\n\n# Quoin\n\n[](https://discord.gg/6qsdhSPE)\n[](https://www.iso.org/standard/72089.html)\n[](https://github.com/GoogleCloudPlatform/knowledge-catalog/tree/main/okf)\n\n`quoin` is a bundle of **Quire modules**, **agent skills**, and **workflows** for\nauthoring [ISO/IEC/IEEE 29148](https://www.iso.org/standard/72089.html)-aligned software specifications and other technical\ndocuments. It includes prepackaged modules for the spec vocabulary and ideation/authoring/review/planning\nworkflows agents need to write and validate specs directly as Markdown.\n\n`quoin` is built on the [Quire](https://github.com/agent-ix/quire-rs) document standard and validation engine by Agent-IX.\n\n> **Why:** AI agents write code fast but drift from vague intent. Quoin makes the spec the source of truth — your agent authors a validated, traceable spec first, then plans and builds against it.\n\n## How\n\nIn Claude Code, Codex, or the coding agent of your choice:\n\n#### 1. Ideate & Specify\n\nIdeate, then pass your idea to `/specify`. A `specification` containing `user stories`, `functional requirements`,\n`stakeholder requirements`, `non-functional requirements`, and other artifacts will be created.\n\n```\n> /specify an electron app for tracking spice production\n```\n\n#### 2. Spec Review\n\nUse `/spec-review` for agent-assisted review. Multiple analysis tasks will run in parallel and output `Reviews`\nwith `Findings` and suggested fixes.\n\n```\n> /spec-review review the specs for the spice production tracker.\n```\n\n#### 3. Convert to plans\n\nBuild the test `traceability matrix` and `plan`. These skills will break the work down into a `plan`\nwith multiple `tasks`.\n\n```\n> /spec-matrix /spec-to-plan prep the spice tracking app for coding\n```\n\n#### 4. Implement!\n\nCall `/implement-plan` to trigger your coding agent to begin work on the plan.\n\n```\n> /implement-plan build the spice tracking app\n```\n\n#### 5. Gap review\n\n`/gap-analysis` validates that the `UserStory` and `Functional Requirements` are implemented and tested using the `traceability matrix`\nas the guide. `/gap-analysis` will optionally perform a _semantic_ comparison of `spec`, `code`, and `tests` to ensure the\n`plan` is faithfully implemented.\n\n```\n> /gap-analysis\n```\n\n## What's included\n\nThe default module set defines the spec archetypes and domain-object vocabulary.\n\n**Artifact archetypes** — the document types you author:\n\n| Module | Archetypes |\n| ---------------------------------------------------------------------------- | -------------------------------------------------------------------- |\n| [spec-artifacts-iso](https://github.com/agent-ix/spec-artifacts-iso) | `StR`, `FR`, `NFR`, `US`, `IT`, `TC`, `Spec`, `master-requirements` |\n| [spec-artifacts-app](https://github.com/agent-ix/spec-artifacts-app) | `ApplicationSpec`, `MasterRequirements` |\n| [spec-artifacts-process](https://github.com/agent-ix/spec-artifacts-process) | `ADR`, `Plan`, `Task`, `Review`, `Finding`, `TestMatrix`, `Standard` |\n\n**Domain objects** — prefab templates for common objects\n\n| Module | Objects |\n| ---------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| [spec-objects-business](https://github.com/agent-ix/spec-objects-business) | `domain`, `entity`, `value_object`, `aggregate_root`, `nested_entity`, `repository`, `event`, `state_machine`, `process`, `enumeration` |\n| [spec-objects-architecture](https://github.com/agent-ix/spec-objects-architecture) | `api_endpoint`, `data_schema`, `queue`, `action`, `ui_component`, `interface`, `external_contract`, `extension_point`, `binary_format`, `rate_limit` |\n| [spec-objects-enterprise](https://github.com/agent-ix/spec-objects-enterprise) | `capability`, `business_function`, `value_stream`, `decision`, `objective`, `principle`, `kpi` |\n| [spec-objects-operational](https://github.com/agent-ix/spec-objects-operational) | `configuration`, `migration`, `sli`, `slo`, `alert`, `runbook`, `incident`, `deployment` |\n| [spec-objects-security](https://github.com/agent-ix/spec-objects-security) | `auth_flow`, `permission`, `scope`, `role`, `secret`, `encryption_key`, `session_config`, `data_classification`, `trust_boundary`, `audit_event`, `threat`, `control`, `risk`, `vulnerability`, `asset`, `attack_surface`, `policy`, … |\n\n### Agent Skills\n\n- **`specify`** — create or edit spec files using catalog authoring packs + Quire validation\n- **`spec-review`** — review specification for quality, consistency, and completeness\n- **`spec-matrix`** — build/maintain the requirements Test Matrix at 100% coverage\n- **`spec-to-plan`** — convert StR/FR/NFR into a TDD project plan\n- **`spec-ideation`** — loose, exploratory drafting before formal authoring\n- **`spec-app-review`** / **`spec-object-review`** — application-spec and domain-object audits\n- Analysis lenses — focused review passes over a spec:\n - **`spec-integrity-analysis`** — completeness, consistency, and atomicity quality gates\n - **`spec-scope-boundary-analysis`** — system boundaries and responsibility allocation\n - **`spec-dependency-analysis`** — separates enablement work from feature work\n - **`spec-evidence-analysis`** — verification methods and evidence artifacts per requirement\n - **`spec-failure-domain-analysis`** — unstated failure modes, identity confusion, edge cases\n - **`spec-risk-complexity-analysis`** — technical risk and volatility before tasking\n - **`spec-security-analysis`** — applicable security standards and compliance traceability\n\n## Install\n\nInstalling quoin is **two steps**: the CLI (from public npm) and a plugin that adds the\n[skills](#agent-skills) and workflows to your coding agent. The same skill bundle installs\ninto **Claude Code, OpenAI Codex, opencode, and GitHub Copilot** — pick your agent below. No\nAnthropic API key is required — your existing agent subscription is used.\n\n**1. Install the CLIs** (`quoin` plus `ix-flow`, which runs the workflow lifecycle commands):\n\n```bash\nnpm install -g @agent-ix/quoin@latest @agent-ix/ix-flow@latest\n```\n\n**2. Add the plugin to your coding agent:**\n\n\nClaude Code\n\nRun these inside Claude Code:\n\n```text\n/plugin marketplace add agent-ix/quoin\n/plugin install quoin@quoin\n```\n\n\n\n\nOpenAI Codex\n\n```bash\ncodex plugin marketplace add agent-ix/quoin\ncodex plugin add quoin\n```\n\nOr browse and install quoin from the `/plugins` menu inside the Codex TUI.\n\n\n\n\nopencode\n\nInstall the skills with the GitHub CLI (requires `gh` ≥ 2.90.0). `--all` installs\nthe whole bundle; `--scope user` makes it available in every repo:\n\n```bash\ngh skill install agent-ix/quoin --all --scope user --agent opencode\n```\n\n\n\n\nGitHub Copilot\n\nWith the Copilot CLI:\n\n```bash\ncopilot plugin marketplace add agent-ix/quoin\ncopilot plugin install quoin@quoin\n```\n\nOr install the skills with the GitHub CLI (requires `gh` ≥ 2.90.0):\n\n```bash\ngh skill install agent-ix/quoin --all --scope user --agent github-copilot\n```\n\n\n\nEither way, that registers quoin's spec-authoring skills and workflows so you can drive them\nby asking the agent.