Borrowing it
Nothing to install: this file belongs to kaze-jp/kusa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kaze-jp/kusa/main/.claude/commands/kiro/spec-impl.mdgit clone --depth 1 https://github.com/kaze-jp/kusaWrote 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.
[](https://agentmods.dev/commands/kaze-jp/kusa/spec-impl)<a href="https://agentmods.dev/commands/kaze-jp/kusa/spec-impl"><img src="https://agentmods.dev/badge/commands/kaze-jp/kusa/spec-impl/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.
<a href="https://agentmods.dev/commands/kaze-jp/kusa/spec-impl"><img src="https://agentmods.dev/badge/commands/kaze-jp/kusa/spec-impl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00000 | $0.00803 |
| Opus 5.5 | $0.00000 | $0.00321 |
| Sonnet 5.5 | $0.00000 | $0.00161 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
spec-impl scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start Implementation
Begin implementing approved tasks using TDD in an isolated worktree. This is the manual implementation command — for fully autonomous execution (implementation → PR → review → merge), use /kiro:ao-run instead.
Usage
/kiro:spec-impl <feature-name> [task-numbers]
/kiro:spec-impl my-feature— all pending tasks/kiro:spec-impl my-feature 1.1— single task/kiro:spec-impl my-feature 1,2,3— specific tasks
Instructions
-
Validate prerequisites:
.kiro/specs/$FEATURE_NAME/tasks.mdmust exist. If not →/kiro:spec-tasksfirst..kiro/specs/$FEATURE_NAME/design.mdmust exist..kiro/specs/$FEATURE_NAME/requirements.mdmust exist.
-
Read context:
.kiro/specs/$FEATURE_NAME/tasks.md— task definitions, dependencies,(P)markers.kiro/specs/$FEATURE_NAME/design.md— API contracts, data models, component design.ao/steering/tech.md— coding standards, patterns.ao/steering/structure.md— file placement conventions.ao/ao.yaml— quality gate commands, git strategy
-
Create worktree:
- Use
/superpowers:using-git-worktreesto create an isolated worktree - Branch:
<git.branch_prefix><feature-name> - All implementation happens in the worktree — never on the base branch
- Use
-
Select tasks:
- If task numbers specified → execute those tasks only
- Otherwise → execute all pending tasks (
- [ ]in tasks.md) - Skip already completed tasks (
- [x]) - Respect dependency ordering
-
Execute each task with TDD (invoke
/superpowers:test-driven-development):For each task, follow Kent Beck's TDD cycle:
- RED: Write a failing test that captures the acceptance criteria
- GREEN: Write the minimum code to make the test pass
- REFACTOR: Clean up while keeping tests green
- VERIFY: Run quality gates from
ao.yaml(typecheck, lint, test, build) - MARK: Update
tasks.mdcheckbox from- [ ]to- [x]
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.
- 2mo ago First seen · 76 lines · 0 tokens per session scan A 9e87c566b6da
spec-impl is a command published in the GitHub repository kaze-jp/kusa (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 803 tokens. 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.
Other commands, from other repositories
check
Run project checks and fix any errors without committing.
act
Follow RED-GREEN-REFACTOR cycle approach for test-driven development.
implement-feature
Implement an approved feature plan with benefit-based placement, TDD, revision-bound evidence, and PR-ready output.
implement
Execute all implementation tasks from tasks.md with test-driven development, parallel batching, and atomic commits.
implement-revalidate
Read by /implement when the user asks to re-validate (D-CMD-REF-HAND).
build
Invoke the agent-skills:incremental-implementation skill alongside agent-skills:test-driven-development.