Spec Kitty is an open-source command-line tool that turns product requirements into a repository-based workflow for AI-assisted software development. It stores specifications, plans, tasks, acceptance criteria, reviews, and merge decisions in Git while giving agents isolated git worktrees for parallel implementation. The catalogue add-ons support the project's workflows for coordinating agents and governing their work.
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.
npx skills add Priivacy-ai/spec-kitty --skill spec-kitty-git-workflowgit clone --depth 1 https://github.com/Priivacy-ai/spec-kittyWrote 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/skills/priivacy-ai/spec-kitty/spec-kitty-git-workflow)<a href="https://agentmods.dev/skills/priivacy-ai/spec-kitty/spec-kitty-git-workflow"><img src="https://agentmods.dev/badge/skills/priivacy-ai/spec-kitty/spec-kitty-git-workflow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.02247 |
| Opus 5 | $0.00063 | $0.01123 |
| Sonnet 5 | $0.00025 | $0.00449 |
| Haiku 4.5 | $0.00013 | $0.00225 |
Grade A, and why
spec-kitty-git-workflow 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 8d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-kitty-git-workflow
Understand the boundary between what spec-kitty's Python code does with git and what LLM agents are expected to do. This boundary is critical — agents that try to create worktrees manually or skip implementation commits will break the workflow.
The Core Boundary
Python handles infrastructure git — worktrees, lane commits, merges, cleanup. Agents handle content git — implementation commits, rebases, conflict resolution.
| Git Operation | Who Does It | When |
|---|---|---|
git worktree add |
Python | spec-kitty implement WP## |
git commit (planning artifacts) |
Python | Before worktree creation |
git commit (lane transitions) |
Python | WP moves through claimed/in_progress/for_review/in_review |
git commit (implementation code) |
Agent | After writing code in worktree |
git merge/auto-rebase (stale lane sync) |
Python or Agent | When stale checks classify the lane as recoverable |
git merge (lane → mission → target) |
Python | spec-kitty merge |
git push |
Python (opt-in) | spec-kitty merge --push only |
git push |
Agent | Any other push scenario |
| Conflict resolution | Agent | During rebase or manual merge |
git worktree remove |
Python | After successful merge |
git branch -d (cleanup) |
Python | After successful merge |
What Python Does Automatically
1. Worktree Creation
When you run spec-kitty implement WP01, Python:
git worktree add -b kitty/mission-042-mission-lane-a .worktrees/042-mission-lane-a kitty/mission-042-mission
It also records the lane workspace context in
.kittify/workspaces/<feature>-<lane>.json so later commands resolve the same
lane worktree deterministically.
The agent never creates worktrees. Always use spec-kitty implement.
For dependent WPs in the same execution lane:
spec-kitty implement WP02
This reuses the lane worktree instead of creating a second workspace:
# WP02 reuses .worktrees/042-mission-lane-a
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 275 lines · 125 tokens per session scan A d93fa7371dc7
spec-kitty-git-workflow is a skill published in the GitHub repository Priivacy-ai/spec-kitty (1,603 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 2,247 once invoked, about $0.0006 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.
Other skills, from other repositories
shipping-and-launch
Pre-deploy hygiene for a Spring Boot 4 feature — verify gates, capture rollback plan, sign off observability, generate release notes, and stage the rollout. Used by /ship after /review approves the diff. The agent never deploys; it produces the plan a human executes.
git-workflow-and-versioning
Use when managing branches, commits, versioning, and release workflows for Android projects. Covers trunk-based development, atomic commits, versionCode/versionName, and signing configurations.
shipping-and-launch
Use when preparing to release an Android app to production. Pre-launch checklist covering code quality, security, performance, accessibility, Play Store requirements, staged rollout, and rollback planning.
github
GitHub issues, pull requests, repos, code search, releases, gists, stars, watching, forks, and Actions via the gh CLI. Use when the user mentions GitHub, an issue/PR number, a repo, a commit, a release, a gist, or code review.
gitlab
GitLab issues, merge requests, repositories, CI pipelines, and code search via the glab CLI. Use when the user mentions GitLab, an MR/issue number, a project on gitlab.com, or a self-hosted GitLab instance.
repository-template
Create code repository from template, or/and update it in parts from the content of the template that contains example of use of tools like make, pre-commit git hooks, Docker, and quality checks.