implement-issue

A command that reads one or more GitHub issues and implements the requested code changes in a repository. It also examines related source files, documentation, tests, and referenced issues or pull requests.

In plain words
What is it for?
Use it when you want an agent to implement one or more GitHub issues identified by their issue numbers.
Why use it?
It brings the issue description and the codebase investigation into one workflow. This helps avoid implementing a ticket without understanding its surrounding behavior or test expectations.

Command for Claude Code

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/utensils/claudette/implement-issue
Clone the repo
git clone --depth 1 https://github.com/utensils/claudette

Made for: Claude Code.

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 965 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 $0.00000 $0.00965
Opus 5 $0.00000 $0.00483
Sonnet 5 $0.00000 $0.00193
Haiku 4.5 $0.00000 $0.00097

Measured yesterday against content hash 5336d74735ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-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 yesterday.

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/implement-issue.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement the changes described in one or more GitHub issues passed via $ARGUMENTS.

Arguments

$ARGUMENTS accepts one or more GitHub issue numbers in any of these formats:

  • 123 — single issue
  • #123 #456 — multiple with hash prefixes
  • 123,456,789 — comma-separated
  • #123, #456 — comma-separated with hashes

Parsing rule: strip all # characters, then split on commas and/or whitespace to extract individual issue numbers.

Steps

  1. Fetch the issues — Get the full details for each issue:

    • Parse $ARGUMENTS using the rule above to extract all issue numbers
    • For each issue number, run gh issue view <number> --json title,body,labels,comments
    • Read all titles, descriptions, and comments carefully for every issue
  2. Understand the context — Research the codebase before making changes:

    • Identify which domains, files, and systems are affected across all issues
    • Read the relevant source files to understand the current behavior
    • Check docs/ for any existing documentation on the affected areas
    • Review related tests to understand expected behavior and edge cases
    • If any issue references other issues or PRs, fetch those for additional context
    • When working with multiple issues, identify shared concerns, overlapping files, and dependencies between the issues
  3. Ask clarifying questions — Before implementing, check for ambiguity:

    • If any issue is underspecified, missing acceptance criteria, or has multiple valid interpretations, stop and ask the user for clarification
    • If the combined scope seems larger than expected, confirm the approach before proceeding
    • If there are architectural decisions to make, present the options with trade-offs
    • When working with multiple issues, flag any conflicts or contradictions between issue requirements
  4. Plan the implementation — Outline the approach:

    • Enter plan mode and draft a step-by-step implementation plan
    • Plan a single unified implementation that addresses all issues cohesively
    • Identify all files that need to be created or modified
    • Note any migrations, new dependencies, or configuration changes required
    • Call out where issue requirements interact or depend on each other
    • Call out risks or areas that need extra care
    • Wait for the user to approve the plan before proceeding

Read the full file on GitHub · 69 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.

  1. yesterday First seen · 69 lines · 0 tokens per session scan A 5336d74735ad

Subscribe to this mod's changes

implement-issue is a command published in the GitHub repository utensils/claudette (75 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 965 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 2026-08-30.