Skill Claude CodeCodex
Route work into the right maestro tier and drive the SPEC/NOTES/VERIFY bundle lifecycle - open, resume, close, recall.
not rated 231
changed 2d ago A SkillSpector: pass 32 tokens
original MIT
231Stars on the repository
13Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Settle unknowns and lock decisions before implementation - pick the mode per unknown (grill, research, prototype, model, wayfind), recall past bundles, walk one fork at a time, record every settled choice with a rationale, and open the bundle only when a Full trigger holds.
not rated 231
changed 2d ago A SkillSpector: warn 62 tokens
original MIT
Skill Claude CodeCodex
Turn filed lessons into the smallest doctrine edit. Use when a Lead assigns improvement work for one target: group pending lessons, make one evidence-linked commit per target, return it for independent challenge, and process each accepted or rejected lesson without deleting history.
not rated 231
changed 3d ago A SkillSpector: pass 0 tokens
original MIT
Skill Claude CodeCodex
Verify and close - cross-check coverage, run the VERIFY table, deliver the verdict, harvest durable lessons into decisions, close the bundle, and never claim remote state from local evidence.
not rated 231
changed 3d ago A SkillSpector: pass 41 tokens
original MIT
maestro-work
05Skill Claude CodeCodex
Drive one accepted implementation unit - smallest falsifiable behavior, minimum edits, evidence that names the real falsifier; red tests only inside a Full bundle.
not rated 231
changed 2d ago A SkillSpector: pass 34 tokens
original MIT
Skill Claude CodeCodex
Decision support and grounded teaching for the human. Invoke when the user signals a message did not land ("wait, what?", "I don't understand", "explain it like I'm five", "which is better?", "I'm not sure") about a question or fork they have been asked, or when they hand over a locked decision, a lesson, or a bundle…
not rated 231 2d ago A SkillSpector: pass 86 tokens
original MIT
Skill Claude CodeCodex
Diagnosis-only investigation of a failure with unknown cause - reproduce, localize, reduce, deliver root cause with evidence. Read-only; an explicit fix request routes by target and tier instead, never here.
not rated 231 2d ago A SkillSpector: pass 46 tokens
original MIT
Skill Claude CodeCodex
Answer an evidence question without touching production code - research external facts against primary sources, build or iterate a disposable prototype (its own bugfixes included), or baseline current repository behavior before deciding or implementing. Use when the question is answerable by reading, building, or…
not rated 231 2d ago A SkillSpector: pass 79 tokens
original MIT
Skill Claude CodeCodex
Turn a decision the user cannot fully answer into a Markdown questionnaire for the one person who can - filled in async, or together over a meeting.
not rated 231
changed 2d ago A SkillSpector: warn 34 tokens
original MIT
Skill Claude CodeCodex
Lead-only council for a hard-to-reverse fork - a neutral brief, sealed independent seats, one premise verifier on unanimity, bounded verifiers, one cross-examination round, a draft-verdict audit, and one binding verdict recorded as a decision with its dissent. Never inside a seat.
not rated 231 2d ago A SkillSpector: pass 65 tokens
original MIT
Skill Codex
Drive a pre-known multi-agent path as a maestro graph - run it by name or from a file you just wrote, pull each agent node with graph next, spawn it as a sub-agent under its maestro- definition, hand the result back with graph result, repeat until the verdict. Author a new graph from the reference when no preset fits.
not rated 231 2d ago A SkillSpector: warn 77 tokens
original MIT
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: