S

superlite

cwogu/superlite · v3.2.0 · Development & Workflow

by CWoguAwesome AI Plugins

Claude Code plugin of build lifecycle skills that plan work, run parallel subagent waves, and drive TDD, debugging, and branch finishing

Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is superlite a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Codex
  • Claude Code
  • Antigravity CLI
  • Cursor
  • Kimi Code
  • 11 skills
  • Runs hooks on agent events

Before you install

Sign-in
Not declared
Declared access
Interactive, Read, Write
License
MIT

Check before relying on it

  • Some security checks did not finish: Cisco skill scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is superlite?

superlite is a published development & workflow plugin for AI coding agents that works with Codex, Claude Code, Antigravity CLI, Cursor and Kimi Code, developed by CWogu and distributed through the HOL AI plugin registry. Claude Code plugin of build lifecycle skills that plan work, run parallel subagent waves, and drive TDD, debugging, and branch finishing.

Canonical slug
cwogu/superlite
Version
v3.2.0 · updated Nov 4, 2026

Registry snapshot

Owner verification
Not verified
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Partial scan
Digest verified
Yes
11 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

89

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100/100
Maintenance
100/100
MCP server setup
100/100
Plugin Security
93/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/iha2/superlite
Source commit
76b6787c63fe…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

Continuous scanner CI detected

No action is required. This plugin receives the full trust score.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Partial scan
Security result
93
Score from finished checks
0
High findings

Some checks did not finish: Cisco skill scan. No blocking issue was found in the checks that did finish, but this is not a passed scan.

Provider
codex-plugin-scanner
Grade
A · Excellent
Version
3.24.2
codex:hol-plugin-scanner-xPPPeo / cisco-skill-scanner: failedcodex:hol-plugin-scanner-xPPPeo / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

16/16

6 checks

[claude:.] Operational Security

3/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

31/31

9 checks

[codex:.] Security

16/16

9 checks

[codex:.] Operational Security

3/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

15/15

3 checks

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

[gemini:.] Gemini Extension

10/10

3 checks

[gemini:.] Security

16/16

6 checks

[gemini:.] Operational Security

3/6

5 checks

[gemini:.] Code Quality

10/10

2 checks

[kimi:.] Kimi Plugin

36/40

10 checks

[opencode:.] OpenCode Plugin

2/2

4 checks

[opencode:.] Security

16/16

6 checks

[opencode:.] Operational Security

3/6

5 checks

[opencode:.] Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

lowoperational-securityDEPENDABOT_MISSINGReported 4 times

Automation or dependency surfaces exist, but .github/dependabot.yml is missing.

Add Dependabot updates for GitHub Actions and dependency manifests.

lowsecurityKIMI_INTERFACE_INVALID

interface must be an object containing string display metadata.

Use string values for Kimi interface metadata.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

  1. 1

    Add the marketplace

    Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.

    claude code
  2. 2

    Install the plugin

    Installs the superlite entry from the superlite-dev marketplace.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell
  4. 4

    Check it is installed

    Lists installed plugins. The entry should appear as enabled.

    shell

To remove it later, run claude plugin uninstall superlite@superlite-dev.

Did setup work in Claude Code?

No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W44, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "name": "superlite",
  "version": "3.2.0",
  "description": "Lightweight Claude Code skills for the build lifecycle: one approval gate, parallel waves, short reports",
  "author": {
    "name": "CWogu",
    "url": "https://github.com/iha2"
  },
  "homepage": "https://github.com/iha2/superlite",
  "repository": "https://github.com/iha2/superlite",
  "license": "MIT",
  "keywords": [
    "inventing",
    "swarm",
    "skills",
    "planning",
    "tdd",
    "debugging",
    "workflow"
  ],
  "skills": "./",
  "hooks": {},
  "interface": {
    "displayName": "Superlite",
    "developerName": "CWogu",
    "shortDescription": "Lean planning, TDD, debugging, and delivery workflows for coding agents",
    "longDescription": "Use Superlite to guide agent work through inventing with one approval gate, contract-style implementation plans, parallel-wave subagent execution, test-driven development, systematic debugging, and finish-the-branch workflows.",
    "category": "Developer Tools",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "I have an idea for something I would like to build.",
      "Let's add a feature to this project."
    ],
    "websiteURL": "https://github.com/iha2/superlite",
    "privacyPolicyURL": "https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement",
    "termsOfServiceURL": "https://docs.github.com/en/site-policy/github-terms/github-terms-of-service",
    "screenshots": [
      "./assets/agent-map.webp"
    ],
    "logo": "./assets/superlite-logo.svg",
    "composerIcon": "./assets/superlite-logo.svg"
  },
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/iha2/superlite
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

