to remote
main. Use a branch/worktree unless the owner or Kanzen trunk procedure explicitly authorizes local-main work; keep localmaingreen. - Keep the canonical project checkout on
main. The primaryboring-ui-v2checkout is the coordination anchor and should trackorigin/main, not an agent feature branch. Agents must do coding in isolated branch worktrees (which must always be created inside the.worktrees/directory) and leave the anchor clean/current for handoffs. - Do not overwrite other agents' work. Investigate unexpected changes before editing.
- Tangible progress, anti-ceremony, and honest credit.
- No process porn: a process artifact exists only when it hard-gates a named feature or capability.
- Feature-first ratio: process/ops beads capped at ~5% of open beads; each must name the feature work it gates.
- Honesty is absolute: no fake tests, no weakened assertions, no false closes. A false close is reopened with an incident comment.
- Refusal-only implementations earn partial credit, labeled
(
refusal-only), and never close a feature work item.
- Session history is host app user data: Pi chat transcripts/session lists
are owned by the deployed core app host, not by the sandbox/workspace
runtime. Store them on the host app's durable volume via
BORING_AGENT_SESSION_ROOT(typically/data/pi-sessions), not in container home/root. If host-sideBORING_AGENT_WORKSPACE_ROOT=/data/workspaces, keep the host session root as sibling/data/pi-sessionsunless the user explicitly chooses another mounted volume. - Default communication style: concise, direct, high-signal. Honor user
requests for
stop caveman,normal mode, or any other explicit tone change. - Reconcile architecture proposals with the ratified long-term plan: before proposing cross-package architecture, ontology changes, or new durable primitives, read the ratified long-term vision, architecture plan, and owner rulings linked below. State how the proposal aligns and name every conflict. Never silently supersede a frozen ruling; a conflict requires an explicit owner decision and an update to the ratified plan.
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 · 103 lines · 1,470 tokens per session scan C ae37eb031bde
boring-ui AGENTS.md is an instructions file published in the GitHub repository hachej/boring-ui (46 stars, last pushed today), licensed MIT. It adds 1,470 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
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.
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).
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).
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.
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.