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/iress/design-system/bugfixinggit clone --depth 1 https://github.com/iress/design-systemWhat 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 | $0.04638 | $0.04638 |
| Opus 5 | $0.02319 | $0.02319 |
| Sonnet 5 | $0.00928 | $0.00928 |
| Haiku 4.5 | $0.00464 | $0.00464 |
Grade A, and why
design-system bugfixing.instructions.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.
How it starts
The opening of the file, as written. The whole thing — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fixing Best Practices
1. Initial Analysis (Don't Jump to Solutions)
Parse the Support Request
- Extract key symptoms: What exactly is broken? What's the expected vs actual behavior?
- Identify affected components: Which UI elements, APIs, or features are involved?
- Classify the issue: Bug, feature request, configuration issue, or user error?
- Note reproduction context: Browser, environment, specific data, user actions
Understand the Technical Flow
- Trace the data path: From input → processing → output where does it break?
- Identify the domain: Styling, event handling, data transformation, rendering, etc.
- Consider scope: Is this a single component issue or systemic problem?
Communicate Initial Analysis
Always summarize your initial understanding and ask for confirmation:
- "Based on the bug report, I understand that [X problem] is happening when [Y scenario]. Is this correct?"
- "I think this affects [components/areas]. Should I investigate these areas first?"
- "This seems like a [bug type] issue. Does this match your expectations?"
Wait for confirmation before proceeding to investigation.
Create Story for Visual Inspection
After confirming the analysis, create a Storybook story to reproduce the bug:
- Create the story in the main/root component's stories file (e.g.,
RichSelect.stories.tsx, notSelectMenu.stories.tsx) - This makes the bug reproduction more accessible and realistic for users
- Include problem summary in the story description
- Document expected vs actual behavior
- Provide clear test steps
- Make the bug visually apparent in the story
- Use the actual component API that users would interact with
- Create mock data that triggers the bug if needed
Template for bug reproduction story:
export const BugReproduction: Story = {
name: 'Bug: [Brief Description]',
args: {
// Props that trigger the bug
},
parameters: {
docs: {
description: {
story: `
**Problem Summary:** [What goes wrong]
**Expected Behavior:** [What should happen]
**Actual Behavior:** [What actually happens]
**How to Test:**
1. [Step by step instructions]
2. [To reproduce the issue]
`,
},
},
},
};
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 · 588 lines · 4,638 tokens per session scan A d15750f53fca
design-system bugfixing.instructions.md is an instructions file published in the GitHub repository iress/design-system (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 4,638 tokens to every session, about $0.0232 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 2026-08-31.
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).
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.
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.