implement

A workflow for carrying out an approved implementation plan in a code project. It tracks tasks and checks the work as each part is completed.

In plain words
What is it for?
Use it to execute a planned project phase, delegate coding tasks, review the results, and manage fixes before moving to the next phase.
Why use it?
It connects planning with actual coding, so tasks do not remain vague or lose their status. It also catches quality problems during implementation.

Skill for Claude CodeCodex

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/danweinerdev/claude-sdd-planner/implement
Any agent
npx skills add danweinerdev/claude-sdd-planner --skill implement
Clone the repo
git clone --depth 1 https://github.com/danweinerdev/claude-sdd-planner

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,099 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 $0.00033 $0.05099
Opus 5 $0.00016 $0.02550
Sonnet 5 $0.00007 $0.01020
Haiku 4.5 $0.00003 $0.00510

Measured yesterday against content hash 887a9d8131fc, 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/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/implement — Execute Plan Phase

Path Resolution

The plugin directory contains commands/, agents/, and shared/ as siblings. Find it by globbing for **/commands/research/SKILL.md in both the current directory and ~/.claude/plugins/cache/; if multiple versions match, sort them as semantic versions (like sort -V) and use the highest, then strip commands/research/SKILL.md from the match. Resolve the planning root (artifacts) and target repository per shared/path-resolution.md in the plugin directory. Also read shared/completion-evidence.md — no task, phase, or plan flips to complete without conforming retrospective evidence.

When to Use

When a plan is approved and you're ready to implement a phase. This skill coordinates implementation: it delegates actual code work to code-implementer agents, runs them in parallel where dependencies allow, triggers quality-scanner agents after each task for a fast intent-blind quality check, and manages the review-fix cycle. It bridges the gap between /plan (which defines what to build) and /debrief (which captures what happened).

Per-task reviews during /implement dispatch quality-scanner directly (not the full four-lane review) because the relevant question after a single task is "is this code any good?" not "does the whole phase still align with the plan?". The full four-lane orchestrated review happens at end-of-phase via /code-review, which dispatches drift-detector, quality-scanner, spec-compliance, and blind-spot-finder in parallel and synthesizes their reports.

Process

1. Select Phase

  • Scan Plans/ for plans whose README frontmatter status is approved or active (skip draft, complete, and archived)
  • Ask which plan and phase to implement (or infer from context)
  • Read the plan README to understand overall context and phase dependencies
  • Read the target phase document to get the task list
  • Verify prerequisites:
    • Plan status must be approved or active
    • Phase status must be planned or in-progress (not complete, blocked, or deferred)
    • Any phases in depends_on must be complete
  • If plan status is approved, update the README frontmatter status to active
  • If phase status is planned, update it to in-progress

Read the full file on GitHub · 247 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 247 lines · 33 tokens per session scan A 887a9d8131fc

Subscribe to this mod's changes

implement is a skill published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 5,099 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

moai-kanban-foreman

One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…

modu-ai/moai-adk · 76 tokens

moai-workflow-project

Integrated project management system covering documentation, language initialization, template optimization, docs generation, and JIT document loading. Absorbed from moai-workflow-templates, moai-docs-generation, and moai-workflow-jit-docs.

modu-ai/moai-adk · 55 tokens

stale-ticket-triage

Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90 seconds Monday morning.

aozyildirim/Agena · 57 tokens

weather-fetcher

Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.

shanraisshan/claude-code-best-practice · 21 tokens

time-skill

Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.

shanraisshan/claude-code-best-practice · 37 tokens

weather-svg-creator

Creates an SVG weather card showing the current temperature for Dubai. Writes the SVG to orchestration-workflow/weather.svg and updates orchestration-workflow/output.md.

shanraisshan/claude-code-best-practice · 36 tokens