A project-specific workflow for handling GitHub issues from investigation through release. GitHub issues are records used to track bugs, feature requests, and other work; a monorepo is one repository containing multiple parts of a project.

Creating or selecting issues, investigating and fixing them, checking version changes and platform-specific behavior, addressing review findings, and preparing a release.

It gathers the required checks for the lox-brain project in one process, reducing the chance of missed updates, broken platform behavior, or unresolved review feedback.

issue — Skill for Claude Code and Codex by isorensen: A project-specific workflow for handling GitHub issues from investigation…

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.

agentmods

npx agentmods add skills/isorensen/lox-brain/issue

Any agent

npx skills add isorensen/lox-brain --skill issue

Clone the repo

git clone --depth 1 https://github.com/isorensen/lox-brain

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/isorensen/lox-brain/issue.svg)](https://agentmods.dev/skills/isorensen/lox-brain/issue)

Your own site

<a href="https://agentmods.dev/skills/isorensen/lox-brain/issue"><img src="https://agentmods.dev/badge/skills/isorensen/lox-brain/issue.svg" alt="Measured on agentmods" height="20"></a>

Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,358 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00124	$0.03358
Opus 5	$0.00062	$0.01679
Sonnet 5	$0.00025	$0.00672
Haiku 4.5	$0.00012	$0.00336

Measured 5d ago against content hash abaf94112710, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue scanned grade A with 1 finding 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 5d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

4. **Know the cross-platform pitfalls**: `shell()` in `packages/installer/src/utils/shell.ts` wraps commands with `cmd.exe /c` on Windows. `execFile` with arrays does NOT resolve `.cmd`/`.bat` — always use `shell()` or `

.claude/skills/issue/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/issue — GitHub Issue Handler

End-to-end workflow for resolving GitHub issues in the lox-brain monorepo. Covers everything from reading the issue to creating the GitHub Release.

Usage modes

/issue <number> — Work on an existing issue (full workflow below)
/issue new <description> — Create a new issue and optionally start working on it
/issue (no args) — List open issues and ask which to work on

Why this skill exists

Handling issues in this project requires a specific checklist that is easy to forget partially. Past incidents:

Version hardcoded in LOX_VERSION and DEFAULT_CONFIG.version was not updated alongside package.json, causing the splash screen to show the wrong version for multiple releases.
Windows .cmd fix was shipped but didn't actually work because execFile() can't run .cmd files — unit tests with mocks passed but real execution failed.
Code review findings were not addressed before merge.

This skill encodes the full checklist so nothing slips through.

Creating a new issue (`/issue new`)

When the user provides a description for a new issue:

Determine issue type: bug, feature, or enhancement based on the description.

Draft the issue using the repo's issue templates. Create via:

gh issue create --title "<title>" --body "<body>" --label <bug|enhancement>

Show the created issue URL to the user.
Ask: "Want to start working on this issue now?" If yes, proceed with the full workflow below using the new issue number.

Keep the title concise (<70 chars). Use the description body to include context, expected behavior, and any relevant details the user provided.

Working on an issue (`/issue <number>`)

Phase 0 — Orient (if context is fresh)

If you're starting with a clean conversation and don't yet know this codebase, do this FIRST before reading the issue:

Read CLAUDE.md — project overview, architecture (Obsidian vault <-> VM via WireGuard <-> MCP server), monorepo layout, tech stack (TypeScript + Node 22 + PostgreSQL 16 + pgvector + vitest), security constraints (Zero Trust, no public IPs, no hardcoded secrets).
Scan packages/ — ls packages/ shows which packages exist. Key packages:
- installer/ — cross-platform setup wizard (user flow, runs locally on user machine)
- core/ — MCP server, vault watcher, embedding service (runs on GCP VM)
- shared/ — constants, types shared across packages
- cli/ — lox command-line tool (lox status, lox migrate)
Know where fixes live: installer bugs -> packages/installer/src/steps/step-*.ts; MCP/DB bugs -> packages/core/src/; version/constants -> packages/shared/.
Know the cross-platform pitfalls: shell() in packages/installer/src/utils/shell.ts wraps commands with cmd.exe /c on Windows. execFile with arrays does NOT resolve .cmd/.bat — always use shell() or execSync with a string for Windows compatibility.

Read the full file on GitHub · 200 lines

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.

5d ago First seen · 200 lines · 124 tokens per session scan A abaf94112710

Subscribe to this mod's changes

issue is a skill published in the GitHub repository isorensen/lox-brain (2 stars, last pushed 20d ago), licensed MIT. It adds 124 tokens to every session and 3,358 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflow Project management obsidian openbrain secondbrain

plannotator

Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and exporting or sharing Guided Reviews. Invoke when asked to use Plannotator for anything not covered by a more specific…

backnotprop/plannotator · 73 tokens

plannotator-annotate

Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.

backnotprop/plannotator · 29 tokens

wiki-context-pack

Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "use my vault as context", "context slice for X", "pack the wiki for my agent", or "bounded context for Y".

Ar9av/obsidian-wiki · 63 tokens

obsidian-bases

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

kepano/obsidian-skills · 63 tokens

design-mcp-server

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

cyanheads/obsidian-mcp-server · 62 tokens

maintenance

Investigate, adopt, and verify dependency updates — with special handling for @cyanheads/mcp-ts-core. Captures what changed, understands why, cross-references against the codebase, adopts framework improvements, syncs project skills, and runs final checks. Supports two entry modes: run the full flow end-to-end, or…

cyanheads/obsidian-mcp-server · 75 tokens

issue