Command
Check fresh evidence before claiming work is complete.
11 24d ago A 9 tokens
original MIT
SessionStart
26Hook
Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From jcwleo/oh-no-harness.
11 24d ago A
tokens not measured
copy · 86% MIT
auto-routing
27Skill Claude CodeCodex
Use when the user asks to enable, disable, or inspect future-session routing guidance; configuration only, not current-turn workflow selection.
11 24d ago A 29 tokens
original MIT
Skill Claude CodeCodex
User-invoked setup action that configures the model and reasoning effort of the installed Oh No Harness Claude Code subagents. Run it explicitly with the slash command; it is never auto-invoked by the model.
11 24d ago A 48 tokens
original MIT
Skill Claude CodeCodex
Use when the user explicitly requests rescue or multi-agent synthesis, or a hard problem remains stalled after ordinary analysis/debugging; not for first-pass planning/debugging or routine implementation.
11 24d ago A 39 tokens
original MIT
Skill Claude CodeCodex
User-invoked setup action that installs the Oh No Harness developer statusline into the user's Claude Code settings. Run it explicitly with the slash command; it is never auto-invoked by the model.
11 24d ago A 45 tokens
original MIT
interview
31Skill Claude CodeCodex
Use when the requested deliverable is vague, broad, ambiguous, requirement-light, or missing users, constraints, or acceptance criteria and needs requirements discovery before implementation planning or execution.
11 24d ago A 38 tokens
original MIT
ralph
32Skill Claude CodeCodex
Use when an approved plan, PRD, spec, ticket, or concrete add/fix/refactor/implement request supplies a usable acceptance contract; explicit test-first intent uses test-driven-development, while unknown root-cause investigation uses systematic-debugging.
11 24d ago A 52 tokens
original MIT
ralplan
33Skill Claude CodeCodex
Use when requirements are sufficiently known but implementation is broad, risky, architecture-sensitive, cross-file, multi-step, or strategy-unclear and needs a plan; not for still-vague discovery or an execution-ready task.
11 24d ago A 47 tokens
original MIT
simplify
34Skill Claude CodeCodex
Use when a behavior-locked changed diff needs post-implementation, pre-review cleanup for reuse, simplicity, efficiency, and appropriate abstraction; not for initial implementation or correctness/root-cause work.
11 24d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Use when an observed failure, regression, flake, unexpected output, or unknown root cause needs investigation; a known-cause execution-ready fix remains Ralph.
11 24d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Use when the user explicitly requests TDD, test-first, or RED-GREEN-REFACTOR, or an already-selected workflow enters its internal TDD gate; ordinary implementation remains Ralph.
11 24d ago A 42 tokens
original MIT
ultrawork
37Skill Claude CodeCodex
Use when the user explicitly delegates autonomous end-to-end delivery across discovery, planning, implementation, and verification; not for a small execution-ready task.
11 24d ago A 34 tokens
original MIT
Skill Claude CodeCodex
Use when an imminent complete, fixed, passing, ready, or safe claim—or final status after edits/tests—needs an evidence gate; not as an implementation substitute.
11 24d ago A 38 tokens
original MIT
MCP server Claude CodeCodexCursor +2
MCP server "ccxt-mcp-server" as configured in jcwleo/ccxt-mcp-server. Runs locally from the ccxt-mcp-server Python package.
8 1y ago A
tokens not measured
original MIT