Automation

awsh for Claude Code: an aw subagent type whose model steps are answered by a session on the local awsh harness daemon, so any harness and any backend the daemon can drive runs as a native Claude Code subagent, streamed live. Also carries the Aither World skills, the aither output style, MCP servers for installed bricks and portable brick hooks.

Compacts a long tool result through the AitherOS decision door before the model reads it: per LINE SHAPE, learned from outcomes, never dropping a traceback or a summary line.

Generate and edit images using Google Gemini, OpenAI GPT Image, xAI Grok Image, and OpenRouter APIs

Claude Mod for cueloop Threads: plan, reply, prototype, diff, review, and refine

State-aware Neovim diff panes

One-pass local response cleanup without agent retries

Asks before Claude edits a file another open chat changed in the last 30 minutes: Proceed, Move to a worktree, or Cancel (/guard)

Compacts when the work moves on from one sub-task to the next instead of when the context window fills, including in the middle of a long turn. Once the context is past a floor, a model judges each step, reading what you asked for and where Claude has got to but never any tool output, for whether the work moves on from a finished piece to another; if it does, taskcut runs Claude Code's own...

After an edit that adds a GitHub Actions step pinned to a tag or a branch, names the commit SHA to write instead, from the GitHub API.

Picks the recommended option of a question that waited unanswered for a set time, so a session you left does not stop. Off until you turn it on.

Runs proof-driven bug hunt rounds with /bughunt: each round proves one bug with a failing command the mod runs itself, fixes it, and proves the fix, and the loop stops on a blocked or unverified round. /bughunt collab runs a read-only scanner, planner and critic in sequence.

Names the uncommitted files to you at the end of each turn, and tells the model at the next prompt to commit each finished piece as it lands.

Parses each JSON, YAML, TOML or .env file an Edit or Write touches, notes a parse error at once instead of at the next build, and says so again when a later edit fixes it.

Hands a skill or command call the current text of its file when the file changed on disk after the session loaded it, and hands the model a rules file or the global CLAUDE.md that changed on disk.

After the model changes a function signature with Edit, adds the callers ripwire finds to the Edit's result, so the model fixes them before the build does.

Asks a council of models about a hard problem, when the model calls its tool or you run /council : Claude models, and Gemini models when gemini-core has a key, answer in parallel, and the model of the session writes one verdict from their answers.

Checks each package the model installs against its registry and OSV.dev, and stops a missing, brand-new, look-alike, outdated or vulnerable one, naming the latest version.

Sends a desktop notification when a question or a plan waits for your answer, and when a turn ends or fails.

After each commit the model makes, adds the doc lines that commit made stale (file:line references, symbol names) to the commit's result, from ripwire doc-drift, and holds each finding open until the doc holds again.

Adds a note to the fifth edit of one file in one turn, so the model re-reads the code path and states the root cause instead of trying again.

Has a small model rate how hard each prompt is and runs that turn and its subagents at the matching effort, within the levels you allow, on the models whose prompt cache survives an effort change.

After each commit the model makes, names the env variables its added lines read that .env.example lacks, with the file and line of each.

Sends one continue prompt after a turn an API error killed, so the half-done work carries on instead of the session going idle, at most 99 times in a row by default.

Remembers which tests failed on which code, and tells the model when a failing test has both passed and failed on the same code, so it runs the test again instead of changing code.