Agent Claude Code
The visionary. Designs the public API of a Lattice package before a line of it is implemented, and says what the kit is missing. Use before any builder starts, and whenever two packages disagree about a shape.
16 tagged deterministic, measured the same way as everything else here.
Browse within: canvas 6game-development 6agent-framework 5
Agent Claude Code
The visionary. Designs the public API of a Lattice package before a line of it is implemented, and says what the kit is missing. Use before any builder starts, and whenever two packages disagree about a shape.
Agent Claude Code
The adversary. Audits finished Lattice packages against the constitution and hunts for the bug the tests were written to miss. Reports, and fixes only what its task authorises.
Agent Claude Code
The developer. Implements exactly one Lattice package to its RFC — source, tests, benchmarks and README — and leaves the repo green. Owns only the paths its task names.
Agent
Security vulnerability scanner. Invoked when code crosses a trust boundary: parsing untrusted input, constructing queries or commands from user data, handling credentials or tokens, introducing hardcoded secrets or API keys, enforcing authorization, or modifying security-relevant configuration.
Agent
Advisory multi-LLM craftsmanship council. Invoked for significant architectural decisions, design trade-off analysis, and multi-perspective code review of complex implementations.
Agent
Route queries deterministically with regex patterns. Fuse results with RRF. No LLM in the retrieval loop.
halvrenofviryel/phionyx-research
Agent Claude Code
Fresh-context adversarial review of an uncommitted (or just-committed) diff. Surfaces semantic bugs, version drift, stale references, and contract drift that the implementing session is biased to miss. Read-only — never edits, never commits.
Agent Claude Code
Strict reviewer for monetary values, accounts, and financial constructs. Ledger kernel + review + security. Use for PRs or pre-commit on value diffs.
Agent Claude Code
Investigates one subtopic by crawling URLs and extracting usage-focused code examples.
Agent Claude Code
Formats validated, synthesized research into TUI-ready artifacts and reports progress.
Agent Claude Code
Converts vague topics into structured research plans with subtopics, questions, and seed URLs.