flow.implement

A workflow that carries out every task listed in tasks.md using test-driven development, or TDD: writing tests before the code that makes them pass.

In plain words
What is it for?
Use it to implement all planned tasks, resume unfinished work, or skip the test-first approach with --no-tdd.
Why use it?
It provides an ordered implementation process and checks required design, task, constitution, and branch setup before starting.

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/billbuchanan-code/claude-code-power-setup/flow.implement
Any agent
npx skills add billbuchanan-code/claude-code-power-setup --skill flow.implement
Clone the repo
git clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setup

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,549 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 $0.00012 $0.02549
Opus 5 $0.00006 $0.01274
Sonnet 5 $0.00002 $0.00510
Haiku 4.5 $0.00001 $0.00255

Measured yesterday against content hash cc6b5b770258, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flow.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.

skills/flow.implement/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critical Rules

  1. NEVER edit tasks.md directly to mark tasks complete - use specflow mark T###
  2. NEVER edit .specflow/orchestration-state.json directly - use specflow state set
  3. TDD by default: Write tests first, then implement (use --no-tdd to skip)
  4. Use specflow directly, NOT npx specflow - It's a local CLI, not an npm package

User Input

$ARGUMENTS

Arguments

Argument Description
(empty) Execute all tasks with TDD workflow
--no-tdd Skip test-first approach (not recommended)
continue Resume from last incomplete task

Prerequisites

Requirement Check Command If Missing
Design gate passed specflow check --gate design Run /flow.design
tasks.md exists specflow status --jsoncontext.hasTasks Run /flow.design
Constitution .specify/memory/constitution.md Run /flow.init
Git branch git branch --show-current Should be on phase branch

Execution

1. Initialize

Create todo list immediately (use TodoWrite):

  1. [IMPL] INITIALIZE - Verify design gate and load context
  2. [IMPL] EXECUTE - Implement all tasks from tasks.md
  3. [IMPL] COMPLETE - Verify implementation gate

Set [IMPL] INITIALIZE to in_progress.

specflow status --json

Parse response:

  • context.featureDir → FEATURE_DIR (abort if null)
  • context.hasTasks → must be true
  • progress.tasksTotal → verify tasks exist
specflow check --gate design

Abort if gate fails - instruct user to run /flow.design first.

Update state (respecting orchestrate ownership):

CURRENT_STEP=$(specflow state get orchestration.step.current 2>/dev/null)

# Only set step.current if not already set (standalone mode)
# Orchestrate owns step transitions - sub-commands only update status
if [[ -z "$CURRENT_STEP" || "$CURRENT_STEP" == "null" ]]; then
  specflow state set orchestration.step.current=implement orchestration.step.index=2
fi

specflow state set orchestration.step.status=in_progress

# Initialize implementation domain (for progress tracking/compaction recovery)
specflow state set orchestration.implement.started_at=$(date -Iseconds)
specflow state set orchestration.implement.current_section=""

Read the full file on GitHub · 341 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. yesterday First seen · 341 lines · 12 tokens per session scan A cc6b5b770258

Subscribe to this mod's changes

flow.implement is a skill published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 29d ago), licensed MIT. It adds 12 tokens to every session and 2,549 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens