implement

A command that starts executing the tasks for the currently selected feature. It reads the feature's task list and can retry failed tasks or create recovery tasks.

In plain words
What is it for?
Use it to implement a feature from its task list, set retry limits, or enable automatic recovery when tasks fail.
Why use it?
It removes the need to start each implementation task manually and checks that the required feature files exist first. This keeps execution tied to the documented plan.

Command

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/tzachbon/smart-ralph/implement
Clone the repo
git clone --depth 1 https://github.com/tzachbon/smart-ralph
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,022 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 $0.00004 $0.09022
Opus 5 $0.00002 $0.04511
Sonnet 5 $0.00001 $0.01804
Haiku 4.5 $0.00000 $0.00902

Measured 2d ago against content hash ef901e46c9bb, 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.

plugins/ralph-speckit/commands/implement.md · 1,122 lines

How it starts

The opening of the file, as written. The whole thing — 1,122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start Execution

You are starting the task execution loop.

Determine Active Feature

  1. Read .specify/.current-feature to get active feature (format: <id>-<name>)
  2. If file missing or empty: error "No active feature. Run /speckit:start first."

Validate Prerequisites

  1. Check .specify/specs/$feature/ directory exists
  2. Check .specify/specs/$feature/tasks.md exists. If not: error "Tasks not found. Run /speckit:tasks first."

Parse Arguments

From $ARGUMENTS:

  • --max-task-iterations: Max retries per task (default: 5)
  • --recovery-mode: Enable iterative failure recovery (default: false). When enabled, failed tasks trigger automatic fix task generation instead of stopping.

Commit Uncommitted Spec Files

Before starting execution, check if spec files are uncommitted:

git status --porcelain .specify/specs/$feature/

If uncommitted files exist, commit them:

git add .specify/specs/$feature/
git commit -m "chore(speckit): commit spec files before implementation"

This ensures spec files are tracked before task execution begins.

Initialize Execution State

  1. Count total tasks in tasks.md (lines matching - [ ] or - [x])
  2. Count already completed tasks (lines matching - [x])
  3. Set taskIndex to first incomplete task
  4. Read featureId and name from feature directory name (format: <id>-<name>)

Write .specify/specs/$feature/.speckit-state.json:

{
  "featureId": "<3-digit id>",
  "name": "<feature-name>",
  "basePath": ".specify/specs/<id>-<name>",
  "phase": "execution",
  "taskIndex": <first incomplete>,
  "totalTasks": <count>,
  "taskIteration": 1,
  "maxTaskIterations": <parsed from --max-task-iterations or default 5>,
  "globalIteration": 1,
  "maxGlobalIterations": 100,
  "awaitingApproval": false,
  "recoveryMode": <true if --recovery-mode flag present, false otherwise>,
  "maxFixTasksPerOriginal": 3,
  "fixTaskMap": {}
}

Start Execution

After writing the state file, output the coordinator prompt below. This starts the execution loop. The stop-hook will continue the loop by outputting continuation prompts until all tasks are complete.

Read the full file on GitHub · 1,122 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. 2d ago First seen · 1,122 lines · 4 tokens per session scan A ef901e46c9bb

Subscribe to this mod's changes

implement is a command published in the GitHub repository tzachbon/smart-ralph (527 stars, last pushed 4d ago), licensed MIT. It adds 4 tokens to every session and 9,022 once invoked, about $0.0000 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 2026-08-30.