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/rajitsaha/100xprism/launchgit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/rules/rajitsaha/100xprism/launch)<a href="https://agentmods.dev/rules/rajitsaha/100xprism/launch"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/launch.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 | $0.00005 | $0.02948 |
| Opus 5 | $0.00003 | $0.01474 |
| Sonnet 5 | $0.00001 | $0.00590 |
| Haiku 4.5 | $0.00001 | $0.00295 |
Grade A, and why
launch scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8000/health 2>/dev/null || \ How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch — Pre-flight Pipeline: Docker → Test → Lint → Security → Build → Commit → Push → Cleanup
Release engineer mode: execute each phase in order; each must fully complete before advancing. Do NOT ask for permission. Stop only if something is truly unfixable.
Phase 0 — Docker Build & Smoke Test (if applicable)
PROJECT_ROOT=$(git rev-parse --show-toplevel)
ls "$PROJECT_ROOT/Dockerfile" 2>/dev/null && echo "HAS_DOCKERFILE" || echo "NO_DOCKERFILE"
Skip this phase if no Dockerfile exists. Otherwise:
0a. Build images
Detect multiple services from docker-compose.yml. Build all:
cd "$PROJECT_ROOT"
docker build -t $(basename $PROJECT_ROOT)-api:local . 2>&1
# If dashboard/frontend Dockerfile exists:
docker build -t $(basename $PROJECT_ROOT)-dashboard:local ./dashboard 2>&1 || true
Fix build errors; iterate until all images build.
0b. Start stack
# Use docker-compose.yml or compose.yml if present
COMPOSE_FILE=$(ls docker-compose.yml compose.yml deploy/docker-compose.yml 2>/dev/null | head -1)
[ -n "$COMPOSE_FILE" ] && docker compose -f "$COMPOSE_FILE" up -d || docker compose up -d
docker compose ps
Expected: all services running/healthy.
0c. Run migrations (if applicable)
docker compose run --rm migrate 2>/dev/null || true
0d. Smoke test
Read the project instruction file or README.md for the health endpoint; fall back to common defaults:
curl -s http://localhost:8000/health 2>/dev/null || \
curl -s http://localhost:3000/health 2>/dev/null || \
curl -s http://localhost:8080/health 2>/dev/null || echo "No health endpoint found"
0e. Cleanup
docker compose down 2>/dev/null || true
GATE: All images build, containers healthy, smoke test passes.
Phase 1 — Tests
Run the test workflow, which will:
- Auto-start required Docker services (DB, Redis, etc.) for integration tests
- Run unit tests against real services — no DB mocks
- Run integration tests against a real Docker DB
- Run E2E tests against the full docker compose stack
- Loop until all thresholds are met with zero failures
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 · 329 lines · 5 tokens per session scan A 7c78e28b224e
launch is a cursor rule published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 4d ago), licensed MIT. It adds 5 tokens to every session and 2,948 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
ops-safety
运维安全规则:系统命令风险说明、回滚方案、Docker/数据库操作安全.
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.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.