Agent
Low-uncertainty implementation profile for isolated, deterministic changes; use when complexity is 0-1 and acceptance is mechanically verifiable.
334 yesterday A 33 tokens
original MIT
final-gate
26Agent
Narrow adversarial lifecycle-gate profile for aggregate plan or execution risk; use only after ordinary reviews and validations are complete.
334 yesterday A 29 tokens
original MIT
fixer
27Agent
Surgical remediation profile for a verified implementation or review failure; use after the failure is reproduced and a bounded correction can be validated.
334 yesterday A 29 tokens
original MIT
reviewer
28Agent
Independent evidence-first reviewer for designs, plans, completed execution, and PR diffs; use for artifact-specific acceptance, risk, and correctness review by someone other than the author.
334 yesterday A 38 tokens
original MIT
scout
29Agent
Fast read-only discovery profile for locating facts, files, and established patterns; use when a precise bounded question must be answered before dispatch or implementation.
334 yesterday A 32 tokens
original MIT
SessionStart
30Hook
Runs when a session starts, executing session-context.cjs via node. From automagik-dev/genie.
334 yesterday A
tokens not measured
original MIT
architecture
31Skill Claude CodeCodex
Use when reviewing architecture in any codebase — module boundaries, stated design contracts, abstraction depth, error-handling design. Assess by default, apply changes on request; complexity is dependencies plus obscurity, and deep modules win.
334 yesterday A 47 tokens
original MIT
brainstorm
32Skill Claude CodeCodex
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
334 yesterday A 25 tokens
original MIT
code-quality
33Skill Claude CodeCodex
Use when auditing code quality in any codebase — discover and run the repo's real gates (typecheck, lint, dead-code, complexity), judge type discipline and duplication. Assess by default, apply changes on request; the compiler is the first reviewer.
334 yesterday A 54 tokens
original MIT
council
34Skill Claude CodeCodex
Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested.
334 yesterday A 32 tokens
original MIT
docs
35Skill Claude CodeCodex
Dispatch docs subagent to audit, generate, and validate documentation against the codebase.
334 yesterday A 19 tokens
original MIT
dream
36Skill Claude CodeCodex
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
334 yesterday A 27 tokens
original MIT
dx-docs
37Skill Claude CodeCodex
Use when auditing DX, docs, and delivery in any codebase — the 30-minute-contributor test, docs-vs-reality drift, onboarding friction, error-message quality. Assess by default, fix docs on request; docs are judged by use, and every failure is a misfiled or missing Diátaxis quadrant.
334 yesterday A 70 tokens
original MIT
fix
38Skill Claude CodeCodex
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
334 yesterday A 25 tokens
original MIT
genie-hacks
39Skill Claude CodeCodex
Browse, search, and contribute community hacks — real-world patterns for provider switching, teams, skills, hooks, cost optimization, and more.
334 yesterday A 33 tokens
original MIT
genie
40Skill Claude CodeCodex
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
334 yesterday A 53 tokens
original MIT
omni
41Skill Claude CodeCodex
Wire a Genie agent to an Omni channel in one canonical flow — register the host, bind the instance, route chats to a repo, verify the round-trip.
334 yesterday A 35 tokens
original MIT
perf
42Skill Claude CodeCodex
Use when auditing performance in any codebase — cold starts, hot paths, dependency weight, storage query patterns. Assess by default, optimize on request; measure, don't guess, and every number carries the command that produced it.
334 yesterday A 47 tokens
original MIT
qa
43Skill Claude CodeCodex
Use when auditing test quality in any codebase — run the real suite, map coverage topology, rank untested behaviors by risk. Assess by default, write tests on request; tests are a spec, and the question is what change no test would catch.
334 yesterday A 53 tokens
original MIT
quick
44Skill Claude CodeCodex
Ship tiny low-risk changes to dev within one hour.
334 yesterday A 13 tokens
original MIT
refine
45Skill Claude CodeCodex
Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode.
334 yesterday A 25 tokens
original MIT
repo-hygiene
46Skill Claude CodeCodex
Use when auditing repo hygiene in any codebase — file layout, git history, config sprawl, ignore contracts, open-source readiness. Assess by default, fix on request; treats the repository as a product whose users are contributors.
334 yesterday A 51 tokens
original MIT
report
47Skill Claude CodeCodex
Investigate bugs comprehensively — cascade through trace, capture browser evidence, extract observability data, and prepare or explicitly create a GitHub issue with grounded findings.
334 yesterday A 34 tokens
original MIT
review
48Skill Claude CodeCodex
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
334 yesterday A 29 tokens
original MIT