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 agentmods add instructions/priivacy-ai/spec-kitty/agents-mdgit 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/instructions/priivacy-ai/spec-kitty/agents-md)<a href="https://agentmods.dev/instructions/priivacy-ai/spec-kitty/agents-md"><img src="https://agentmods.dev/badge/instructions/priivacy-ai/spec-kitty/agents-md.svg" alt="Measured on agentmods" 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 | $0.09920 | $0.09920 |
| Opus 5 | $0.04960 | $0.04960 |
| Sonnet 5 | $0.01984 | $0.01984 |
| Haiku 4.5 | $0.00992 | $0.00992 |
Grade A, and why
spec-kitty AGENTS.md 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 today.
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 — 631 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Kitty Development Guidelines
Spec Kitty is a toolkit for Spec-Driven Development (SDD) — clear, actionable specifications ahead of implementation, inspired by GitHub's Spec Kit. Spec Kitty CLI bootstraps projects with the framework: directory structures, templates, and AI agent integrations. Every command template leads with a discovery interview; the CLI refuses to create specs or plans until the question set is answered.
⚠️ CRITICAL: Load the Project Charter First
Every LLM agent working in this repository MUST read the project charter at .kittify/charter/charter.md at the start of a session, before planning or making changes.
The charter is the binding governance document. It carries rules that are NOT repeated in this file, including:
- Governing principles — single canonical authority, architectural alignment, DDD + tiered rigour, ATDD-first, terminology adherence.
- Quality & Tech-Debt Standing Orders — the nine binding practices (adversarial squad cadence, campsite cleaning, mission tracer files, test-remediation/red-first discipline, architectural gate discipline, canonical sources, git/workflow discipline, mission hygiene, red-main & release discipline).
- Agent operating discipline and collaboration strategy — model routing, profile-loaded delegation, draft-PR-first, the operator merges.
- Governance by workflow action — which rules bind specify/plan/implement/review/merge.
For action-scoped detail, load the doctrine context via spec-kitty charter context --action <name> rather than improvising. If the charter and this file ever disagree, the charter wins — flag the drift instead of picking silently.
⚠️ CRITICAL: Template Source Location
Edit SOURCE files, NOT agent copies!
| What | Location | Action |
|---|---|---|
| SOURCE templates | packs/built-in/missions/mission-steps/ |
✅ EDIT THESE |
| Agent copies | .claude/, .amazonq/, .augment/, etc. |
❌ DO NOT EDIT |
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.
- today Changed · +10 tokens per session 67bbe6b418c5
- 2d ago Changed · +2 lines · +501 tokens per session 3959d74cdc97
- 6d ago First seen · 629 lines · 9,409 tokens per session scan A 88117daa8c6b
spec-kitty AGENTS.md is an instructions file published in the GitHub repository Priivacy-ai/spec-kitty (1,595 stars, last pushed yesterday), licensed MIT. It adds 9,920 tokens to every session, about $0.0496 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 instructions, from other repositories
sdd-pilot sddp-bootstrap.instructions.md
Instructions for attilaszasz/sdd-pilot: These are project-level bootstrap documents. Edit each via its owning skill.
sdd-pilot sddp-governance.instructions.md
Instructions for attilaszasz/sdd-pilot, a project described as: Replace chaotic AI code generation with a disciplined, spec-driven workflow. SDD Pilot enforces structured development phases and quality gates, leveraging AI agents to conduct online research for best practices and plan your architecture before a single…
featherspec knowledge-records.instructions.md
FeatherSpec knowledge record rules — observation, rationale, provenance (thin loader).
featherspec constitution.instructions.md
FeatherSpec constitution editing rules (thin loader).
featherspec plans.instructions.md
FeatherSpec plan-file craft rules (thin loader).
specs-driven-development-spring-angular always-on.instructions.md
Always-on guardrails for spec-driven Spring + Angular development.