Mexregkan/claude-for-researchers

Mexregkan/claude-for-researchers

Agent Claude Code

Audits a project code THROUGH its Pipeline/ doc — reads a pipeline .md and its code together, then hunts for genuine bugs (correctness, sign/normalization, convention violations) and concrete optimizations (redundant recomputation, missing memoization, complexity blow-ups). Use to review a documented code for…

Mexregkan/claude-for-researchers

Agent Claude Code

Adversarially audits a result against the artifacts that produced it — a script, a log, a data file — and reports the WEAKEST statement those artifacts support. Spawn it with the artifacts and the drafted claim and NOTHING ELSE: no session history, no reasoning, no hoped-for conclusion. Use before a result leaves the…

Mexregkan/claude-for-researchers

Agent Claude Code

Read-only fresh-context adversary for ONE claim of a project document. Given only the bare claim, its location and the evidence paths — never the caller's verdict — it reads the passage, the cited script / log / output and the sibling records, and returns the weakest statement the evidence supports, ranked breaks…

Mexregkan/claude-for-researchers

Agent Claude Code

Read-only first pass over ONE section or line range of a project document (workbook section, strategy map, big picture, handoff, paper, primer) that extracts every checkable claim into ledger rows — id, location, falsifiable statement, type as written, load class, proposed check — and deliberately produces NO…

Mexregkan/claude-for-researchers

Agent Claude Code

Commits and pushes for this project. Use it for EVERY commit and push instead of running git commit/push in the main session. Give it an explicit file list, the target repo, and the commit message. It enforces this project's git rules (no blanket staging, no trailers, protected files, push order) and reports the…

Mexregkan/claude-for-researchers

Agent Claude Code

Decides whether the last round of work actually advanced the project, and specifies the single next task if it did not. Detects loops — the same residual renamed, a weaker check repeated, an escalation after a failed simple case. Spawn it with the last round's result, the audit of that result, and enough recent…