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/packmindhub/packmind/packmind-frontend-data-flowgit clone --depth 1 https://github.com/PackmindHub/packmindWhat 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 | $0.00416 | $0.00416 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
packmind packmind-frontend-data-flow.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
Standard: Frontend Data Flow
This standard defines the recommended data flow pattern for frontend routes in the Packmind codebase using React Router v7 in framework mode with TanStack Query for data management. It ensures consist... :
- Access data via query or mutation hooks in frontend route modules rather than calling gateways directly to maintain separation between data access and presentation layers
- Consume data in route module components using the useLoaderData() hook to access data returned by the clientLoader
- Define a crumb property in the handle export of route modules to enable automatic navigation breadcrumb generation
- Enable query options conditionally using the enabled property to prevent execution when required parameters are missing or invalid
- Export query hooks (e.g., useGetStandardByIdQuery) alongside query options to provide consistent component-level data access patterns
- Export query options as standalone functions (e.g., getStandardByIdOptions) separate from hooks to enable reuse in both hooks and route loaders
- Name route module default export functions with a suffix of RouteModule (e.g., StandardDetailRouteModule) to clearly identify route-level components
- Prefer
queryClient.ensureQueryData()overqueryClient.fetchQuery()in clientLoaders to return cached data when available instead of always fetching - Store domain queries in the domain folder organized by entity at apps/frontend/src/domain/{entity}/api/queries/ to maintain clear separation of concerns and domain boundaries
- Use clientLoader function (not loader) in route modules for data fetching when using React Router in SPA mode to ensure proper client-side data loading
- Use Gateway type helper for authenticated operations or PublicGateway for public operations in frontend gateway interfaces to ensure proper command/response typing
- Use queryClient.ensureQueryData() or queryClient.fetchQuery() in clientLoader to preload data before rendering and leverage TanStack Query's caching mechanisms
Full standard is available here for further request: Frontend Data Flow
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 · 20 lines · 416 tokens per session scan A 36c0fa3e41ed
packmind packmind-frontend-data-flow.instructions.md is an instructions file published in the GitHub repository PackmindHub/packmind (306 stars, last pushed 4d ago), licensed Apache-2.0. It adds 416 tokens to every session, about $0.0021 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
token-saver CLAUDE.md
Instructions for ppgranger/token-saver, covering token-saver plugin, how it works and important rules.
arai CLAUDE.md
Instructions for taniwhaai/arai, covering claude.md — arai, commands, architecture, prompt-collector module (src/promptcollector.rs) and extending the match pipeline.
ai-agent-instruction-modules AGENTS.md
Instructions for tablackburn/ai-agent-instruction-modules, covering ai agent instructions, instructions for ai agents, instruction applicability matrix, available instruction files and quick reference.
arai AGENTS.md
Instructions for taniwhaai/arai, covering agents.md — arai, core discipline (non-negotiable), taniwha / subagent rules, work style and tool usage.
stenographer-mode copilot-instructions.md
Instructions for AkashAi7/stenographer-mode, covering steno mode — global instructions, contract, rules and levels.
booklib AGENTS.md
Instructions for booklib-ai/booklib, covering booklib, stack, key directories, commands and rules.