flow.implement

flow.implement is a skill for Claude Code from billbuchanan-code/claude-code-power-setup. It costs 12 tokens per session (2,549 once invoked), scanned A, original, MIT.

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 Code

Written for Claude Code: context: fork in frontmatter. Also seen: mentions subagents; names the TodoWrite tool.

Good fit Use it to implement all planned tasks, resume unfinished work, or skip the test-first approach with --no-tdd.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/billbuchanan-code/claude-code-power-setup/flow.implement
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.

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.

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 flow.implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/billbuchanan-code/claude-code-power-setup/flow.implement/github.svg)](https://agentmods.dev/skills/billbuchanan-code/claude-code-power-setup/flow.implement)
Your own site
<a href="https://agentmods.dev/skills/billbuchanan-code/claude-code-power-setup/flow.implement"><img src="https://agentmods.dev/badge/skills/billbuchanan-code/claude-code-power-setup/flow.implement/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for flow.implement

Your own site · 80×15
<a href="https://agentmods.dev/skills/billbuchanan-code/claude-code-power-setup/flow.implement"><img src="https://agentmods.dev/badge/skills/billbuchanan-code/claude-code-power-setup/flow.implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00012 $0.02549
Opus 5.5 $0.00005 $0.01020
Sonnet 5.5 $0.00002 $0.00510
Haiku 4.5 $0.00001 $0.00255

Measured 1mo ago against content hash cc6b5b770258, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

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 --json → context.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. 1mo ago 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 2mo ago), licensed MIT. It adds 12 tokens to every session and 2,549 once invoked, about $0.0000 per session on Opus 5.5. 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.