spec-kitty AGENTS.md

spec-kitty AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Priivacy-ai/spec-kitty. It costs 9,920 tokens per session, scanned A, original, MIT.

Project instructions for Spec Kitty, a toolkit that uses written specifications and plans before implementation; this approach is called Spec-Driven Development.

In plain words
What is it for?
They are for creating and maintaining specifications, plans, templates, and CLI integrations while keeping development aligned with the project's governing rules.
Why use it?
They require agents to read the project charter and follow its approved templates, terminology, architectural rules, and Git workflow before changing code.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: $ARGUMENTS substitution, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

About the project

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.

Priivacy-ai/spec-kitty · 1,595 stars · on GitHub · spec-kitty.ai

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 instructions/priivacy-ai/spec-kitty/agents-md
Clone the repo
git clone --depth 1 https://github.com/Priivacy-ai/spec-kitty

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

agentmods badge for spec-kitty AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/priivacy-ai/spec-kitty/agents-md.svg)](https://agentmods.dev/instructions/priivacy-ai/spec-kitty/agents-md)
Your own site
<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>
Per session 9,920 This file is loaded in full into every session.
When invoked 9,920 The same file — it is already loaded in full.
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 5.1 $0.09920 $0.09920
Opus 5 $0.04960 $0.04960
Sonnet 5 $0.01984 $0.01984
Haiku 4.5 $0.00992 $0.00992

Measured today against content hash 67bbe6b418c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

AGENTS.md · 631 lines

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

Read the full file on GitHub · 631 lines

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. today Changed · +10 tokens per session 67bbe6b418c5
  2. 2d ago Changed · +2 lines · +501 tokens per session 3959d74cdc97
  3. 6d ago First seen · 629 lines · 9,409 tokens per session scan A 88117daa8c6b

Subscribe to this mod's changes

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.