\n\n## Usage\n\n### skills & workflows\n\nThe primary way users author specs is by asking an agent, which invokes the bundled\n[skills](#agent-skills) and [workflows](#agent-workflows).\n\n### CLI commands\n\nInspect the spec vocabulary and manage installed modules:\n\n```bash\nquoin catalog list\nquoin catalog show FR\nquoin catalog validate\nquoin plugin install path:../spec-objects-business\nquoin plugin list\n```\n\nQuoin also provides rights-safe, project-owned assurance workflows: evaluate a\ngeneric ClauseSet with Quire, account for discharge without a score, render an\nauthored argument with explicit sufficiency decisions, and publish immutable\nexperiment or operational evidence:\n\n```bash\nquire clauses evaluate --module ./modules/widget --authority example.invalid \\\n --set widget-rules --version 1.0.0 \\\n --context product=widget --format json > binding.json\nquoin discharge --binding binding.json --facts discharge-facts.json \\\n --as-of 2026-08-28T00:00:00Z --json\nquoin assurance --argument AA-001 --decisions sufficiency-decisions.json \\\n --as-of 2026-08-28T00:00:00Z\nquoin evidence record-experiment --repo . --input experiment.json\nquoin evidence record-operational --repo . --input operational.json\n```\n\nSee [Assurance workflows](./docs/assurance-workflows.md) for the record shapes,\nexpiry behavior, and the boundary that leaves existing run records unchanged.\n\n## Development\n\n```bash\npnpm install\npnpm run build\npnpm test\npnpm run lint\n```\n\n### Specification\n\nThe technical specification for this library was itself authored with the `spec-artifacts-iso` module — see\n[spec/spec.md](spec/spec.md).\n\n### Evals\n\nEval scenarios live in [spec/evals.md](spec/evals.md) and run through the shared\n[`@agent-ix/cli-agent-evals`](../cli-agent-evals) toolkit. The suite definition is\n[`cli-agent-evals.config.mjs`](cli-agent-evals.config.mjs); quoin-specific fixtures,\nmodule seeding, prompts, and assertions remain under [`evals/`](evals/).\n\nLive runs profile a **real** agent running the skills/workflows and record token,\ntool, and latency metrics from the available transcript. Unit tests cover the\nmechanical CLI behavior.\n\n```bash\nmake evals\nmake evals-all\nnode ../cli-agent-evals/bin/cli-evals.js run \\\n --suite ./cli-agent-evals.config.mjs \\\n --canary \\\n --agent claude \\\n --model sonnet\n```\n\nAgent plugin setup for authoring/running evals from an agent:\n\n```bash\nclaude plugin marketplace add agent-ix/cli-agent-evals\nclaude plugin install cli-agent-evals\n\ncodex plugin marketplace add agent-ix/cli-agent-evals\ncodex plugin add cli-agent-evals\n\ngh skill install agent-ix/cli-agent-evals --all --scope user --agent opencode\ngh skill install agent-ix/cli-agent-evals --all --scope user --agent github-copilot\n```\n\nMinimal integration pattern:\n\n```js\nimport { defineSuite } from \"../cli-agent-evals/dist/index.js\";\nimport { SCENARIOS } from \"./evals/scenarios/index.mjs\";\n\nexport default defineSuite({\n name: \"quoin\",\n rootDir: import.meta.dirname,\n scenarios: SCENARIOS,\n});\n```\n\n## About\n\nquoin is part of the Agent-IX ecosystem built on these core libraries:\n\n- [quire-cli](https://github.com/agent-ix/quire-cli), the static-binary CLI wrapping the Quire engine\n- [ix-cli-core](https://github.com/agent-ix/ix-cli-core), the generic CLI framework\n for Agent IX.\n",
"bytes": 11966,
"sha": "4984a525c6c6207efe65c09d6734429c83ff692f7bfe4cf181bc2bf806fb2f6e",
"repo_slug": "agent-ix/quoin",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/okf_agent_ix_quoin_spec_index_md_91e383bc/readme"
}
![\"Quoin\"](\"logo.png\")
\n