Agent Claude Code
Resource gatekeeper. Other agents must call the budgeter before launching long-running training, expensive LLM calls, or held-out queries. The budgeter consults resbudgetledger and either approves the request, suggests a smaller request, or halts.
Agent Claude Code
Implementation and experimentation. Can write code, run scripts, and record findings to memory.
Agent Claude Code
Discover and structurally ingest papers from arxiv / openalex. Populates the literature index.
Agent Claude Code
Attempt formal proofs in Lean 4 for stated lemmas. Scope: small statistical identities (sample mean unbiasedness, Chebyshev/Cauchy-Schwarz/Markov/Bonferroni inequalities, simple CLT/MLE statements). Triage gate: only spawn when triageforformalization returns eligible=True.
Agent Claude Code
Read-only literature review, idea generation, and hypothesis proposal. Cannot modify code or files.
Agent Claude Code
Adversarial reviewer of finished manuscripts. Refuses to sign off on central result claims until publication-critical metrics trace back to pinned evidence (empirical checklist) AND theorem claims trace back to an empty diagnostic manifest plus either a Lean verification or an explicit unverified flag (proof…
Agent Claude Code
Independent verification of claims. Read-only access to code; can run verification tools but cannot edit.
Hook Claude Code
Runs before the agent uses a tool for Read, Write, Edit, Bash and Bash tool calls, executing leakage_guard.py and destructive_bash_guard.py via uv with --no-sync (2 commands). From whenpoem/aiscientist.
Hook Claude Code
Runs after a tool call finishes for Bash tool calls, executing provenance_log.py via uv with --no-sync. From whenpoem/aiscientist.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing intervention_pump.py via uv with --no-sync. From whenpoem/aiscientist.
Hook Claude Code
Runs when the agent finishes a response, executing intervention_pump.py and stop_flush.py via uv with --no-sync (2 commands). From whenpoem/aiscientist.
Settings file Claude Code
MCP configuration declaring 7 servers: memory, verify, prove, lean, cockpit, arxiv.
Skill Claude CodeCodex
Rank competing hypotheses or proof skeletons from the complete comparison ledger using a joint batch MAP Bradley-Terry fit and approximate posterior intervals. Use whenever 3 or more candidates compete for the next experiment, or when the user asks which branch currently leads. Do not present the intervals as…
Skill Claude CodeCodex
Diagnose errors, failed tests, crashes, hangs, regressions, suspicious outputs, and unexpected experimental results through reproducible hypothesis-driven debugging. Use whenever a script or system behaves incorrectly, even if the user only says it is broken or pastes an error. Respect diagnosis-only requests…
Skill Claude CodeCodex
Lock a confirmatory falsification target and its fixed multiple-comparison family before observing the confirmatory result. Use before promoting an exploratory finding to a main claim or whenever several related hypotheses need Bonferroni control. Records metric, threshold, family id/size, correction, and seed budget.
Skill Claude CodeCodex
Build and audit a statistical or mathematical proof from proposition capture through skeleton selection, diagnosis, correction, optional empirical checking, and optional Lean reinsurance. Use when the user asks to prove or rigorously derive a proposition, a graph proposition lacks a verified proof, or a reviewer…
Skill Claude CodeCodex
Audit a past pruning or approval decision by creating a counterfactual branch from a saved snapshot without mutating the live graph. Use when the user asks what would have happened under another decision, disputes a paused branch, or wants to inspect an earlier checkpoint.
Skill Claude CodeCodex
Run an end-to-end, auditable research workflow from question framing through literature, competing hypotheses, experiment selection, implementation, verification, and claim handoff. Use whenever the user asks to investigate, compare, test, validate, or establish an empirical research claim, including when they do not…
Skill Claude CodeCodex
Produce or revise research reports, result-bearing Markdown, paper sections, and manuscripts without overstating evidence. Use whenever writing text that reports experimental metrics, statistical conclusions, hypothesis rankings, theorem claims, or research findings. Do not trigger for ordinary README edits…
MCP server Claude CodeCodexCursor +2
MCP server "memory" as configured in whenpoem/aiscientist. Launched with uv tool run --from claudescientist==5.1.4 claudescientist mcp memory.
MCP server Claude CodeCodexCursor +2
MCP server "verify" as configured in whenpoem/aiscientist. Launched with uv tool run --from claudescientist==5.1.4 claudescientist mcp verify.
MCP server Claude CodeCodexCursor +2
MCP server "prove" as configured in whenpoem/aiscientist. Launched with uv tool run --from claudescientist[all]==5.1.4 claudescientist mcp prove.
MCP server Claude CodeCodexCursor +2
MCP server "cockpit" as configured in whenpoem/aiscientist. Launched with uv tool run --from claudescientist==5.1.4 claudescientist mcp cockpit.
MCP server Claude CodeCodexCursor +2
MCP server "arxiv" as configured in whenpoem/aiscientist. Launched with uv tool run arxiv-mcp-server==0.5.0.