spec-impl

A command that implements specification tasks using TDD, or test-driven development: writing tests before the code that makes them pass.

In plain words
What is it for?
Run it for selected tasks or all unfinished tasks after requirements and task files have been generated.
Why use it?
It ensures implementation follows the approved tasks and exposes missing or incorrect behavior through tests.

Command

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/gotalab/cc-sdd/spec-impl
Clone the repo
git clone --depth 1 https://github.com/gotalab/cc-sdd
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 509 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 $0.00007 $0.00509
Opus 5 $0.00003 $0.00254
Sonnet 5 $0.00001 $0.00102
Haiku 4.5 $0.00001 $0.00051

Measured 2d ago against content hash ddf3a127bebd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-impl 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • spec-impl — 86% identical, 12 lines differ
tools/cc-sdd/templates/agents/claude-code-agent/commands/spec-impl.md · 69 lines

What it actually says

Implementation Task Executor

Parse Arguments

  • Feature name: $1
  • Task numbers: $2 (optional)
    • Format: "1.1" (single task) or "1,2,3" (multiple tasks)
    • If not provided: Execute all pending tasks

Validate

Check that tasks have been generated:

  • Verify {{KIRO_DIR}}/specs/$1/ exists
  • Verify {{KIRO_DIR}}/specs/$1/tasks.md exists

If validation fails, inform user to complete tasks generation first.

Task Selection Logic

Parse task numbers from $2 (perform this in Slash Command before invoking Subagent):

  • If $2 provided: Parse task numbers (e.g., "1.1", "1,2,3")
  • Otherwise: Read {{KIRO_DIR}}/specs/$1/tasks.md and find all unchecked tasks (- [ ])

Invoke Subagent

Delegate TDD implementation to spec-tdd-impl-agent:

Use the Task tool to invoke the Subagent with file path patterns:

Task(
  subagent_type="spec-tdd-impl-agent",
  description="Execute TDD implementation",
  prompt="""
Feature: $1
Spec directory: {{KIRO_DIR}}/specs/$1/
Target tasks: {parsed task numbers or "all pending"}

File patterns to read:
- {{KIRO_DIR}}/specs/$1/*.{json,md}
- {{KIRO_DIR}}/steering/*.md

TDD Mode: strict (test-first)
"""
)

Display Result

Show Subagent summary to user, then provide next step guidance:

Task Execution

Execute specific task(s):

  • /kiro:spec-impl $1 1.1 - Single task
  • /kiro:spec-impl $1 1,2,3 - Multiple tasks

Execute all pending:

  • /kiro:spec-impl $1 - All unchecked tasks

Before Starting Implementation:

  • IMPORTANT: Clear conversation history and free up context before running /kiro:spec-impl
  • This applies when starting first task OR switching between tasks
  • Fresh context ensures clean state and proper task focus
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 · 69 lines · 7 tokens per session scan A ddf3a127bebd

Subscribe to this mod's changes

spec-impl is a command published in the GitHub repository gotalab/cc-sdd (3,646 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 509 once invoked, about $0.0000 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.