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 agents/itdojp/ae-framework/formal-agentgit clone --depth 1 https://github.com/itdojp/ae-frameworkWhat 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 | $0.00000 | $0.06515 |
| Opus 5 | $0.00000 | $0.03257 |
| Sonnet 5 | $0.00000 | $0.01303 |
| Haiku 4.5 | $0.00000 | $0.00651 |
Grade A, and why
formal-agent 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 yesterday.
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 — 988 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Formal Agent - Phase 2 of ae-framework
Historical document / 履歴文書: This page preserves the retired PoC interface, including
enableModelCheckingandmodel_check, for historical context only. Those paths did not constitute actual checker execution and are not current Assurance evidence. Usedocs/quality/formal-runbook.mdfor the current scaffold/execution boundary. / このページは廃止済み PoC interface を履歴として保存しています。enableModelCheckingとmodel_checkは実 checker execution または現在の Assurance Evidence ではありません。現行境界はdocs/quality/formal-runbook.mdを参照してください。
English
The Formal Agent is a critical component of the ae-framework that bridges Phase 1 (Intent) and Phase 3 (Tests) by converting requirements into formal, verifiable specifications. It provides comprehensive capabilities for generating, validating, and model-checking formal specifications across multiple notations and formats.
Overview
The Formal Agent transforms natural language requirements into mathematically precise specifications that can be validated, verified, and used to generate tests. It supports multiple formal specification languages and provides integrated validation and model checking capabilities.
Key Capabilities
- Formal Specification Generation: TLA+, Alloy, Z notation
- API Specification Creation: OpenAPI, AsyncAPI, GraphQL schemas
- State Machine Generation: FSM definitions with invariants
- Contract Specification: Design by Contract (preconditions, postconditions, invariants)
- Property-based Specifications: For property-based testing
- Formal Verification: Model checking and property verification
- Specification Validation: Consistency and correctness checking
- Diagram Generation: UML, sequence, state, class, and component diagrams
Architecture
The Formal Agent consists of two main components:
- Core Agent (
src/agents/formal-agent.ts): The main business logic - MCP Server Wrapper (
src/mcp-server/formal-server.ts): Model Context Protocol server for tool integration
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.
- yesterday First seen · 988 lines · 0 tokens per session scan A 70901d7811f2
formal-agent is an agent published in the GitHub repository itdojp/ae-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,515 tokens. 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 2026-08-31.
Other agents, from other repositories
playwright-test-generator
Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…
playwright-test-healer
Use this agent to debug and fix failing SigNoz E2E Playwright tests. Examples — Context: A spec is red. user: 'tests/e2e/tests/dashboards/list.spec.ts is failing, fix it' assistant: 'Using the healer agent to debug each failing scenario and adjust the spec.' Context: After a frontend change a previously-green spec…
playwright-test-planner
Use this agent to create a comprehensive E2E test plan for a SigNoz frontend feature. Examples — Context: A new feature has shipped and we need test coverage. user: 'Plan E2E tests for the alerts list page' assistant: 'I'll use the planner agent to read the relevant frontend source, navigate the page in a real…
codex
Production OpenAI-Codex-capable rootfs/initramfs.
claude
Production Claude-capable rootfs/initramfs.
doc-style
Markdown documentation prose — RFCs, ADRs, files under docs/, and READMEs — follows the same one-paragraph-per-line rule as commit messages. Write each paragraph on a single line; do not hard-wrap prose to a fixed column. The renderer reflows it to the reader's display width, whereas manual mid-paragraph line breaks…