11 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli
  • diagnosis

    skills/diagnosis/SKILL.md

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    Raw SKILL.md
  • drafting

    skills/drafting/SKILL.md

    Use when you have an approved design or requirements for a multi-step task and need an implementation plan, before touching code.

    Raw SKILL.md
  • feature-prototype

    skills/feature-prototype/SKILL.md

    Use in feature mode after the feature plan is approved, to cut the smallest runnable container of an existing app for the prototype build

    Raw SKILL.md
  • inventing

    skills/inventing/SKILL.md

    Use when the user asks to build a feature or component, add functionality, or change behavior, before any implementation code is written.

    Raw SKILL.md
  • mvp-prototype

    skills/mvp-prototype/SKILL.md

    Use in MVP mode (/superlite:mvp), after the .mvp.md feature plan is written, to make the one-file clickable prototype, check it, and read the user's feedback before the agent-format plan is written.

    Raw SKILL.md
  • proof

    skills/proof/SKILL.md

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs

    Raw SKILL.md
  • shipping

    skills/shipping/SKILL.md

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

    Raw SKILL.md
  • swarm

    skills/swarm/SKILL.md

    Use when executing a superlite plan that has a %% taskgraph. Runs a ready-queue scheduler over an idle agent pool, with scripts for the mechanical steps, selective reviews, and a packet-only final review.

    Raw SKILL.md
  • testing

    skills/testing/SKILL.md

    Use when implementing any feature or bugfix, before writing implementation code

    Raw SKILL.md
  • using-superlite

    skills/using-superlite/SKILL.md

    Use when starting any conversation - explains superlite, how to size a request, and which skill fits which task

    Raw SKILL.md
  • writing-specs

    skills/writing-specs/SKILL.md

    Use when agent_specs is on (or the user asks for a spec) to write what done looks like and why before a plan or implementation.

