implement

A development command for taking a GitHub issue through implementation to a commit ready for review. It is tailored to the mcp-cli project and includes branch preparation, repository checks, and issue-specific work.

In plain words
What is it for?
Use it when you have a GitHub issue number and want to prepare the fix, work on the correct branch, and produce a merged-ready commit.
Why use it?
It gives a repeatable workflow for moving from a tracked problem to code that can be reviewed and merged. It also avoids common mistakes with temporary worktree branches.

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/theshadow27/mcp-cli/implement
Clone the repo
git clone --depth 1 https://github.com/theshadow27/mcp-cli

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 2,278 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 $0.02278
Opus 5 $0.00000 $0.01139
Sonnet 5 $0.00000 $0.00456
Haiku 4.5 $0.00000 $0.00228

Measured yesterday against content hash 6d40927e6fa8, 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 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.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement GitHub Issue

You are a developer on the mcp-cli project. Your job is to take a GitHub issue from description to merged-ready commit.

Input

The user will provide a GitHub issue number (e.g., /implement 12 or /implement #12). Parse the number from: $ARGUMENTS

Workflow

Step 0: Prepare Branch

You must be on an issue-named branch before your first commit — never push from the worktree's auto-created worktree-claude-* (or agent-*) scratch branch. gc/cleanup heuristics key on those prefixes to reclaim disposable worktrees (#2662), so a PR pushed from one can have its branch deleted while the PR is still open (#2866).

If you are in a worktree (the common sprint case — git branch --show-current prints worktree-claude-* or agent-*), you cannot git checkout main (main is checked out in the base repo). Rename the current branch in place instead:

git branch -m fix/issue-<number>-<short-slug>   # renames the scratch branch

If you are in the base repo (branch is main), start clean and cut a new branch:

git checkout main
git pull origin main
git checkout -b fix/issue-<number>-<short-slug>

Use a prefix that matches the expected commit type (feat/, fix/, refactor/, etc.).

Step 1: Fetch the Issue

gh issue view <number>

Read the title, body, labels, and comments. Extract:

  • Goal: What needs to exist when this is done
  • Acceptance criteria: How we know it works
  • Scope boundaries: What's explicitly out of scope or deferred

Summarize what you understood back to the user in 3-5 bullet points before proceeding.

Step 1a: Read sprint plan context

If a sprint is active, the issue may have plan-level scope decisions that override or narrow the issue body — typically captured in the sprint plan's "Pre-session clarifications required" section, "Hot-shared file watch", or the Excluded list. The issue body alone is not authoritative when a sprint plan exists (sprint-45 issue #1775 shipped the wrong design because the worker never read its plan entry, see #1801).

Read the full file on GitHub · 230 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 · 230 lines · 0 tokens per session scan A 6d40927e6fa8

Subscribe to this mod's changes

implement is a command published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,278 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.