agentmods.dev

heaven-style

heaven-style is a skill for Claude Code, Codex from Magolor/Blueprint. It costs 22 tokens per session (1,644 once invoked), scanned A, original, MIT.

A coding and project-work guide for TypeScript and Python repositories. It sets rules for code, documentation, architecture, interfaces, data handling, and tests.

In plain words
What is it for?
Use it when writing or reviewing code and documentation, designing interfaces, refactoring, or aligning tests.
Why use it?
It gives an agent a consistent way to work within an existing repository’s language, tools, ownership rules, and compatibility limits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

not rated 5repo changed today A scan SkillSpector: warn 22 tokens original MIT

Good fit Use it when writing or reviewing code and documentation, designing interfaces, refactoring, or aligning tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/magolor/blueprint/heaven-style
View source ↗ Magolor/Blueprint
Install

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.

Any agent
npx skills add Magolor/Blueprint --skill heaven-style
Clone the repo
git clone --depth 1 https://github.com/Magolor/Blueprint

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for heaven-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/magolor/blueprint/heaven-style/github.svg)](https://agentmods.dev/skills/magolor/blueprint/heaven-style)
Your own site
<a href="https://agentmods.dev/skills/magolor/blueprint/heaven-style"><img src="https://agentmods.dev/badge/skills/magolor/blueprint/heaven-style/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.

agentmods 80×15 button for heaven-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/magolor/blueprint/heaven-style"><img src="https://agentmods.dev/badge/skills/magolor/blueprint/heaven-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 47
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.01644
Opus 5 $0.00011 $0.00822
Sonnet 5 $0.00004 $0.00329
Haiku 4.5 $0.00002 $0.00164

Measured today against content hash 4a45e2ad6316, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

heaven-style 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 today.

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.

.agents/skills/heaven-style/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Heaven Style

Summary

Use shared code, design, GUI, and authoring conventions. Apply repository policy, runtime contracts, and compatibility promises first. Preserve the repository's language and toolchain. Default an undecided new project to TypeScript.

Quick Read

At each new request, select or retain the agent role, using Default when none fits. Apply intent and judgment: preserve the goal and explicit constraints, assess suggested approaches, and retain decision authority. Follow the role, then a fitting workflow and its tasks. A role can span a session or one assignment; workflows sequence distinct tasks.

This entry is a summary, not a substitute for the full rules. Complete the reading procedure before implementation, diagnosis, review, explanation, tests, or code-bearing examples. Small changes have the same reading prerequisite.

  • Code: Read every Markdown file recursively in the applicable TypeScript or Python rule tree, plus all shared project rules and design philosophy. Include nested examples, formats, lifecycle, package, and configuration pages. Read both language trees for work involving both languages.
  • Architecture: Complete code reading for the target language, then read architecture checks, the design guide, every design manual, and all code-design comparisons. Also inspect the repository’s architecture and decision owners before proposing structure.
  • GUI: Read every file in GUI design, including stack, interaction, review, and all six palette files. GUI code and architecture work also require the corresponding code and architecture reading.
  • Authoring: Before creating or substantively editing PRs, issues, comments, docs, or reports, read authoring for explicit Summary sections and searchable YAML, then the applicable template. Standalone docs also require the documentation task and all documentation rules, including nested pages. Code examples and architecture claims add their respective reading prerequisites. Load only applicable template details. Routine coding does not require the template catalog.

Read the full file on GitHub · 62 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. today Changed · +5 lines · +1 tokens per session 4a45e2ad6316
  2. 2d ago Changed · -113 lines · -42 tokens per session ed02f0e2eeaf
  3. 4d ago Changed · +1 lines a13aec7196e2
  4. 10d ago First seen · 169 lines · 63 tokens per session scan A ca3335b34eeb

Subscribe to this mod's changes

heaven-style is a skill published in the GitHub repository Magolor/Blueprint (5 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 1,644 once invoked, about $0.0001 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.

Code reviewProject managementPythongithub-actionspyprojectpython-templatestarter-templatetemplate
Related

Other skills, from other repositories

uv

Guide for using uv, the Python package and project manager. Use this when working with Python projects, scripts, packages, or tools.

smorinlabs/py-launch-blueprint · 29 tokens

pr-review-triage

Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.

cobusgreyling/loop-engineering · 35 tokens

new-python-project

Use when bootstrapping a new Python repo, project, CLI, package, script, or uv project from py-launch-blueprint. Ask whether the user wants the opinionated template bootstrap or a minimal setup before running commands.

smorinlabs/py-launch-blueprint · 49 tokens

check

Run the full local quality gate (prek hooks + tox test matrix) before committing or opening a pull request. Use when asked to "check", "lint", "run CI locally", or verify a change is ready.

gpauloski/python-template · 46 tokens

validate-python-stack

Validate the Python Template repository or a project generated from it. Use before committing, publishing, deploying, or reviewing a stack to check catalog compilation, rendering, dependencies, formatting, tests, security workflows, skills, and representative runtime behavior.

leynier/python-template · 51 tokens

aget-close-project

Close a PROJECTPLAN with verifiable-assertion gate (V-tests + commits + retrospective), deferred-surface scan for next-plan handoff, and status transition (ACTIVE → COMPLETE / CLOSED / ABANDONED / SUPERSEDED). Strict counterpart to /aget-create-project (D71 Layer 2). Closes asymmetric verb-pair gap at PROJECTPLAN…

aget-framework/template-advisor-aget · 78 tokens