issue-maker

A GitHub issue capture tool for turning a discussion into structured work items. GitHub issues are shared records for bugs, requests, and tasks.

In plain words
What is it for?
Use it to draft, refine, open, and close GitHub issues without creating branches, worktrees, or code changes.
Why use it?
It keeps the conversation focused on creating, editing, and closing issues instead of starting implementation work. It also reviews the request before creating an issue.

Skill for Claude CodeCodex

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/auerbachb/claude-code-config/issue-maker
Any agent
npx skills add auerbachb/claude-code-config --skill issue-maker
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

Made for: Claude Code, Codex.

Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00193 $0.18287
Opus 5 $0.00097 $0.09144
Sonnet 5 $0.00039 $0.03657
Haiku 4.5 $0.00019 $0.01829

Measured 2d ago against content hash bcf20adf27c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-maker 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/resolve-log.sh, scripts/set-log.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/issue-maker/SKILL.md · 784 lines

How it starts

The opening of the file, as written. The whole thing — 784 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/issue-maker — capture-only issue thread

This skill switches the whole thread into issue-capture mode and keeps it there. The only work that happens here is creating, editing, and closing GitHub issues. No implementation, no worktrees, no branches, no /start-issue, no in-thread CR-plan polling. Capture mode is a session invariant — it never turns off mid-thread.

TOP-LEVEL RULE — reflect before you file (NON-NEGOTIABLE)

Never pass a user's sentence straight through to gh issue create. Every issue gets the reflection pass below — the skill just no longer gates on it. Default mode auto-opens the issue, then reports the scope calls it made as decision points (Step 9a); it does not stop to ask first.

Why this is rule #1 — the LLM pass-through bias. LLMs have a strong bias toward passing input straight through the model to a quick output — the machine analogue of a human making assumptions instead of stopping to think before writing something down. Without an explicit, top-of-file guardrail, this skill will degrade into a thin wrapper around gh issue create: a user sentence in, a half-baked issue out. The reflection discipline is the entire point of the skill. Do not water it down or "optimize" it away under time pressure. Issue #691 changed where the reflection surfaces — as a post-create decision-points report instead of an upfront Q&A — not whether it happens. Treat any change that removes the reflection pass, or lets an issue be filed with no decision-points report naming the calls made, as a regression.

Run this reflection pass on every issue, before and after drafting:

  1. Scope check (narrow): "Is this tighter than it sounds — is the real ask just X?"
  2. Scope check (expand): "Is there an adjacent concern (Y) that should ride along so the change is coherent?"
  3. Split check: "This sounds like 2+ distinct issues — should it be split into subsidiary issues?"
  4. Sizing check (subagent fit): "This is one coherent concern — but can one Phase A/B/C pipeline land it as one reviewable PR?"
  5. Ambiguity: name any concrete word/phrase whose meaning materially changes the issue.

Read the full file on GitHub · 784 lines

Files

What ships with it

3 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. 2d ago First seen · 784 lines · 193 tokens per session scan A bcf20adf27c8

Subscribe to this mod's changes

issue-maker is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 3d ago), licensed MIT. It adds 193 tokens to every session and 18,287 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

fixer

Surgical code fixer for Bug Hunter. Implements minimal, precise fixes for verified bugs. Uses doc-lookup (Context Hub + Context7) to verify correct API usage in patches. Respects fix strategy classifications (safe-autofix vs manual-review vs larger-refactor).

codexstar69/bug-hunter · 57 tokens

referee

Final arbiter for Bug Hunter. Receives Hunter findings and Skeptic challenges, independently re-reads code, and delivers authoritative verdicts with CVSS scoring and proof-of-concept generation for security findings.

codexstar69/bug-hunter · 44 tokens

commit-security-scan

Scan code changes for security vulnerabilities using Bug Hunter-native artifacts and STRIDE context. Use whenever the user asks for PR security review, commit-diff scanning, staged-change security checks, branch-comparison security review, or pre-merge security analysis of changed code.

codexstar69/bug-hunter · 57 tokens

decompose

Decompose project or track into modules with dependency mapping. Project scope updates architecture.md and derives .ai-context.md. Track scope generates hld.md (always) and lld.md (when --lld or High-complexity module triggers it) — design-mandated artifacts that drive implement, deploy-checklist, and upload sign-off.

drafthq/draft · 71 tokens

adr

Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.

drafthq/draft · 37 tokens

deploy-checklist

Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.

drafthq/draft · 32 tokens