This is the single agent loop kit: a Claude Code skill (skill/), four scripts, a reference loop, and a runnable example. README.md has the map. Follow examples/support-desk/RUNBOOK.md. During the audit, do not open examples/support-desk/ANSWER-KEY.md, examples/support-desk/single_loop/ or examples/support-desk/example-run/. They give away the verdicts the audit is supposed to reach from the code and traces. The skill belongs in their agent repo, not here. Point them at "Use it on your own system" in README.md. - Run python3 -m unittest discover tests…
10125d agoReviewMountCreate a free account to mount
This is an agent context file. It provides AI coding agents (GitHub Copilot, Claude, Cursor, or any LLM-based development tool) with the information they need to work effectively in your repository. Think of it as onboarding documentation, but optimized for agents: structured, explicit, and maintained alongside your code. WHY DOES IT MATTER? Without an agent context file, every agent session starts from zero. The agent must infer your conventions, guess your architecture, and hope its assumptions match yours. With a…
985mo agoReviewMountCreate a free account to mount
There are no automated tests; verification is manual by running the app and observing ETW events during a Defender scan. A WPF application with three components wired together in Program.cs: EtwListener.cs — subscribes to the Microsoft-Antimalware-Engine ETW provider on a background thread. Correlates Start/Stop Streamscanrequest events using ActivityID (Guid), calculates scan duration, and emits EventInfo records via a reactive Subject<EventInfo>. Plotter.cs — subscribes to the IObservable<EventInfo> stream. Accumulates durations per-process per-second in a ConcurrentDictionary, then a DispatcherTimer fires every second…
973mo agoReviewMountCreate a free account to mount
The worldwide gem provides internationalization and localization APIs for Ruby, including address validation/formatting, currency handling, date/time formatting, region/country data, phone validation, and more. It also includes a TypeScript/JavaScript package at…
9713mo agoReviewMountCreate a free account to mount
For agents working on the SDK. To use an SDK, see README.md and the SDK's own README.md. The one client-code rule is in the last section. One Rust core (rust/sdk/), exposed through several bindings; two SDKs do not use it. Run from the SDK directory.
9511d agoReviewMountCreate a free account to mount
C++ wrapper around the Rust core via the C FFI library (rust/ffi/zerobus.h). Like Go, it consumes the C FFI directly; unlike Go there is no GC, so resource management is RAII and errors are reported by throwing zerobus::ZerobusException. The public headers never include zerobus.h; they hold opaque, forward-declared FFI handles. Only src/ includes the generated C header, keeping the C FFI an implementation detail of the SDK. Run from cpp/: - make build — Configure (CMake) and build the SDK,…
9511d agoReviewMountCreate a free account to mount
Go wrapper around the Rust core via cgo and the C FFI library. When writing or reviewing client/example code, follow the idiomatic async flow. IngestRecordOffset() and IngestRecordsOffset() (on ZerobusStream), as well as IngestBatch() (on ZerobusArrowStream), return as soon as the record is queued; the SDK sends it and tracks its acknowledgment in the background. - Ingest in a loop, then call Flush() to confirm durability — once for a bounded batch, or periodically for a long-running stream. - Acks are…
9511d agoReviewMountCreate a free account to mount
Java wrapper around the Rust core via JNI. Ingestion is asynchronous. ingestRecordOffset() (and ingestRecordsOffset()) return as soon as the record/batch is queued — the SDK sends it and tracks its acknowledgment in the background. - Idiomatic flow: ingest in a loop, then call flush() once (after a bounded batch, or periodically for a long-running stream) to confirm durability. Equivalently, call waitForOffset() on the last returned offset — acks are ordered, so confirming the last offset confirms every prior record. -…
9511d agoReviewMountCreate a free account to mount
