An end-to-end feature implementation command that takes a ticket or written specification through planning, coding, checking, review, and delivery. It can ask questions first or use a more intensive question-by-question mode.

Use it to implement a feature from a ticket or specification, including creating a branch, making the change, verifying it, reviewing it, and preparing the result.

It gives a feature request a defined path from requirements to a deliverable change, reducing the need to coordinate each stage manually.

implement — Command by lugassawan

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/lugassawan/swe-workbench/implement

Clone the repo

git clone --depth 1 https://github.com/lugassawan/swe-workbench

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,420 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	$0.00024	$0.01420
Opus 5	$0.00012	$0.00710
Sonnet 5	$0.00005	$0.00284
Haiku 4.5	$0.00002	$0.00142

Measured yesterday against content hash 7148f09d33b3, 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.

commands/implement.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature request: $ARGUMENTS

If $ARGUMENTS contains a ticket reference, invoke swe-workbench:ticket-context first and prepend its structured summary to the delegation context below. Skip if $ARGUMENTS is free-text with no recognizable ref. (Trigger patterns are defined in that skill's "When to invoke" section.)

Interrogation mode. Before producing anything, resolve the mode:

Explicit signal in the invocation is honored without asking. grill-me = --grill, "grill me", or "grill-me mode". standard = --standard, "standard", or "quick". Strip the signal from $ARGUMENTS and record the resolved mode.
No explicit signal: ask via AskUserQuestion — one question, header "Mode", options Standard (recommended, listed first) and Grill me. Standard description: "Lightweight clarify — a restatement and at most one question, then proceed." Grill-me description: "Relentlessly walk the decision tree one question at a time, each with a recommended answer, self-answering from the codebase where possible." Use the user's choice.

Standard mode: proceed with the command's existing lightweight clarify (a restatement and at most one clarifying question) — do not ask the mode question again.

Grill-me mode: activate swe-workbench:workflow-grill and run its interrogation loop to completion (exit on shared understanding or when the user says "proceed"). Then thread the emitted ## Resolved decisions block into the command's normal artifact/delegation step below — the same way a ticket-context summary is prepended — and continue as in standard mode.

Activate the swe-workbench:workflow-development skill in Mode B (Implementation-Time Behavior). Execute all five phases in order:

Phase 1 — Branch Isolate this work in a worktree when the scope warrants it (non-trivial changes, risk of destabilizing main). For tiny single-file changes, skip with a written rationale. swe-workbench:workflow-development Phase 1 will detect the worktree provider automatically: rimba add <task> when rimba is available (PATH or common install locations), otherwise superpowers:using-git-worktrees.

Phase 2 — Implement

Architectural consult (conditional): If the ticket implies a new service, a boundary or contract change, a technology choice, or any non-trivial design fork — invoke the swe-workbench:senior-engineer subagent before plan-writing for a boundary/trade-off read. Fold its output into the plan.
If no written plan exists, draft one via superpowers:writing-plans. Whenever you author or finalize a plan that modifies the codebase — whether saved to a plan file or passed to ExitPlanMode — first activate swe-workbench:workflow-development in Mode A and embed the rendered ## Workflow section per skills/workflow-development/templates/plan-workflow-section.md before the plan is finalized (i.e. before ExitPlanMode). Run the skill's project-detection (git branch -a, git log --oneline -20, Makefile grep, PR-template lookup) so placeholders are substituted from this repo, not left as [[detect:…]]. Since /swe-workbench:implement always modifies the codebase, Mode A always applies here.
- Defect guard: if the plan being finalized lacks a ## Workflow section, add it before emitting the plan rather than passing an incomplete plan to ExitPlanMode.
Execute via superpowers:executing-plans for sequential work, superpowers:subagent-driven-development for parallelizable units, or swe-workbench:workflow-delegated-implementation when scope/complexity warrants grouping changes into focused swe-workbench:code-impl sub-agent dispatches to keep the orchestrator context lean.
Apply swe-workbench:principle-tdd per implementation unit: red → green → refactor.
Mid-implementation forks: If an architectural decision emerges that was not anticipated in the plan, pause and consult swe-workbench:senior-engineer rather than guessing. Update the plan before continuing.

Phase 3 — Verify Run superpowers:verification-before-completion before claiming any phase done. Do not advance to Phase 4 until this passes clean.

Read the full file on GitHub · 51 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.

yesterday First seen · 51 lines · 24 tokens per session scan A 7148f09d33b3

Subscribe to this mod's changes

implement is a command published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,420 once invoked, about $0.0001 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 2026-08-31.

Code review Git and workflow Planning claude-code claude-code-plugin clean-architecture design-patterns domain-driven-design golang

implement

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

What this file has done since we first saw it

Other commands, from other repositories

dispatch-worker

release-tag

OPSX: Fast Forward

deploy

simplify

gum-schema