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 rules/conlinjoe/ai-platform/00-platformgit clone --depth 1 https://github.com/ConlinJoe/ai-platformWhat 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 | $0.03752 | $0.03752 |
| Opus 5 | $0.01876 | $0.01876 |
| Sonnet 5 | $0.00750 | $0.00750 |
| Haiku 4.5 | $0.00375 | $0.00375 |
Grade A, and why
00-platform 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 yesterday.
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 — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global AI Platform
This repository contains the shared AI platform used by all development projects.
Objective
Produce production-ready solutions that are simple, maintainable, and consistent with the existing project architecture.
Decision Making
- Think through the complete solution before responding.
- Present one final recommendation.
- Do not present drafts, alternatives, or incremental improvements unless explicitly requested.
- Treat architecture, directory structures, workflows, and long-term design decisions as frozen once approved.
Fresh threads and completion reporting
Fresh threads are the default for bounded tasks. Do not reconstruct a large kickoff prompt.
Before the first edit in a session, read docs/working-mode.md if it
exists. It is operational continuation state, not project context,
architecture, or a progress log. Follow its references. Do not ingest
unrelated docs. If the user only asked to resume or orient, confirm
readiness and wait. If they supplied a bounded task, proceed under that
working mode.
Portable orientation prompt: core/prompts/resume.md in the AI Platform
clone.
Update docs/working-mode.md only when the working mode itself changes,
not after routine bounded tasks. Durable facts belong in the
authoritative contract, ADR, or status document.
Default to a short completion: DONE or BLOCKED, what materially changed, verification performed, and any actual concern or required human action. Do not require headings. Do not routinely emit file lists, walkthroughs, unchanged-behavior tables, architecture recaps, exhaustive test counts, or long READY reports. Use a longer report when the user asks, the task is an audit or review, architecture changed, operations require it, something failed or is blocked, the next decision needs the detail, or another contract requires it.
For applicable frontend or public-facing work, verification includes
scripts/check-guardrails.sh. Lint, tests, and build passing do not
imply that check ran. A failed guardrail check is not a green
completion.
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.
- yesterday First seen · 452 lines · 3,752 tokens per session scan A d85df05b2efd
00-platform is a cursor rule published in the GitHub repository ConlinJoe/ai-platform (2 stars, last pushed 4d ago), licensed MIT. It adds 3,752 tokens to every session, about $0.0188 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.