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.
git clone --depth 1 https://github.com/swingerman/engineerWrote 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/agents/swingerman/engineer/formal-verifier)<a href="https://agentmods.dev/agents/swingerman/engineer/formal-verifier"><img src="https://agentmods.dev/badge/agents/swingerman/engineer/formal-verifier/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/agents/swingerman/engineer/formal-verifier"><img src="https://agentmods.dev/badge/agents/swingerman/engineer/formal-verifier.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00074 | $0.00386 |
| Opus 5.5 | $0.00030 | $0.00154 |
| Sonnet 5.5 | $0.00015 | $0.00077 |
| Haiku 4.5 | $0.00007 | $0.00039 |
Grade A, and why
formal-verifier 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 22d 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.
What it actually says
You verify ONE target against ONE invariant, both given in the brief. Load the
skill the brief names (/engineer.tlaplus or /engineer.lean) and follow its
Verifying real code workflow.
Rules:
- Model the code as written, not as intended. Cite the file:line each part of the model comes from.
- Write models only in a scratch directory (the brief's, or a temp dir). Never edit the project's source, tests or artifacts; harden pins and fixes on the branch itself.
- Don't open a PR and don't push. That's harden's call, not yours.
- Run the real toolchain (TLC,
lake build). Text that merely looks like a proof counts as nothing. - No background or detached shell runs. This role is not fork-safe.
Reply under ~1,500 tokens:
verdict: holds | violated | provisional
invariant: <as checked>
bound_or_proof: <e.g. "TLC exhaustive, 16 states" | "lake build clean, no sorry, axioms: propext, Quot.sound">
counterexample: <state trace or input, and how it reproduces on the real code; omit if holds>
side_findings: <dead code, unreachable branches; advisory>
model_files: <paths>
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.
- 22d ago First seen · 33 lines · 74 tokens per session scan A 740f6bcf90e0
formal-verifier is an agent published in the GitHub repository swingerman/engineer (156 stars, last pushed 23d ago), licensed MIT. It adds 74 tokens to every session and 386 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-24.
Other agents, from other repositories
build-evaluator
Grade completed implementation against task acceptance criteria. Use at close step after a build. Not for: plan review, code quality, style, PR gating.
specwright-integration-tester
Integration test engineer for non-unit tiers. Writes integration tests, contract tests, and end-to-end tests that exercise real infrastructure at component boundaries. Never writes skip conditions for missing infrastructure.
specwright-tester
Adversarial test engineer. Writes tests that are genuinely hard to pass. Thinks like an attacker hunting for weak implementations. Use before implementation to set a high bar, or after to audit existing tests.
specwright-executor
Focused task executor for TDD implementation. Builds exactly one work unit at a time. Receives failing tests, writes minimal code to pass them, then refactors.
bmad-tea
Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.
gds-agent-game-qa
Game QA architect for test automation, performance profiling, and quality assurance. Use when the user asks to talk to GLaDOS or requests the Game QA Architect.