lestrrat-ai

lestrrat-ai/claude-code-plugins

Plugin Claude Code

Claude Code plugins by lestrrat.

lestrrat-ai/claude-code-plugins

Instructions file CodexOpenCode

Instructions for lestrrat-ai/claude-code-plugins, covering claude-code-plugins, keep claude code and codex compatible, follow the procedure the running skill specifies and version is the plugin cache key.

lestrrat-ai/claude-code-plugins

Instructions file

Instructions for lestrrat-ai/claude-code-plugins.

lestrrat-ai/claude-code-plugins

Plugin Claude Code

Query the Autodesk Fusion 360 Python API from a pre-compiled reference database.

lestrrat-ai/claude-code-plugins

Skill Claude CodeCodex

Compile or upgrade the Autodesk Fusion 360 Python API reference database from the AutodeskFusion360/FusionAPIReference GitHub repository. Use when the user asks to build, refresh, upgrade, or recompile the Fusion API database, or when query-api reports the database is missing.

lestrrat-ai/claude-code-plugins

Skill Claude CodeCodex

Look up Autodesk Fusion 360 Python API symbols — classes, methods, properties, functions, enum values — from a pre-compiled reference database. Use when the user asks what a Fusion API class/method/property does, what members or signature a Fusion type has, or where a Fusion API name is defined.

lestrrat-ai/claude-code-plugins

Plugin Claude Code

Adversarial review-to-merge pipeline: sweep, verify, fan out, gate, merge.

lestrrat-ai/claude-code-plugins

Skill Claude CodeCodex

Works Gauntlet's durable follow-up queue end to end instead of only listing it. Each open entry is resumed at the step its lifecycle state has already reached: a fresh read-only subagent must reproduce or refute a still-unverified claim, only a corroborated entry is taken up, a separate scoped subagent then authors…

lestrrat-ai/claude-code-plugins

Skill Claude CodeCodex

Gates PRs to merge. A self-looping review-to-merge campaign: existing PRs are adopted into a run (pass PR numbers, or discover this run's labelled PRs), each PR is triaged to a review tier, and a per-PR review gauntlet (tier-dependent fresh, context-isolated SATISFIED verdicts on the whole PR diff, reviewed one at a…

lestrrat-ai/claude-code-plugins

Skill Claude CodeCodex

Evaluate and address GitHub Copilot PR review items for a GitHub pull request. Use when user provides a GitHub PR link and wants Copilot review comments checked, verified, fixed, committed, and summarized. Fetch review items with gh, verify each claim against source/tests before changing code, ask user before making…

lestrrat-ai/claude-code-plugins

Skill Claude CodeCodex

Show Gauntlet's durable follow-up queue through its existing read-only table command. Use when the user asks to list or inspect Gauntlet follow-ups, deferred work candidates, or hidden and rejected follow-up entries.

lestrrat-ai/claude-code-plugins

Skill Claude CodeCodex

Show a Gauntlet campaign ledger through its existing read-only table command. Use when the user asks for campaign status, a campaign ledger, PR state for a named or current campaign run, or hidden, merged, and aborted campaign entries.

lestrrat-ai/claude-code-plugins

Skill Claude CodeCodex

Reports findings; by default makes no changes. A two-pass adversarial code review focused on security, API consistency/symmetry, and user experience. Pass 1 is hostile (assume the worst, surface everything). Pass 2 is a neutral audit that confirms, adjusts, or refutes each finding. Use when the user asks for a…