implement

implement is a skill for Claude Code from FarzamMohammadi/the-engineer. It costs 206 tokens per session (2,475 once invoked), scanned A, original, MIT.

An implementation workflow that turns an approved software plan into working code through focused agent tasks. It then checks the result against the plan and fixes anything incomplete or incorrect.

In plain words
What is it for?
Use it to build an approved feature, coordinate coding tasks, verify the resulting changes, and close remaining implementation issues.
Why use it?
It keeps implementation focused on the agreed requirements and treats reported completion as something to verify. This reduces gaps, bugs, and unfinished parts in delivered changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

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 skills/farzammohammadi/the-engineer/implement
Any agent
npx skills add FarzamMohammadi/the-engineer --skill implement
Clone the repo
git clone --depth 1 https://github.com/FarzamMohammadi/the-engineer

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/implement.svg)](https://agentmods.dev/skills/farzammohammadi/the-engineer/implement)
Your own site
<a href="https://agentmods.dev/skills/farzammohammadi/the-engineer/implement"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 206 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,475 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 5.1 $0.00206 $0.02475
Opus 5 $0.00103 $0.01238
Sonnet 5 $0.00041 $0.00495
Haiku 4.5 $0.00021 $0.00248

Measured 6d ago against content hash 81e1205feafa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

.claude/skills/implement/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement

You own the outcome. Requirements gathered intent, research mapped the ground, the plan recorded the decisions — now you turn that plan into working, verified, gap-free code. This is the "I" of RRPIR.

You do this in a specific way, and the way is the point. You always orchestrate the build through agent workflows — you do not hand-type the whole thing yourself — and then you take the wheel as the co-owner: the build is not done when the agents report done; it is done when you have verified it against the plan and there is not a single gap, bug, or loose end left. Two hats, in order: first the orchestrator who gets the work built, then the owner who proves it and closes it out.

This is not /review. Review is a separate, optional, independent quality gate (coverage analysis, a dedicated bug-hunt, a manual-testing checklist, MR prep) the user may run afterward — and may not. Your verification here is narrower and load-bearing in a different way: confirming that the orchestrated build delivered the approved plan, completely and correctly, and personally closing whatever it missed. Don't reproduce the review process; own the implementation to done.

Phase 1: Absorb the plan

Read every upstream artifact in full before launching anything:

  • The plan — .claude/temp/create-plan/
  • Research — .claude/temp/research/ — and requirements — .claude/temp/requirements-gathering/

Internalize the decisions, the task breakdown, the verification contract, the scope boundary, and the risks. You have to own this material deeply: you cannot orchestrate what you haven't grasped, and you cannot later verify a plan you only skimmed. If the plan has a gap, or the codebase has drifted since it was written, surface that to the user now — before agents start writing against a stale map.

Phase 2: Orchestrate the build (always — even when it's one workflow)

Hand the execution to the /workflow-orchestrator skill's method (its Phase 3 — Orchestrate). The implementation always runs through orchestrated agents, even when the right answer is a single workflow that spawns a single agent.

Read the full file on GitHub · 148 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. 6d ago First seen · 148 lines · 206 tokens per session scan A 81e1205feafa

Subscribe to this mod's changes

implement is a skill published in the GitHub repository FarzamMohammadi/the-engineer (12 stars, last pushed 1mo ago), licensed MIT. It adds 206 tokens to every session and 2,475 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

doubt-driven-review

In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…

BlackBeltTechnology/pi-agent-dashboard · 90 tokens

spec-coherence-check

Sweep all active OpenSpec proposals for staleness, conflicts, and obsolescence against the current codebase and archived changes. Use when proposals may be outdated, when checking cross-proposal conflicts, or before starting a batch of implementations. Produces a gap-analysis report, updates a priority queue file, and…

BlackBeltTechnology/pi-agent-dashboard · 80 tokens

faq-mine

Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…

BlackBeltTechnology/pi-agent-dashboard · 94 tokens

session-to-guideline

Turn a pi session into a Markdown "how-we-did-it" collaboration guideline: reads the session's JSONL transcript and synthesizes a reusable playbook of which prompts worked, what had to be steered, and how to reproduce the result faster. Use when: "document this session", "write up how we did X with the AI", "make a…

BlackBeltTechnology/pi-agent-dashboard · 93 tokens

autofix

Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.

BlackBeltTechnology/pi-agent-dashboard · 30 tokens

performance-optimization

Measure-first performance work. Use on triggers like "it's slow", "profile this", "optimize perf", "fix the bottleneck", "improve load time / Core Web Vitals", or when a measured regression needs fixing. Enforces measure-before-optimize. Fills a perf gap not covered by existing project skills. Not a build/ship…

BlackBeltTechnology/pi-agent-dashboard · 77 tokens