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/releasegit 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/release)<a href="https://agentmods.dev/rules/rajitsaha/100xprism/release"><img src="https://agentmods.dev/badge/rules/rajitsaha/100xprism/release.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 | $0.02213 |
| Opus 5 | $0.00003 | $0.01107 |
| Sonnet 5 | $0.00001 | $0.00443 |
| Haiku 4.5 | $0.00001 | $0.00221 |
Grade C, and why
release scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/release-test-venv How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release — Local Gate → Install Test → Version Bump → Tag → Publish → Verify
You are a release engineer. Execute each phase in order. Each must fully complete before advancing. Do NOT ask for permission. Do NOT skip phases.
Usage
/release patch # 1.2.3 → 1.2.4
/release minor # 1.2.3 → 1.3.0
/release major # 1.2.3 → 2.0.0
/release 1.4.0 # explicit version
If no argument is given, ask: patch, minor, or major?
Phase 0 — Detect registries
PROJECT_ROOT=$(git rev-parse --show-toplevel)
cd "$PROJECT_ROOT"
{ [ -f pyproject.toml ] || [ -f setup.py ]; } && PYPI=true || PYPI=false
[ -f package.json ] && node -e "const d=require('./package.json'); process.exit(d.private ? 1 : 0)" 2>/dev/null && NPM=true || NPM=false
[ -f Dockerfile ] && DOCKER=true || DOCKER=false
Print detected registries before continuing:
Detected registries:
PyPI: true | false
npm: true | false
Docker: true | false
Phase 1 — Quality Gate (MANDATORY)
Run the gate workflow. Do NOT continue until it reports ✅ ALL GATES PASSED.
Phase 2 — Confirm current version
Print current → new version before proceeding. Do not proceed without confirming the version transition is correct.
python3 -c "import tomllib; print(tomllib.load(open('pyproject.toml','rb'))['project']['version'])" 2>/dev/null || true
node -e "console.log(require('./package.json').version)" 2>/dev/null || true
Print:
Current version: X.Y.Z
New version: A.B.C
Phase 3 — Build packages locally
PyPI (if PYPI=true)
pip install build twine --quiet
python -m build
twine check dist/*
GATE: twine check must report PASSED for all distributions. If it fails → STOP.
npm (if NPM=true)
npm pack --dry-run
GATE: must complete with no errors. If it fails → STOP.
Docker (if DOCKER=true)
docker build -t "$(basename "$PROJECT_ROOT"):release-candidate" .
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 · 288 lines · 5 tokens per session scan C 08249b40a1de
release 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 2,213 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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
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.
family-instance-domain-actions
Family instance domain action implementation patterns.