A command for making one GitHub issue the focus of a coding session. GitHub issues are task records that describe bugs, changes, or other work.

Fetching an issue, checking its required sections, reading listed architecture decision records and one reference file, creating a matching branch, and summarising the work.

It gathers the issue requirements and related architecture decisions before implementation, so work starts with the intended constraints and acceptance checks.

issue-start — Command for Claude Code by albertomarturelo: A command for making one GitHub issue the focus…

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 commands/albertomarturelo/sii/issue-start

Clone the repo

git clone --depth 1 https://github.com/albertomarturelo/sii

Made for: Claude Code.

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/commands/albertomarturelo/sii/issue-start.svg)](https://agentmods.dev/commands/albertomarturelo/sii/issue-start)

Your own site

<a href="https://agentmods.dev/commands/albertomarturelo/sii/issue-start"><img src="https://agentmods.dev/badge/commands/albertomarturelo/sii/issue-start.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 523 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00523
Opus 5	$0.00000	$0.00262
Sonnet 5	$0.00000	$0.00105
Haiku 4.5	$0.00000	$0.00052

Measured 4d ago against content hash 55924ce9a71e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-start 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 4d 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.

.claude/commands/issue-start.md · 49 lines

What it actually says

The user passes an issue number. If they don't, ask which (or list open issues via gh issue list --repo AltumStack/sii --state open).

Fetch the issue: gh issue view <n> --repo AltumStack/sii
Parse the 6 fixed sections: Context, Target, ADRs to load, Acceptance criteria, Reproduction (fixes only), Estimated sessions. If any required section is missing, STOP and tell the user the issue is malformed — propose editing it before starting. Don't infer.
For each ADR listed in ADRs to load, read the file in docs/decisions/. These set the constraints the implementation must satisfy.
Read the file in Pattern to mirror ONCE for shape. Skim, don't study.
Do NOT read the files listed in Target yet — they are where the work goes, not where context comes from.
Create the branch: git switch -c <type>/GH-<n>-<slug> where <type> matches the issue's type label and <slug> is a short kebab-case summary.
Summarize for the user, exactly:
- Objective (one line, from Context).
- Acceptance checklist (verbatim — this is the DoD; copy to the PR description on submit).
- ADRs loaded and what each constrains.
- Target paths (the files you'll write to).
- Pattern to mirror.
- Branch created: <type>/GH-<n>-<slug>.
Ask: "Ready to start?"

If Estimated sessions > 1, remind the user the issue should have been decomposed and ask whether to split it now via /issue:new.

Token discipline: do NOT scan target files or neighboring modules at this step. The issue body + ADRs are the spec. Code reading happens when implementation starts, not during orientation.

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.

4d ago First seen · 49 lines · 0 tokens per session scan A 55924ce9a71e

Subscribe to this mod's changes

issue-start is a command published in the GitHub repository albertomarturelo/sii (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 523 tokens. 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.

Git and workflow Project management anthropic chile claude cli mcp model-context-protocol

issue-start

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

tm-main

help

update-single-task

add-subtask

clear-all-subtasks

clear-subtasks