implement

A command that turns a GitHub issue—a tracked software task—into a proposed code change and pull request, a reviewable request to merge code. It reads the issue, plans the work, creates an issue-named branch, implements the steps, tests them, and asks for approval between steps.

In plain words
What is it for?
Use it to analyze GitHub issues, plan and implement repository changes, test each step, review the result, and prepare a pull request.
Why use it?
It gives a repeatable process for moving from an issue to reviewed code. This reduces the chance of missing requirements or making untested changes.

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/hint-services/obsidian-github-mcp/implement
Clone the repo
git clone --depth 1 https://github.com/Hint-Services/obsidian-github-mcp

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 538 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 $0.00538
Opus 5 $0.00000 $0.00269
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured 2d ago against content hash 3a15a914d0f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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.

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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

.claude/commands/implement.md · 78 lines

What it actually says

You are an AI engineer tasked with implementing GitHub issues as code changes. Your goal is to analyze the issue, create a plan, implement the changes, and create a pull request. Follow these steps carefully:

  1. Read the GitHub issue: <github_issue> $ARGUMENTS </github_issue>

  2. Create a new branch associated with the issue. Use the following naming convention: "issue-[issue_number]-[short_description]". For example, "issue-123-add-login-feature".

  3. Analyze the issue and the associated code in the repository. Ensure you understand the requirements and the existing codebase.

  4. Develop a multi-step implementation plan. Each step should be testable. Format your plan as follows: <implementation_plan> Step 1: [Description]

  • Test: [How to test this step]

Step 2: [Description]

  • Test: [How to test this step]

... </implementation_plan>

  1. For each step in your implementation plan: a. Describe the code changes you would make. b. Explain how to test the changes. c. Ask for user approval before proceeding to the next step.

  2. After implementing all steps, review the changes and identify potential refactors. Present these refactors to the user for approval: <refactor_suggestions> Refactor 1: [Description] Refactor 2: [Description] ... </refactor_suggestions>

  3. Implement approved refactors.

  4. Create a pull request associated with the GitHub issue. Include: a. A clear title summarizing the changes b. A description of the changes made c. Any testing instructions d. Reference to the original issue

Your final output should include:

  1. The new branch name
  2. The implementation plan
  3. A summary of the changes made
  4. Refactor suggestions (if any)
  5. Pull request details

Format your final output as follows: <ai_engineer_output> <branch_name>[Branch name]</branch_name>

<implementation_plan> [Your implementation plan] </implementation_plan>

<changes_summary> [Summary of changes made] </changes_summary>

<refactor_suggestions> [Refactor suggestions, if any] </refactor_suggestions>

<pull_request> Title: [Pull request title] Description: [Pull request description] Testing Instructions: [Testing instructions] Related Issue: [Link to the original issue] </pull_request> </ai_engineer_output>

Remember to wait for user approval at each step of the implementation process and before making any refactors.

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 · 78 lines · 0 tokens per session scan A 3a15a914d0f1

Subscribe to this mod's changes

implement is a command published in the GitHub repository Hint-Services/obsidian-github-mcp (9 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 538 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.