verification agents

80 tagged verification, measured the same way as everything else here.

Browse within: codec 57hardware 57harness 57rtl 57typescript 7

FStarDev

01

FStarLang/FStar

Agent

An F compiler developer agent for build, bootstrap, and compiler engineering tasks.

3.1k 2d ago A 19 tokens original Apache-2.0

wio-candidate-scout

02

workersio/skills

Agent

Read-only WIO subagent for discovering high-value test or workload candidates before implementation. Use during $wio scan, $wio workload, or the discovery stage of $wio test.

159 1mo ago A 46 tokens original MIT

wio-strategy-critic

03

workersio/skills

Agent

Read-only WIO subagent for challenging the selected testing strategy before implementation. Use after candidate selection and before editing test files.

159 1mo ago A 32 tokens original MIT

wio-test-reviewer

04

workersio/skills

Agent

Read-only WIO subagent for reviewing a written test and deciding KEEP, REDO, or REMOVE. Use after $wio test edits a test, or when asked whether a test is valuable.

159 1mo ago A 47 tokens original MIT

acto-builder

05

Corvidae-Coding-Projects/Thermite

Agent Claude Code

Multi-file authorized agent for shipping missing Thermite-toolchain infrastructure that exceeds acto-fixer's single-file scope — a whole component a design doc calls for that does not yet exist (a parser module + its AST consumers; the combinator registry + its lowering hooks; the forge check pipeline + its JSON…

52 24d ago A 122 tokens original MIT

acto-critic

06

Corvidae-Coding-Projects/Thermite

Agent Claude Code

ACToR-style discriminator for the Thermite toolchain. Hunts for divergence between the toolchain's behavior and its authority (the design doc + the conformance corpus + Verus/Kani golden files). ALWAYS writes a FAILING test that pins down the divergence — NEVER writes a fix. Dispatch when a builder/fixer declares…

52 24d ago A 90 tokens original MIT

acto-doc-author

07

Corvidae-Coding-Projects/Thermite

Agent Claude Code

Authors design docs under .design/ / .md that ADAPT to existing Thermite-toolchain code and the thermite-design.md thesis. Each REQ status table is grounded in quoted-code evidence from the current implementation. REQs are classified BINARY — SHIPPED (end-to-end functional with a non-test production consumer + tests +…

52 24d ago A 90 tokens original MIT

babyworm/rtl-agent-team

Agent

Phase 1 research pipeline orchestrator. Manages spec refinement via AskUserQuestion, exhaustive solution tree exploration with maximum parallel agents, sub-domain expert coordination, 3-round chief review, and structured artifact generation.

50 8d ago A 50 tokens original MIT

babyworm/rtl-agent-team

Agent

Phase 1 research team coordination teammate. Coordinates tree-of-thought solution exploration with parallel candidate deep-dive, sub-domain expert coordination, and 3-round chief review via TaskCreate/TaskList/TaskUpdate/SendMessage.

50 8d ago A 55 tokens original MIT

babyworm/rtl-agent-team

Agent

Phase 3 μArch design pipeline orchestrator. Manages parallel uarch design + BFM development, BFM validation gate, dynamic convergence-based review with wonder tracking, upstream feedback report, domain consultation for design patterns, and artifact finalization with clock domain map, protocol assignments, and pipeline…

50 8d ago A 68 tokens original MIT

ana-learn

11

anatomia-dev/anatomia

Agent Claude Code

Ana Learn — quality gardener. Triages findings, promotes rules, routes observations.

32 29d ago A 20 tokens original MIT

ana-setup

12

anatomia-dev/anatomia

Agent Claude Code

Setup orchestrator — calibrates Ana's knowledge with your project's identity, architecture, and values.

32 29d ago A 23 tokens original MIT

ana-verify

13

anatomia-dev/anatomia

Agent Claude Code

AnaVerify — fault-finder and code reviewer. Runs mechanical checks, forms independent findings about the code.

32 29d ago A 25 tokens original MIT

verifier

14

henchmarketing-rgb/sub-zero-skill

Agent

Fresh-context ship-verifier. Receives a win-condition string and a project root, verifies in the real world, returns PASS / FAIL / TOOLGAP with concrete evidence. Never modifies state.

5 3mo ago A 42 tokens original MIT

witness

15

henchmarketing-rgb/sub-zero-skill

Agent

Build the human-reviewable HTML for a /finish-him run. Two modes — "plan" (Mode A audit output) and "execute" (Mode B execution annotations). Captures its own visual evidence via Playwright. Read-only on project state except for the HTML output + asset files.

5 3mo ago A 63 tokens original MIT

verifier

18

AojdevStudio/hermes-satellite

Agent

Generic verifier — decomposes the user's request into atomic claims, validates each independently, reports. Read-only tool surface; no write or edit. Use this when no domain-specific persona fits yet.

2 10d ago A 41 tokens original MIT