lumin-repo-lens-write-gate

lumin-repo-lens-write-gate is a skill for Claude Code, Codex from annyeong844/lumin-repo-lens. It costs 63 tokens per session (1,212 once invoked), scanned A, original, MIT.

A review gate for TypeScript and JavaScript code changes that checks whether existing code can be reused before writing and records what changed afterward. It applies to adding, editing, moving, renaming, or refactoring code.

In plain words
What is it for?
Use it before and after code changes to find reusable files, types, functions, or helpers and to verify the exact structural differences introduced.
Why use it?
It reduces duplicate helpers and unsupported claims about what exists in a repository. The checks provide evidence about the searched area and the resulting change.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also agents/openai.yaml present.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the lumin-repo-lens plugin — 3 skills, 9 commands, 4 hooks shipped together

Good fit Use it before and after code changes to find reusable files, types, functions, or helpers and to verify the exact structural differences introduced.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add annyeong844/lumin-repo-lens
Claude Code
/plugin install lumin-repo-lens

Made for: Claude Code, Codex.

Or install lumin-repo-lens, the plugin that ships this one along with the rest of its 3 skills, 9 commands, 4 hooks.

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 lumin-repo-lens-write-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/annyeong844/lumin-repo-lens/lumin-repo-lens-write-gate/github.svg)](https://agentmods.dev/skills/annyeong844/lumin-repo-lens/lumin-repo-lens-write-gate)
Your own site
<a href="https://agentmods.dev/skills/annyeong844/lumin-repo-lens/lumin-repo-lens-write-gate"><img src="https://agentmods.dev/badge/skills/annyeong844/lumin-repo-lens/lumin-repo-lens-write-gate/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 lumin-repo-lens-write-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/annyeong844/lumin-repo-lens/lumin-repo-lens-write-gate"><img src="https://agentmods.dev/badge/skills/annyeong844/lumin-repo-lens/lumin-repo-lens-write-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,212 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.
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 $0.00063 $0.01212
Opus 5 $0.00032 $0.00606
Sonnet 5 $0.00013 $0.00242
Haiku 4.5 $0.00006 $0.00121

Measured 13d ago against content hash 7f6ca332d427, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lumin-repo-lens-write-gate 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 13d 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.

skills/lumin-repo-lens-write-gate/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lumin Repo Lens Write Gate

This is the code-change transaction surface for lumin-repo-lens. It owns pre-write and post-write together because post-write reads the pre-write-advisory.<invocationId>.json produced by the same change.

Keep the human-facing answer short and kind. The assistant reads the cold artifacts; the human gets the next concrete step.

Core Contract

NO STRUCTURAL CLAIM WITHOUT MACHINE EVIDENCE
NO ABSENCE CLAIM WITHOUT STATED SCAN RANGE

Use hedging like "looks like" only when the internal label is degraded or unknown.

Shared Engine

The shared engine lives in the sibling audit skill:

node ${CLAUDE_PLUGIN_ROOT}/skills/lumin-repo-lens/scripts/audit-repo.mjs

In a maintainer checkout, the equivalent command is:

node audit-repo.mjs

Slash commands still read <SKILL_ROOT>/references/command-routing.md from the shared audit skill for exact flag routing. Below, <SKILL_ROOT> means ${CLAUDE_PLUGIN_ROOT}/skills/lumin-repo-lens in plugin installs, or the repo root in a maintainer checkout.

Below, <audit-repo> means whichever of the two commands above applies to the current context.

This surface owns /lumin-repo-lens:pre-write and /lumin-repo-lens:post-write.

References To Load

  • Read <SKILL_ROOT>/references/command-routing.md first for slash-command routing.
  • Read <SKILL_ROOT>/references/pre-write-intent-shape.md before constructing or repairing intent JSON.
  • Read <SKILL_ROOT>/canonical/pre-write-gate.md for the pre-write protocol, domain-cluster hints, exact shape lookup, and advisory language.
  • Read <SKILL_ROOT>/canonical/any-contamination.md for planned type escapes, contaminated reuse demotion, and post-write escape deltas.
  • Read <SKILL_ROOT>/references/lifecycle-modes.md when exact flags, exit codes, or artifact names matter.
  • Read <SKILL_ROOT>/references/glossary.md and <SKILL_ROOT>/references/false-positive-index.md when advisory output surfaces FP/tier terms that need explanation. The long FP case ledger is maintainer-only; do not load it for ordinary pre-write/post-write.

Read the full file on GitHub · 139 lines

Files

What ships with it

1 file 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. 13d ago First seen · 139 lines · 63 tokens per session scan A 7f6ca332d427

Subscribe to this mod's changes

lumin-repo-lens-write-gate is a skill published in the GitHub repository annyeong844/lumin-repo-lens (26 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 1,212 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

frontend-ai-guide

Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.

shinpr/claude-code-workflows · 41 tokens

better-auth

Skill for integrating Better Auth - comprehensive TypeScript authentication framework for Cloudflare D1, Next.js, Nuxt, and 15+ frameworks. Use when adding auth, encountering D1 adapter errors, or implementing OAuth/2FA/RBAC features.

secondsky/claude-skills · 53 tokens

typescript-rules

React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.

shinpr/claude-code-workflows · 39 tokens

bun-bundler

This skill should be used when the user asks about "bun build", "Bun.build", "bundling with Bun", "code splitting", "tree shaking", "minification", "sourcemaps", "bundle optimization", "esbuild alternative", "building for production", "bundling TypeScript", "bundling for browser", "bundling for Node", or…

secondsky/claude-skills · 90 tokens

bun-hot-reloading

Use when implementing hot reloading with Bun (--hot, --watch), HMR, or automatic code reloading during development. Covers watch mode, hot mode, and HTTP server reload.

secondsky/claude-skills · 42 tokens

pulumi-best-practices

Load when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output or apply() usage; wants to create ComponentResource classes; needs to refactor resources without destroying them (aliases); is setting up secrets or config; or is configuring a pulumi preview/up CI workflow.…

pulumi/agent-skills · 92 tokens