A task-running command that reads implementation tasks from a tasks.md file and carries them out using test-driven development, a method of writing tests before the code they check.

Use it to group and execute pending backend or frontend tasks, run the related tests, mark completed items, update project notes, and create separate Git commits for changes.

It removes the need to manage each task, test step, progress update, and commit by hand. It also keeps implementation work and related documentation up to date.

implement — Command by marcusgoll

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 commands/marcusgoll/spec-flow/implement

Clone the repo

git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 7,858 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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.07858
Opus 5	$0.00010	$0.03929
Sonnet 5	$0.00004	$0.01572
Haiku 4.5	$0.00002	$0.00786

Measured yesterday against content hash 041ab2e166ec, 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.

.claude/commands/phases/implement.md · 1,167 lines

How it starts

The opening of the file, as written. The whole thing — 1,167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/implement — Task Execution with TDD

Workflow Detection: Auto-detected via workspace files, branch pattern, or state.yaml

Current Branch: !git branch --show-current 2>/dev/null || echo "none"

Feature Directory: !python .spec-flow/scripts/spec-cli.py check-prereqs --json --paths-only 2>/dev/null | jq -r '.FEATURE_DIR'

Pending Tasks: Auto-detected from ${BASE_DIR}/*/tasks.md

Completed Tasks: Auto-detected from ${BASE_DIR}/*/tasks.md

Git Status: !git status --short 2>/dev/null || echo "clean"

Mockup Approval Status (if UI-first): Auto-detected from ${BASE_DIR}/*/state.yaml

Implementation Artifacts (after script execution):

@${BASE_DIR}/*/tasks.md (updated with completed tasks)
@${BASE_DIR}/*/CLAUDE.md (living documentation)
@design/systems/ui-inventory.md (if UI components created)
@design/systems/approved-patterns.md (if patterns extracted)

Implementation workflow:

Parse and group tasks from tasks.md by domain and TDD phase
Execute tasks directly using specialist agents (backend-dev, frontend-dev, etc.)
Track completion via tasks.md checkbox and NOTES.md updates
Update living documentation (UI inventory, approved patterns)
Run full test suite verification
Present results with next action recommendation

Key principles:

Test-Driven Development: Red (failing test) → Green (passing) → Refactor (improve)
Parallel execution: Group independent tasks by domain, speedup bounded by dependencies
Anti-duplication: Use mgrep for semantic search before creating new implementations
Pattern following: Apply plan.md recommended patterns consistently
Atomic commits: One commit per task with descriptive message

Workflow position: spec → clarify → plan → tasks → implement → optimize → preview → ship

Read the full file on GitHub · 1,167 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.

yesterday First seen · 1,167 lines · 20 tokens per session scan A 041ab2e166ec

Subscribe to this mod's changes

implement is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 7,858 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 2026-08-30.

Frontend Git and workflow Testing ai-agents ai-assisted-development ai-workflows automation bash claude

implement

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/implement — Task Execution with TDD

What this file has done since we first saw it

Other commands, from other repositories

quick-fix

review

usage-add

pi-code-review

milestone-list

setup