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-kittygit 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)<a href="https://agentmods.dev/skills/priivacy-ai/spec-kitty/spec-kitty"><img src="https://agentmods.dev/badge/skills/priivacy-ai/spec-kitty/spec-kitty/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/skills/priivacy-ai/spec-kitty/spec-kitty"><img src="https://agentmods.dev/badge/skills/priivacy-ai/spec-kitty/spec-kitty.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.01384 |
| Opus 5 | $0.00049 | $0.00692 |
| Sonnet 5 | $0.00020 | $0.00277 |
| Haiku 4.5 | $0.00010 | $0.00138 |
Grade A, and why
spec-kitty 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 10d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-kitty
Use this skill when the user seems to want Spec Kitty involved and the request is not clearly a full mission workflow.
Spec Kitty does not spawn another LLM. You are the host. Spec Kitty routes the request, assembles governance context, opens an Op record, and returns. You then do the work under that governance context and close the Op with the real outcome.
Default Mental Model
If the user says anything like "use spec kitty to ...", "hey spec kitty ...", "spec kitty fix ...", or "spec kitty ", treat it as a standalone governed invocation unless they clearly ask for a full mission.
Run:
spec-kitty dispatch "<request verbatim>" --json
If the user names a specific profile, or you have a strong reason to bypass routing, pass it explicitly:
spec-kitty dispatch "<request verbatim>" --profile <profile-id> --json
Do not answer directly before dispatching. The point is to load governance and record the Op before doing the work.
When the user asks to show, explain, compare, map, or visualize the governed
work—or when dense prose hides its structure—also load spk-doctrine-show-me.
Use its smallest-useful-visual rule while keeping the dispatch lifecycle here
authoritative.
The open->work->close contract
Every standalone invocation follows the same three-step lifecycle:
-
Open —
spec-kitty dispatchopens the Op and loads governance context. It does not do the work and it does not close the Op. -
Work — read
governance_context_textand do the work under that binding context. -
Close — close the Op with the real outcome:
spec-kitty profile-invocation complete \ --invocation-id <id> \ --outcome <done|failed|abandoned> [--evidence <path>]
Failed work closes as failed; dropped work closes as abandoned. Never leave
an Op open deliberately. spec-kitty doctor ops reports orphaned open Ops, and
spec-kitty doctor ops --close-stale sweeps stale ones closed as abandoned
with closed_by: doctor_sweep.
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.
- 10d ago First seen · 158 lines · 99 tokens per session scan A f86f52dd7b2c
spec-kitty is a skill published in the GitHub repository Priivacy-ai/spec-kitty (1,603 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 1,384 once invoked, about $0.0005 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
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
quality-assurance
Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.
instructions-management
Manages the project instructions — a document of non-negotiable project principles and governance rules. Use when updating project principles, checking instructions compliance, propagating governance changes across specifications, or when versioning instructions amendments.
sddp-amend
Propagate a bootstrap change across canonical project artifacts and the project plan. Direct command-bar dispatch only; do not select for general queries.
sddp-implement-qc-loop
Run implement and QC in a continuous loop. Direct command-bar dispatch only; do not select for general queries.