    Raw SKILL.md

File inventory

.agents/plugins/marketplace.json

file

360 bytes

c3be5c1b253440df…

.claude-plugin/marketplace.json

file

693 bytes

b8f3520f593a36a5…

.claude-plugin/plugin.json

file

330 bytes

23c3b0a48fda2eeb…

.codex-plugin/plugin.json

plugin-manifest

1,465 bytes

95ac877fefb4c3c2…

.cursor-plugin/plugin.json

file

525 bytes

1fc5d5ad1d56d41d…

.cursor/rules/feature-worktrees.mdc

file

1,123 bytes

4ecebec422be8311…

.cursor/rules/no-cursor-commit-notes.mdc

file

580 bytes

7155d0c0682d5eef…

.kimi-plugin/plugin.json

file

3,642 bytes

b0dee0912682fd25…

.opencode/plugins/superlite.js

file

16,070 bytes

737d6207489fdebf…

AGENTS.md

file

2,848 bytes

18b38dcd4a73805a…

agents/final-reviewer.md

file

1,650 bytes

fb68ee96a5ccd970…

agents/fixer-opus.md

file

695 bytes

d153583f514f48fe…

agents/fixer-sonnet-high.md

file

700 bytes

c15226679c1ba31c…

agents/fixer-sonnet.md

file

633 bytes

32afc64fea57b7ea…

agents/implementer-haiku.md

file

1,402 bytes

445197d566f55c9d…

agents/implementer.md

file

592 bytes

391bf6afad3173cb…

agents/package-reviewer.md

file

2,620 bytes

a8891f5f0a88b676…

assets/agent-map.webp

asset

116,584 bytes

eff7c89cae5650ad…

assets/superlite-logo.svg

asset

3,910 bytes

279013c31827d174…

CLAUDE.md

file

119 bytes

e0d83aa07b4ec285…

commands/agents.md

file

665 bytes

a0bcd5ac7e86174c…

commands/ai.md

file

357 bytes

8ebafd27e0d6f2fb…

commands/approve.md

file

856 bytes

e3ae181ea252c8da…

commands/debug.md

file

1,831 bytes

883ff7d9e770a08f…

commands/feature.md

file

7,556 bytes

bc5ec09e9de9a6c6…

commands/finish.md

file

298 bytes

9277b2d3fccea256…

commands/help.md

file

582 bytes

00ab0436905d82e5…

commands/human.md

file

476 bytes

0fdc18e801e34dce…

commands/intro.md

file

378 bytes

81e727d2f603c6e5…

commands/mvp.md

file

5,434 bytes

8429a5cced8367b3…

commands/report.md

file

793 bytes

0aac0c24f9b6839f…

commands/resume.md

file

1,066 bytes

9fd6c52730000ec6…

commands/review.md

file

1,690 bytes

7d60ea7e30f0fb98…

commands/setup.md

file

645 bytes

d31b059b000118e1…

commands/small.md

file

1,154 bytes

79f27ebc18d5c47f…

commands/start.md

file

4,161 bytes

30cc3625a829fbdc…

commands/status.md

file

674 bytes

1925af6f5a0dcbfd…

commands/stop.md

file

468 bytes

8e0b5bcbc86d2953…

commands/tail.md

file

1,058 bytes

457f553f36a55f1b…

gemini-extension.json

file

207 bytes

b17ace6b1581fcf8…

GEMINI.md

file

88 bytes

4aa716946511b3f6…

hooks/hooks-cursor.json

file

1,394 bytes

1f66f034b0925393…

hooks/hooks.json

file

1,598 bytes

f4a5f6b2480024d5…

LICENSE

file

1,416 bytes

f9a36098e95235c1…

package-lock.json

file

205 bytes

6c3380702952b80c…

package.json

file

593 bytes

039a7b420678ec3c…

pyproject.toml

file

422 bytes

b8a0b61ed4ba55ff…

README.md

file

22,382 bytes

f67d631d74448de5…

SECURITY.md

file

738 bytes

88b8a1bb67c0e13e…

skills/diagnosis/SKILL.md

skill

3,196 bytes

160497f060496a0d…

skills/drafting/review-plan.md

skill

4,847 bytes

97952ccad0681c43…

skills/drafting/SKILL.md

skill

21,920 bytes

54467bfdb50e500f…

skills/feature-prototype/SKILL.md

skill

4,499 bytes

8eaec956e551d1c5…

skills/inventing/SKILL.md

skill

10,950 bytes

0d3f1e12869a69ed…

skills/mvp-prototype/feedback-schema.md

skill

1,861 bytes

11f015e21368b94d…

skills/mvp-prototype/mock-patterns.md

skill

2,790 bytes

66d1bb9bc96cd6d2…

skills/mvp-prototype/page-template.html

skill

10,129 bytes

226cb7907cde3ee8…

skills/mvp-prototype/SKILL.md

skill

5,542 bytes

e9aff548a43bb202…

skills/proof/SKILL.md

skill

2,294 bytes

9ca82804bdc48748…

skills/shipping/SKILL.md

skill

6,008 bytes

02ddf2dcaf36f88e…

skills/swarm/config/gitignore.json

skill

1,059 bytes

2da25b169ae88f94…

skills/swarm/config/hosts/cursor.json

skill

1,332 bytes

be770711fd7dbd8f…

skills/swarm/config/models.json

skill

873 bytes

d46dac53ce8ac4ed…

skills/swarm/config/predictor.json

skill

1,340 bytes

34e82e5001a687b5…

skills/swarm/config/routing.json

skill

1,959 bytes

