start-issue

start-issue is a skill for Claude Code, Codex from gopherguides/gopher-ai. It costs 64 tokens per session (5,591 once invoked), scanned A, original, MIT.

A workflow for starting work on a numbered GitHub issue, from reading its context through implementation, testing, and pull-request submission. TDD, or test-driven development, means writing tests as part of the process before or alongside the code that satisfies them.

In plain words
What is it for?
Use it to begin a bug fix or feature from an issue number or URL, prepare the worktree, implement the change with TDD, verify it, and submit a pull request.
Why use it?
It turns an issue into a defined development process so the problem, implementation, tests, and submission are handled together.

Skill for Claude CodeCodex

Part of the go-workflow plugin — 10 skills, 3 commands, 4 agents, 4 hooks shipped together

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/gopherguides/gopher-ai/start-issue
Any agent
npx skills add gopherguides/gopher-ai --skill start-issue
Clone the repo
git clone --depth 1 https://github.com/gopherguides/gopher-ai

Made for: Claude Code, Codex.

Or install go-workflow, the plugin that ships this one along with the rest of its 10 skills, 3 commands, 4 agents, 4 hooks.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,591 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 $0.00064 $0.05591
Opus 5 $0.00032 $0.02795
Sonnet 5 $0.00013 $0.01118
Haiku 4.5 $0.00006 $0.00559

Measured 3d ago against content hash ab34d85f66ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-issue 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 3d 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.

plugins/go-workflow/skills/start-issue/SKILL.md · 495 lines

How it starts

The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start Issue

Before requesting decisions, entering a planning workflow, or delegating work, read ${CLAUDE_PLUGIN_ROOT}/lib/driver-interaction.md and follow its cross-platform capability-binding rules.

Read ${CLAUDE_PLUGIN_ROOT}/lib/decision-gates.md before resolving any workflow choice.

Empty Arguments

If $ARGUMENTS is empty or not provided, explain:

This skill starts work on a GitHub issue, automatically detecting whether it's a bug fix or new feature and following the appropriate workflow.

Claude Code: /go-workflow:start-issue <issue-number> [--skip-coverage] [--coverage-threshold <n>]

Codex: $go-workflow:start-issue <issue-number> [--skip-coverage] [--coverage-threshold <n>]

Example: /go-workflow:start-issue 123 or $go-workflow:start-issue 123 --coverage-threshold 80

Options:

  • --skip-coverage: Compatibility hint for source-free changes; changed source files still run coverage verification
  • --coverage-threshold <n>: Override default 60% coverage threshold
  • --no-agents: Use single-session workflow instead of subagent dispatch (for small/simple issues)

Workflow:

  1. Fetch issue details, labels, and comments
  2. Optionally create a git worktree for isolated work
  3. Auto-detect issue type (bug vs feature)
  4. Create fix/ or feat/ branch (or use worktree branch)
  5. For bugs: Check duplicates → TDD red-green → verify → coverage check → security review
  6. For features: Plan approach → TDD red-green → verify → coverage check → security review
  7. Commit, push, and create PR

This is a missing-intent gate. Request the issue number: "What issue number would you like to work on?" If structured input is unavailable, ask in the final response and stop without initializing the loop or claiming completion.


Subagent Model Policy

Default orchestrated mode uses model frontmatter from ${CLAUDE_PLUGIN_ROOT}/agents/*.md:

Role Model policy
Explore haiku
Implementer inherit
Spec Review sonnet
Quality Review sonnet

Read the full file on GitHub · 495 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. 3d ago First seen · 495 lines · 64 tokens per session scan A ab34d85f66ac

Subscribe to this mod's changes

start-issue is a skill published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 5,591 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.