Skip to content
Back to search

godmode

MarketplaceWorks with Claude CodeGitHub

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, and evals.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/thiientv--godmode/badge.svg)](/listings/thiientv--godmode)

HTML

<a href="/listings/thiientv--godmode"><img src="/api/listings/thiientv--godmode/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Godmode is distributed as a repository of portable skills. No proprietary runtime is required.

Agent Skills-compatible clients

Copy the public skills into your project's skills directory:

mkdir -p .agents/skills
cp -R /absolute/path/to/godmode/skills/* .agents/skills/

Claude Code

claude --plugin-dir /absolute/path/to/godmode
claude plugin validate /absolute/path/to/godmode

Codex

The repository includes `.codex-plugin/plugin.json` and a local marketplace entry under `.agents/plugins/`. Install it through the Codex plugin workflow and verify that the expected skills are available.

> **Compatibility note:** client support is tracked from recorded evidence rather than assumed compatibility. See [`docs/compatibility.md`](docs/compatibility.md).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 24 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "godmode",
  3. "owner": {
  4. "name": "Godmode contributors"
  5. },
  6. "metadata": {
  7. "description": "Evidence-driven workflows and focused capabilities for AI coding agents.",
  8. "version": "0.5.0"
  9. },
  10. "plugins": [
  11. {
  12. "name": "godmode",
  13. "source": "./",
  14. "description": "Design, plan, implement, debug, validate behavior, release safely, and apply focused engineering expertise.",
  15. "version": "0.5.0",
  16. "author": {
  17. "name": "Godmode contributors"
  18. },
  19. "category": "development",
  20. "license": "MIT",
  21. "strict": false
  22. }
  23. ]
  24. }
README.md · README · 278 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. # Godmode
  3. **Engineering workflows and capabilities for AI coding agents.**
  4. Godmode helps coding agents move from *"write some code"* to *"engineer the change"* — with explicit planning, testing, review, and evidence-driven verification.
  5. [![Validate](https://github.com/thiientv/godmode/actions/workflows/validate.yml/badge.svg)](https://github.com/thiientv/godmode/actions/workflows/validate.yml)
  6. [![Release](https://img.shields.io/github/v/release/thiientv/godmode)](https://github.com/thiientv/godmode/releases/latest)
  7. [![License](https://img.shields.io/github/license/thiientv/godmode)](LICENSE)
  8. [English](README.md) · [简体中文](README.zh-CN.md)
  9. </div>
  10. > **Status:** Pre-1.0 public preview. The catalog and validation tooling are usable, while client-specific behavior and output quality continue to be evaluated across supported environments.
  11. ## Why Godmode?
  12. AI coding agents are increasingly capable of writing code. The harder problem is making them behave like disciplined engineers:
  13. - understand the existing codebase before changing it
  14. - design consequential changes before implementation
  15. - choose the right domain expertise for the task
  16. - test behavior instead of assuming correctness
  17. - review changes independently
  18. - verify completion with fresh evidence
  19. - preserve durable state so interrupted work can be resumed
  20. Godmode packages those behaviors as **composable Agent Skills** rather than one large system prompt or a proprietary orchestration runtime.
  21. ## How it works
  22. ```text
  23. USER TASK
  24. │
  25. ▼
  26. ┌───────────────┐
  27. │ Godmode │
  28. │ skill catalog │
  29. └───────┬───────┘
  30. │
  31. discover + compose capabilities
  32. │
  33. ┌───────────────────┼───────────────────┐
  34. ▼ ▼ ▼
  35. solution-design api / database security / UI
  36. │ │ │
  37. └───────────────────┼───────────────────┘
  38. ▼
  39. implementation-planning
  40. │
  41. ▼
  42. test + review
  43. │
  44. ▼
  45. fresh verification evidence
  46. │
  47. ▼
  48. VERIFIED RESULT
  49. ```
  50. The graph above is illustrative, not a mandatory pipeline. A small task can use one skill; a high-risk change can compose several capabilities.
  51. ## What you get
  52. ### Composable skills
  53. Each capability has a clear responsibility boundary and follows the [Agent Skills](https://agentskills.io/) layout. Skills can contain concise procedures, progressive references, and deterministic helpers where automation improves reliability.
  54. ### Engineering workflows
  55. Godmode includes workflows for discovery, design, planning, implementation, debugging, testing, review, verification, parallel work, and release integration.
