An open-source agent harness for software work.
This repository also configures its own agents. See what aster tells them →
Skill Claude CodeCodex
Reference for aster.yaml, covering review models, analyzers, focus areas, include/exclude globs, minconfidence, and the permissions block that gates edits. Use when creating or editing aster.yaml, choosing hypothesis/verify models, enabling semgrep or ast-grep, or configuring edit permissions.
Skill Claude CodeCodex
Pipe aster review findings into aster fix to generate and apply patches safely, using review --json, fix --findings-json, dry-run inspection, --apply, and permission gating. Use when asked to auto-fix review findings, apply aster's suggested edits, or build a review-then-fix pipeline.
Skill Claude CodeCodex
Create and execute structured plans for multi-step tasks. Use when the user gives a complex task spanning multiple files, asks for a plan or roadmap, says "break this down", or when a task cannot be completed in a single turn. Also use when the task touches several subsystems or the user wants to review the approach…
Skill Claude CodeCodex
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
Skill Claude CodeCodex
Author skills for aster (and Claude Code): SKILL.md format, frontmatter rules, name/description validation limits, folder layout, scaffolding with aster skills init, and local testing with aster skills add -l. Use when writing a new SKILL.md, fixing a skill that fails to load, or publishing a skills repo.
Skill Claude CodeCodex
Semantic code navigation and fast error checks with the lspdiagnostics, lspreferences, and lspdefinitions tools. Use instead of a full build to check whether an edit broke something, or to find real usages of a symbol.
Skill Claude CodeCodex
Structural search and rewrite with the astgrep and astedit tools. Use when the same pattern appears in many places, when text search matches comments or strings, or when a rename or codemod spans multiple files.
Skill Claude CodeCodex
Running the securityscan tool over the repository before shipping a change. Use when the change touches auth, input parsing, file or network access, or when the user asks for a security check.
Skill Claude CodeCodex
Run Apple Shortcuts on this Mac: list the available shortcuts first, then run one by exact name with optional input. Use when the user wants to trigger a shortcut or asks what shortcuts exist.
Skill Claude CodeCodex
The complete map of what Aster can do and the exact command, flag, slash command, key, or config for each: install and sign-in, the chat TUI, permission modes and rules, every agent tool, review and fix, sessions, memory, config/keys/provider/model, mom.yaml routing, skills, plugins, MCP, web tools, sub-agents and…
Skill Claude CodeCodex
How to demo UI work the way Claude does it, never with throwaway HTML mockups. Build the change in the real webview, verify it in the browser harness, open the live dev server for the user to click through, and run the real test suites. Use when the user asks for a demo, a preview, or "let me see" any UI change in the…
Skill Claude CodeCodex
Isolating work in a linked worktree so another branch can be built, tested, or fixed without touching the current checkout. Use when the working tree is dirty or busy and the task needs a different branch checked out.
Skill Claude CodeCodex
Optimize agent instructions for GPT-6 Astra (Codex). Use when the user mentions Astra, Codex, GPT-6, or asks to audit/rewrite AGENTS.md, skills, or prompts for newer models.
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: