coding-agents commands

manishiitg/coding-agent-loop

Command

Handle character work for this production — designing a new one, reviewing what exists, or revising a character already in use. Figure out which of these I mean from what follows, and if it's genuinely ambiguous, ask.

manishiitg/coding-agent-loop

Command

Re-run the quality checks on the current cut.

manishiitg/coding-agent-loop

Command

Show me the plan before you build it.

saif-shines/doraval

Command

A test command.

saif-shines/doraval

Command

Deploy the application.

AnamKwon/agent-skill-router

Command

Refresh skill inventory and organize skills into category routers.

rudraptpsingh/axon

Command Claude Code

You are evaluating axon — a zero-cloud MCP server that gives AI coding agents real-time hardware awareness. You ARE the agent. axon is YOUR tool.

rudraptpsingh/axon

Command Claude Code

Investigate and fix a bug in axon's signal quality.

rudraptpsingh/axon

Command Claude Code

Run a quick CPU stress test and verify axon detection.

open-latch/latch

Command

Manually trigger a latch compaction for the current session.

open-latch/latch

Command

Seed one decision the user has already ruled out (with its reason), then show latch catch a future agent trying to revive it — latch's decision-continuity guardrail, live.

open-latch/latch

Command

Confirmed toggle for latch Unlatched mode.

beyondeye/aitasks

Command

Explore the codebase interactively, then create a task for implementation.

beyondeye/aitasks

Command

Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.

beyondeye/aitasks

Command

Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.

janaraj/tnl

Command Claude Code

Propose a TNL for a feature, get user approval, then implement against the contract.

dmytri/shipshape

Command

Audit Shipshape installation integrity: completeness, freshness, and coherence across channels and scopes. Read-only.

dmytri/shipshape

Command

Report Shipshape deck state derived from repository signals. Read-only.

naimkatiman/continuous-improvement

Command

Establish git ground truth (branch, status, stashes, worktrees, ahead/behind) before any mutation, halt on protected or destructive operations, then carry the known-good state through a single-concern commit, a push, an open PR, and — after the PR merges — a fast-forward of the default branch. Enforces Law 1 (Research…

naimkatiman/continuous-improvement

Command

Law activator and dispatcher — route the task to the right Law-aligned specialist across continuous-improvement and four vendored upstream skill libraries (Obra superpowers, addy-agent-skills, ruflo-swarm, oh-my-claudecode).

naimkatiman/continuous-improvement

Command

Fan out N parallel sub-agents on isolated worktrees with a shared contract test, produce a comparison report. Driven by report.html horizon item 'Parallel Provider-Migration Agents' — pick winners from real evidence instead of discovering tier limits in production.

krimto-labs/krimto

Command

Show the current state of Krimto memory — total facts, scope breakdown, recent writes, and index health.

davesheffer/hunch

Command Claude Code

Run an audit and record what it finds into Hunch as findings (observed gaps, no code change).

davesheffer/hunch

Command Claude Code

Capture an engineering decision into Hunch's graph via a grilling interview (topic, rationale, rejected alternatives).