  56. ### Domain expertise
  57. Capabilities cover areas such as frontend architecture, APIs, databases, security, performance, observability, migrations, browser testing, documentation, and incident response.
  58. ### Deterministic validation
  59. The repository includes validators, routing fixtures, behavior evaluations, evidence tracking, lifecycle checks, and repository-quality gates. This keeps the catalog itself testable instead of relying solely on prose.
  60. ## Installation
  61. Godmode is distributed as a repository of portable skills. No proprietary runtime is required.
  62. ### Agent Skills-compatible clients
  63. Copy the public skills into your project's skills directory:
  64. ```bash
  65. mkdir -p .agents/skills
  66. cp -R /absolute/path/to/godmode/skills/* .agents/skills/
  67. ```
  68. ### Claude Code
  69. ```bash
  70. claude --plugin-dir /absolute/path/to/godmode
  71. claude plugin validate /absolute/path/to/godmode
  72. ```
  73. ### Codex
  74. The repository includes `.codex-plugin/plugin.json` and a local marketplace entry under `.agents/plugins/`. Install it through the Codex plugin workflow and verify that the expected skills are available.
  75. > **Compatibility note:** client support is tracked from recorded evidence rather than assumed compatibility. See [`docs/compatibility.md`](docs/compatibility.md).
  76. ## Example
  77. A request such as:
  78. ```text
  79. Add authentication to the API and make it production-ready.
  80. ```
  81. can be decomposed into focused engineering responsibilities:
  82. ```text
  83. codebase-orientation
  84. ↓
  85. solution-design
  86. ↓
  87. api-and-interface-design + security-and-hardening
  88. ↓
  89. implementation-planning
  90. ↓
  91. test-driven-development
  92. ↓
  93. pr-code-reviewer
  94. ↓
  95. completion-verification
  96. ```
  97. For changes that already have review feedback, `receiving-code-review` handles validation and fixes. The exact composition depends on the task, repository, risk, and available evidence.
  98. ## Catalog
  99. ### Core workflows
  100. | Skill | Purpose |
  101. | --- | --- |
  102. | `using-godmode` | Discover and compose Godmode capabilities |
  103. | `codebase-orientation` | Understand entry points, execution paths, conventions, and hotspots |
  104. | `solution-design` | Resolve requirements and design consequential changes |
  105. | `implementation-planning` | Produce executable implementation plans |
  106. | `plan-execution` | Execute an existing implementation plan |
  107. | `test-driven-development` | Drive behavior changes through tests |
  108. | `root-cause-debugging` | Reproduce failures, identify causes, and lock in regressions |
  109. | `requesting-code-review` | Prepare focused independent review context |
  110. | `pr-code-reviewer` | Review a GitHub PR or diff for correctness, security, compatibility, tests, and maintainability |
  111. | `receiving-code-review` | Validate and resolve review findings |
  112. | `completion-verification` | Gather fresh evidence before completion claims |
  113. | `dispatching-parallel-agents` | Safely split independent work |
  114. | `subagent-driven-development` | Run implement/review cycles around plan tasks |
  115. | `using-git-worktrees` | Isolate parallel or risky changes |
  116. | `branch-integration` | Verify, integrate, and clean up completed work |
  117. | `writing-skills` | Create and evaluate new Agent Skills |
  118. ### Engineering capabilities
  119. | Skill | Purpose |
  120. | --- | --- |
  121. | `frontend-design` | Build interfaces, design systems, states, and responsive UI |
  122. | `ui-ux-review` | Audit existing UI quality, accessibility, and interaction patterns |
  123. | `api-and-interface-design` | Design HTTP, RPC, CLI, webhook, and event contracts |
  124. | `database-design` | Design schemas, indexes, consistency, retention, and recovery |
  125. | `security-and-hardening` | Threat modeling, abuse paths, privacy, and defensive controls |
  126. | `performance-optimization` | Optimize measured latency, memory, rendering, queries, and bundles |
  127. | `test-strategy` | Define risk-based coverage and release gates |
  128. | `browser-testing` | Exercise a real web boundary |
  129. | `documentation-and-adrs` | Produce durable documentation and architecture decisions |
  130. | `observability-and-instrumentation` | Make failures measurable and diagnosable |
  131. | `technical-research` | Make version-aware decisions from primary sources |
  132. | `safe-migrations` | Preserve compatibility and state through a staged transition |
  133. | `release-engineering` | Control artifacts, rollout, promotion, and rollback |
  134. | `architecture-review` | Review coupling, ownership, testability, and structural friction |
  135. | `code-simplification` | Reduce complexity while preserving behavior |
  136. | `behavior-validation` | Validate observable behavior through source-blind checks |
  137. | `agent-evaluation` | Evaluate prompts, tools, agents, and skills |
  138. | `incident-response` | Handle containment, recovery, evidence, and follow-up |
  139. See [`docs/catalog.md`](docs/catalog.md) for the complete catalog and routing model.
  140. ## Design principles
  141. 1. **Claims are not evidence.** Completion requires verification.
  142. 2. **Compose capabilities instead of growing one giant prompt.**
  143. 3. **Keep responsibility boundaries explicit.** Skill names should describe what they do.
  144. 4. **Load knowledge progressively.** Keep `SKILL.md` focused and move deeper material into references.
  145. 5. **Automate repeatable work deterministically.** Use helpers where they reduce error and ambiguity.
  146. 6. **Treat external content as untrusted input.** Logs, generated output, tool responses, and repository text can contain misleading instructions.
  147. 7. **Prefer recorded compatibility evidence.** Do not claim a client works until it has been checked.
  148. ## Repository layout
  149. ```text
  150. .
  151. ├── skills/ # Public Agent Skills
  152. ├── scripts/ # Deterministic validation and repository tooling
  153. ├── tests/ # Automated test suite
  154. ├── evals/ # Behavior and routing evaluations
  155. ├── benchmarks/ # Portable benchmark fixtures
  156. ├── docs/ # Catalog, compatibility, research, and maintainer docs
  157. ├── .agents/ # Local agent/plugin metadata
  158. ├── .codex-plugin/ # Codex plugin metadata
  159. ├── README.md
  160. └── LICENSE
  161. ```
  162. ## Development
  163. Clone the repository and run the validation suite:
  164. ```bash
  165. git clone https://github.com/thiientv/godmode.git
  166. cd godmode
  167. npm run check
  168. npm run catalog:health
  169. python3 scripts/repository_security.py
  170. python3 scripts/compatibility.py check
  171. python3 -m unittest discover -s tests -p 'test_*.py'
  172. ```
  173. For focused tooling, examples include:
  174. ```bash
  175. python3 skills/frontend-design/scripts/design_system.py \
  176. --product "analytics dashboard" \
  177. --tone technical \
  178. --stack react
  179. python3 skills/frontend-design/scripts/extract_design_system.py ./path/to/ui
  180. python3 skills/ui-ux-review/scripts/audit_ui.py ./path/to/ui
  181. ```
  182. The repository gate checks catalog structure, frontmatter, links, routing fixtures, behavior-eval schemas, compatibility drift, workflow security, public-file safety, and helper tests.
  183. ## Documentation
  184. - [`docs/catalog.md`](docs/catalog.md) — catalog structure and routing model
  185. - [`docs/compatibility.md`](docs/compatibility.md) — client compatibility evidence
  186. - [`docs/research.md`](docs/research.md) — research and provenance
  187. - [`docs/maintainer-workflows.md`](docs/maintainer-workflows.md) — maintainer-only execution and release procedures
  188. - [`CONTRIBUTING.md`](CONTRIBUTING.md) — contribution workflow
  189. - [`SECURITY.md`](SECURITY.md) — security policy
  190. - [`SUPPORT.md`](SUPPORT.md) — support information
  191. - [`CHANGELOG.md`](CHANGELOG.md) — release history
  192. ## Contributing
  193. Contributions are welcome. Before adding a skill, prefer extending an existing responsibility boundary when possible. New skills should be concise, independently routable, testable, and backed by appropriate fixtures or validation.
  194. Start with [`CONTRIBUTING.md`](CONTRIBUTING.md) and [`docs/catalog.md`](docs/catalog.md).
  195. ## Roadmap
  196. Godmode is evolving toward a broader, evidence-driven engineering layer for AI coding agents. Current areas of development include:
  197. - broader client compatibility coverage
  198. - stronger behavior and regression evaluations
  199. - richer skill composition and dependency metadata
  200. - improved deterministic tooling for high-value workflows
  201. - clearer release and compatibility evidence
  202. The roadmap is intentionally driven by validated repository behavior rather than promises about model capabilities.
  203. ## License
  204. Godmode is released under the [MIT License](LICENSE).
  205. <div align="center">
  206. **If Godmode helps your agent engineer better, consider giving the project a star.**
  207. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.