Agent Claude Code
Engage when whether the model declares a vertex at all is the question — an effective ggH/γγH in a renormalisable model. Presence is set by vertices.py, not the card: undeclared ⇒ zero diagrams; a card-zeroed coupling still generates (amp→0). Also: an input that is derived, not external (sm MW; Yukawa ≠ pole mass); a…
Skill Claude Code
Audit this agent system's own harness — its agents, skills, rules, and learned memory — against your past sessions and a corpus of agent-design principles, then recommend structural changes (add / remove / adjust a consultant, skill, or rule). Human-gated: recommends and discusses first, snapshots before editing…
Skill Claude Code
Harden the agent system against past mistakes — point it at evidence of a failure (/ma-reflect ) and it tightens its own behaviour so the mistake does not recur. The lead reads the evidence as a whole, abstracts the failures to general mechanisms, and installs a behavioural discipline for each — on the lead, the…
Skill Claude Code
Periodic tidy pass on the wiki/MEMORY tree at .madagents/wiki/ — structural checks, merge near-duplicates, split overgrown pages, balance the MEMORY/wiki tiers, prune; plus a frontmatter scan sub-operation. Reorganizes already-recorded content; it does not source-walk, run MadGraph, or author new principles.…
Skill Claude Code
Record a finding into your own wiki/MEMORY, or consolidate your notes. Invoke to cache something you source-walked for THIS input that is non-obvious and worth a future dispatch (signal = genuine learning, NOT "might be useful"); or to create / extend / supersede a page, merge / split / generalize across pages, or…
Skill Claude Code
Heavy adversarial verification of an assembled MadGraph simulation-spec — an independent, slice-routed claim panel plus a runtime probe that checks the setup by running it, with bounded revision. Use ONLY when the user explicitly asks for deep verification ("verify deeply", "go deep", "check carefully"). Do not…
Skill Claude Code
Adversarial runtime probe of a candidate MadGraph setup — write well-formed expectations about what should be true if the spec is correct, dispatch the ma-probe agent, read per-expectation results. Use any time you're about to run MadGraph to test a candidate — /mg-deep-verify Stage 4, a sanity check after /mg-setup…
Skill Claude Code
Set up MG5aMC for a physics request end-to-end — the default path for any task that builds or configures a MadGraph process or run. Use whenever the deliverable is an MG5 setup: the process line, model, parameters, cuts, scales, LO/NLO mode, decay chains, EFT orders, and so on. Frames the request, classifies the…
Skill Claude Code
Warm-up by phased source scan — study a topic of MadGraph (/mg-study NLO, /mg-study decays) or, bare, each consultant's core area, ahead of any task. Dispatches the relevant consultants to scan their slice in four phases (explore → physics → gaps → cautions), caching facts-with-provenance and flagging…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: