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/openstatushq/data-table-filters/claude-mdgit clone --depth 1 https://github.com/openstatusHQ/data-table-filtersWrote 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/openstatushq/data-table-filters/claude-md)<a href="https://agentmods.dev/instructions/openstatushq/data-table-filters/claude-md"><img src="https://agentmods.dev/badge/instructions/openstatushq/data-table-filters/claude-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 | $0.01088 | $0.01088 |
| Opus 5 | $0.00544 | $0.00544 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
data-table-filters CLAUDE.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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project overview
data-table-filters — a React data table system with faceted filters, sorting, infinite scroll, and virtualization. Delivered as shadcn registry blocks installable via npx shadcn@latest add.
Monorepo structure (pnpm + turborepo)
apps/web— Next.js app (docs site + demo). Uses App Router.packages/registry— the shadcn registry source (components, utilities, Drizzle helpers)packages/tsconfig— shared TS configs
Key commands
pnpm dev # start all workspaces
pnpm build # turbo build (includes registry:build)
pnpm lint # turbo lint (eslint across workspaces)
pnpm typecheck # tsc --noEmit across workspaces
pnpm test # turbo test (vitest across workspaces)
pnpm format # prettier --write .
pnpm registry:build # build shadcn registry artifacts
Database
- Drizzle ORM with Postgres (Supabase)
- DB-dependent tests run in CI only (Postgres service container in GitHub Actions)
- Tests use
describe.skipIf(!hasDatabase)— they skip gracefully withoutDATABASE_URL - Migrations:
pnpm --filter web db:drizzle:migrate - Seed test data:
pnpm --filter web db:drizzle:seed-test
Coding standards
Before every commit, run local checks
The pre-commit hook (.claude/hooks/pre-commit-checks.sh) runs automatically before git commit. It enforces:
pnpm prettier --check .— format check (fix withpnpm formatif needed)pnpm turbo lint— eslintpnpm turbo typecheck— tsc --noEmitDATABASE_URL= pnpm turbo test— vitest (non-DB tests only)
If any step fails, fix it before committing. Do not use --no-verify or skip hooks.
After pushing, verify CI
DB-dependent tests (Drizzle integration tests) only run in GitHub Actions CI where Postgres is available. After pushing a branch or opening a PR, check CI status with gh run list or gh pr checks. If DB tests fail in CI, fix locally and push again.
Testing policy
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.
- 4d ago First seen · 111 lines · 1,088 tokens per session scan A 98f2c53e7aa2
data-table-filters CLAUDE.md is an instructions file published in the GitHub repository openstatusHQ/data-table-filters (2,213 stars, last pushed today), licensed MIT. It adds 1,088 tokens to every session, about $0.0054 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
coss AGENTS.md
AGENTS.md instructions for cosscom/coss, covering agents.md and main documentation.
rush AGENTS.md
Instructions for onurhan1337/rush, covering project rules for ikas app starter app (next.js), core principles, stack overview, mcp usage and graphql and api workflow.
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.
vibedgames CLAUDE.md
Claude Code instructions for kyh/vibedgames, covering agent instructions, agent-driven development, what this is, product & business context and key architectural decisions.
drizzle-cube CLAUDE.md
Claude Code instructions for cliftonc/drizzle-cube, covering claude.md, project structure, agent documentation context, database support and essential commands.
ns-ui AGENTS.md
AGENTS.md instructions for nikolas-sapa/ns-ui, covering agents.md — working inside this repo, structure, autoplay — how a card demonstrates itself, descriptor schema and driver constraints (don't regress these).