FStarDev
01Agent
An F compiler developer agent for build, bootstrap, and compiler engineering tasks.
80 tagged verification, measured the same way as everything else here.
Browse within: codec 57hardware 57harness 57rtl 57typescript 7
Agent
An F compiler developer agent for build, bootstrap, and compiler engineering tasks.
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.
Agent
Read-only WIO subagent for challenging the selected testing strategy before implementation. Use after candidate selection and before editing test files.
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.
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…
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…
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 +…
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.
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.
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…
Agent Claude Code
Ana Learn — quality gardener. Triages findings, promotes rules, routes observations.
Agent Claude Code
Setup orchestrator — calibrates Ana's knowledge with your project's identity, architecture, and values.
Agent Claude Code
AnaVerify — fault-finder and code reviewer. Runs mechanical checks, forms independent findings about the code.
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.
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.
Agent
Dispatch structured work to Hermes via MCP; do not execute locally.
Agent
Read-only satellite verifier for Hermes MCP tasks — decompose, oracle, grade, correct via hermesrespond.
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.