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.
git clone --depth 1 https://github.com/danielvm-git/bigpowersWrote 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/danielvm-git/bigpowers/publish-package)<a href="https://agentmods.dev/rules/danielvm-git/bigpowers/publish-package"><img src="https://agentmods.dev/badge/rules/danielvm-git/bigpowers/publish-package/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/danielvm-git/bigpowers/publish-package"><img src="https://agentmods.dev/badge/rules/danielvm-git/bigpowers/publish-package.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.02602 |
| Opus 5.5 | $0.00014 | $0.01041 |
| Sonnet 5.5 | $0.00007 | $0.00520 |
| Haiku 4.5 | $0.00004 | $0.00260 |
Grade A, and why
publish-package 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 1mo 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish Package
HARD GATE — Do not attempt to publish without verifying prerequisites. Missing auth tokens, stale builds, or duplicate versions cause CI failures that are hard to debug post-push.
HARD GATE — Always run
--dry-runfirst. Package registries are append-only — a bad publish cannot be fully undone on most registries.
Publish packages to language-specific registries. Detects package type from manifest files, verifies publish prerequisites, runs the registry-specific publish command, and confirms the version appears on the registry.
Process
1. Detect package type
Read the project root for manifest files to determine the package type:
| Manifest | Registry | Publish command |
|---|---|---|
package.json |
npm | npm publish --access public |
Cargo.toml |
crates.io | cargo publish |
setup.py / pyproject.toml |
PyPI | twine upload dist/* or flit publish |
Formula/<name>.rb |
Homebrew | brew bump-formula-pr |
| Multiple detected | Polyglot | Error: specify registry with `--registry <npm |
If no manifest is found, prompt the user to specify the type or pass --type <npm|crates.io|pypi|brew>.
2. Verify prerequisites
Before attempting any publish, run all applicable checks:
npm (package.json):
See REFERENCE.md
crates.io (Cargo.toml):
See REFERENCE.md
PyPI (setup.py / pyproject.toml):
See REFERENCE.md
3. Run publish
After all prerequisite checks pass, run the registry-specific command:
See REFERENCE.md
4. Verify publish success
After publish, confirm the version appears on the registry:
See REFERENCE.md
5. Error handling
On failure, surface actionable hints:
See REFERENCE.md
6. Dry-run mode (--dry-run)
Run --dry-run to verify all prerequisites without actually publishing:
See REFERENCE.md
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.
- 1mo ago First seen · 338 lines · 36 tokens per session scan A 6aa0a55098b7
publish-package is a cursor rule published in the GitHub repository danielvm-git/bigpowers (267 stars, last pushed 27d ago), licensed MIT. It adds 36 tokens to every session and 2,602 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
app-router-patterns
Next.js 14+ App Router patterns — Server Components, Client Components, Route Handlers, Server Actions, and metadata API.
general
API design standards — treat the API as a consumer-facing contract. Apply when designing, reviewing, or changing HTTP endpoints, routes, controllers, request/response payloads, and API resources.
00-project-rules
ContextOS core project rules and role orchestration.
vue
Rules for Vue (2 and 3) single-file components.
node
ContextOS rules for node.