implement

A workflow for carrying out a saved software implementation plan from start to finish, using multiple coding agents where work can be done in parallel.

In plain words
What is it for?
Use it to build a feature from a plan in `.plans/`, or to create a plan from a specification and then implement it.
Why use it?
It removes the need to manually coordinate plan phases, dependencies, shared files, and findings from earlier checks.

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/joshsmithxrm/power-platform-developer-suite/implement
Any agent
npx skills add joshsmithxrm/power-platform-developer-suite --skill implement
Clone the repo
git clone --depth 1 https://github.com/joshsmithxrm/power-platform-developer-suite

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 765 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 $0.00032 $0.00765
Opus 5 $0.00016 $0.00382
Sonnet 5 $0.00006 $0.00153
Haiku 4.5 $0.00003 $0.00076

Measured 2d ago against content hash 5026f3e12af6, 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.

.claude/skills/implement/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Plan

/implement — read spec and plan from .plans/, execute phases /implement .plans/<date>-<name>.md — explicit plan path /implement specs/<name>.md — spec path: generate the plan from this spec first, save it to .plans/, then execute

Prerequisites

Agent tool, /review, /verify, /qa, /debug, /gates.

Input

$ARGUMENTS = path to a plan file, or a spec file to generate the plan from. If omitted: use the most relevant spec on the branch, generate a plan, save to .plans/, proceed.

Fallback — no spec: check .plans/context.md first; if present, generate a plan from it. Otherwise: prompt the user — run /design or continue without spec? See REFERENCE.md §1 for the full fallback chain.

Process

Step 1: Read & Analyze Plan

  • Identify phases, dependencies, parallelization opportunities (sequential vs. parallel).
  • Findings reconciliation: Cross-reference every finding ID (CC-01, V-15) from any findings doc against plan text; report gaps.
  • Shared-infrastructure scan: Identify files in multiple phases; flag conflicts (must serialize or designate owner). See REFERENCE.md §5.

Step 2: Load Spec Context

Read specs/CONSTITUTION.md + relevant specs (grep **Code:** frontmatter). Build spec context block for every subagent. See REFERENCE.md §4.

Step 3: Assess Current State

Check git status, branch, existing worktrees, prior phase commits.

Step 4: Create Task Tracking

Build task list from plan phases; mark already-completed work done.

Step 4.5: Assess Model Selection

Read REFERENCE.md §3 for Opus vs. Sonnet guidance.

Step 5: Execute Each Phase

A. Dispatch Agents — parallel for independent tasks; see REFERENCE.md §5.

B. Collect Results — wait for all agents; review summaries.

B2. Cross-Agent Consistency Check — verify cross-surface contract consistency; see REFERENCE.md §7.

C. Verify Phase Gate — build → tests → AC coverage → surface-specific verify/qa → review. See REFERENCE.md §6. Fix before advancing.

Read the full file on GitHub · 66 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. 2d ago First seen · 66 lines · 32 tokens per session scan A 5026f3e12af6

Subscribe to this mod's changes

implement is a skill published in the GitHub repository joshsmithxrm/power-platform-developer-suite (5 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 765 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