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/kajitiluna/erd-designer/testinggit clone --depth 1 https://github.com/kajitiluna/erd-designerWhat 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 | $0.00184 | $0.00184 |
| Opus 5 | $0.00092 | $0.00092 |
| Sonnet 5 | $0.00037 | $0.00037 |
| Haiku 4.5 | $0.00018 | $0.00018 |
Grade A, and why
erd-designer testing.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.
What it actually says
Testing Requirements
Test files live in __tests__/ directories adjacent to the source file (e.g. src/models/__tests__/).
When modifying a source file:
- Add or update tests in the corresponding
__tests__/directory to cover the change. - If creating a new source file, create a matching test file in the adjacent
__tests__/directory. - Run
npm run testrunand confirm all tests pass before considering the task complete.
Code Conventions
- TypeScript strict mode; React components use
.tsx, plain logic uses.ts - CSS Modules (
.module.css) for component styles - No ESLint errors (
eslint.config.js)
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 · 22 lines · 184 tokens per session scan A 51aca6148fd6
erd-designer testing.instructions.md is an instructions file published in the GitHub repository kajitiluna/erd-designer (18 stars, last pushed 9d ago), licensed Apache-2.0. It adds 184 tokens to every session, about $0.0009 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
liam CLAUDE.md
Instructions for liam-hq/liam, covering claude.md, essential commands, app-specific commands, run only the main web app (port 3001) and format code.
liam AGENTS.md
Instructions for liam-hq/liam, covering repository guidelines, project structure & modules, build, test, and development, coding style & naming and testing guidelines.
laravel-truss CLAUDE.md
Instructions for albertoarena/laravel-truss, covering claude.md — instructions for claude code, project overview, stack, commands and conventions (always true).
Messenger AGENTS.md
AGENTS.md instructions for yoosuf/Messenger, covering agents guide, purpose, repository focus, agent objectives and required update rules.
Messenger CLAUDE.md
Claude Code instructions for yoosuf/Messenger, covering claude instructions for messenger, role, core files, working rules and mandatory sync policy.
Messenger copilot-instructions.md
Copilot instructions for yoosuf/Messenger, covering copilot instructions, primary sources, change policy, quality expectations and preferred output in prs.