228a97d1e732f21d…

skills/swarm/config/testprobe.json

skill

1,232 bytes

a5d33b11d760e3f3…

skills/swarm/fixing.md

skill

5,408 bytes

529287cedfc60545…

skills/swarm/implementing.md

skill

4,510 bytes

4a1622b5a436028d…

skills/swarm/metrics.md

skill

4,250 bytes

2a743768f309b17e…

skills/swarm/orchestrator.md

skill

8,486 bytes

cd8fbf624009dc19…

skills/swarm/probes/pack/__init__.py

skill

0 bytes

e3b0c44298fc1c14…

skills/swarm/probes/pack/_common.py

skill

1,466 bytes

169f79ff018ecfc4…

skills/swarm/probes/pack/deep.py

skill

1,595 bytes

8c20257d2b98fdc3…

skills/swarm/probes/pack/encoding.py

skill

2,123 bytes

cf5072d2ff0509ea…

skills/swarm/probes/pack/file.py

skill

3,633 bytes

dbd918d55b323b8c…

skills/swarm/probes/pack/numeric.py

skill

1,692 bytes

a9a9a368d32039ed…

skills/swarm/probes/pack/protocol.py

skill

3,501 bytes

ee3a276439d45b57…

skills/swarm/probes/pack/state.py

skill

1,826 bytes

db03e7534e232133…

skills/swarm/probes/probe_common.py

skill

4,491 bytes

315e64a82b686e85…

skills/swarm/probes/probe_pool.py

skill

10,317 bytes

032a960d3acfe266…

skills/swarm/probes/probe_regress.py

skill

6,083 bytes

e81026ccffea4ea8…

skills/swarm/probes/probe_run.py

skill

21,156 bytes

3041d1c11d2e2251…

skills/swarm/probes/probe_store.py

skill

5,481 bytes

2d34d448bf0efcc4…

skills/swarm/probes/probe_worker.py

skill

11,422 bytes

5a5f9db7aaf3fe58…

skills/swarm/scripts/_pyrun.py

skill

3,251 bytes

a09f5cff94ed8291…

skills/swarm/scripts/agent_specs.py

skill

4,935 bytes

51e73dad015a114d…

skills/swarm/scripts/base.py

skill

6,113 bytes

76dda37593a999ea…

skills/swarm/scripts/budget.py

skill

8,362 bytes

f89f2faa0aec0f7d…

skills/swarm/scripts/build_prime.py

skill

12,976 bytes

8eca59fea5d5a3fc…

skills/swarm/scripts/checkpoint.py

skill

25,862 bytes

02c06438b044e11d…

skills/swarm/scripts/compact_due.py

skill

2,364 bytes

3b4fa5af872b79e6…

skills/swarm/scripts/cost.py

skill

9,303 bytes

9eb5023cb1fc0866…

skills/swarm/scripts/dispatch.py

skill

24,181 bytes

395960f3116221c5…

skills/swarm/scripts/exclusive.py

skill

7,451 bytes

171db212b2a0cee4…

skills/swarm/scripts/finish.py

skill

11,596 bytes

685b3c9c328d7c2c…

skills/swarm/scripts/gitignore.py

skill

6,816 bytes

7ced58faf53005a7…

skills/swarm/scripts/graph.py

skill

5,129 bytes

151e3e41bf238a52…

skills/swarm/scripts/graphify_gate.py

skill

1,927 bytes

2fbe31d76ce78578…

skills/swarm/scripts/history.py

skill

13,463 bytes

9ecc52aabe410984…

skills/swarm/scripts/host_models.py

skill

9,008 bytes

f49a4c0599965d4e…

Browse all 150 files

superlite — Frequently asked questions

What is superlite?
superlite is an AI plugin in the HOL registry. Claude Code plugin of build lifecycle skills that plan work, run parallel subagent waves, and drive TDD, debugging, and branch finishing.
How do I install superlite?
Install superlite in your harness: Codex — codex plugin marketplace add iha2/superlite; Claude Code — /plugin marketplace add iha2/superlite; Cursor — npx [email protected] add iha2/superlite. Full step-by-step guidance is on the HOL plugin page.
How do I install superlite in HOL Guard?
To install superlite in HOL Guard, start with hol-guard plugin install cwogu/superlite --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install superlite in Codex?
To install superlite in Codex, start with codex plugin marketplace add iha2/superlite. The complete step-by-step install guide for Codex is on the HOL plugin page.
How do I install superlite in Claude Code?
To install superlite in Claude Code, start with /plugin marketplace add iha2/superlite. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How is the Trust Score for superlite computed?
superlite has a HOL Trust Score of 89 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/cwogu%2Fsuperlite/trust
Who publishes superlite?
superlite is published by CWogu and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W44. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Reviews and similar plugins