Python wrapper around the Rust core via PyO3 and maturin. When writing or reviewing client code that uses this SDK, follow the cross-SDK performance flow from the root CLAUDE.md: - Idiomatic flow: ingest in a loop with ingest_record_offset(), or prefer ingest_records_offset() for bulk data, then call flush() once to confirm durability. ingest_record_offset() returns as soon as the record is queued; the SDK sends it and tracks its acknowledgment in the background. Do not feature ingest_record_nowait() in examples: it spawns a…
9511d agoReviewMountCreate a free account to mount
The core SDK; every Rust-backed SDK binds it: Root CLAUDE.md has the shared rules; this is the Rust-core delta. The JSON/protobuf engine is in sdk/src/stream/grpc/; Arrow Flight is in sdk/src/stream/arrow/ (feature arrow-flight). From rust/: make build / build-release, build-ffi (rebuilds zerobus.h), build-jni, lint, fmt, check. Not obvious: A public-surface change reaches: pub items → Rust consumers; FFI signatures/structs → Go/C++/.NET; JNI methods → Java; PyO3 (python/rust/src/lib.rs) and NAPI (typescript/src/lib.rs) wrap the SDK directly, so refactors can break them via changed…
9511d agoReviewMountCreate a free account to mount
Node.js wrapper around the Rust core via NAPI-RS. When writing or reviewing client code that uses this SDK, prefer the idiomatic ingest-then-flush flow. ingestRecordOffset() (and ingestRecordsOffset()) resolves as soon as the record is queued — the SDK sends it and tracks its acknowledgment in the background. Ingest in a loop, then call flush() once to confirm durability (once for a bounded batch, or periodically for a long-running stream). Each ingest returns the record's offset, and waitForOffset(offset) confirms a specific record…
9511d agoReviewMountCreate a free account to mount
See developer-code-review Operational guidance for commits, issues, MRs, reviews, and repo workflows See developer-operational-guidance Non-optional working requirements for all tasks See developer-working-requirements
8745d agoReviewMountCreate a free account to mount
Guidance for Claude Code when working with this repository. Instructions here override default behavior. Three tenets govern every change in this repo — to code, MCP tools, or prompts. Read docs/PHILOSOPHY.md (mirrored as mcp-steroid://skill/design-philosophy for runtime fetch via steroid_fetch_resource) before proposing any of: Short version: the MCP tool surface (8 today) stays narrow on purpose; the IntelliJ capability surface stays full, exposed via steroid_execute_code plus prompt resources. The strategy page's "Give AI the whole IDE, not just the files" is…
823mo agoReviewMountCreate a free account to mount
This folder holds long-form research, design plans, and the DPAIA arena working log. Read this in addition to the root CLAUDE.md when changing files under docs/ or referencing autoresearch results. The repo's four design tenets — small MCP tool surface; power lives in prompts and direct IntelliJ API usage; devrig is stateless; McpScriptContext is last-resort — are codified in PHILOSOPHY.md (and mirrored at runtime as mcp-steroid://skill/design-philosophy). Autoresearch and prompt- optimization work in this folder is the primary lever for those…
823mo agoReviewMountCreate a free account to mount
Guidance for the :installer-gen module. Instructions here override the root guide for this folder. Read the root CLAUDE.md too (project-wide rules). :installer-gen is build-tooling (no IntelliJ deps). It is the lower of the two distribution generators: :website-gen depends on it. Two responsibilities: 1. JDK detection — resolveAllJdks(cache) (in JdkModel.kt) produces a JdkModel of the JDK 25 builds the installer ships, each field computed from the live vendor sources (nothing hand-pinned). The vendor logic is split per file: CorrettoJdk.kt (Amazon Corretto)…
823mo agoReviewMountCreate a free account to mount
Cross-OS behaviour tests (Windows and Linux) for the script-only, minimal-dependency way an agent plugin launches things — its stdio MCP server and its hooks — validating how Claude Code resolves each candidate script form per OS. Uses mock probe scripts (no real devrig). Live counterpart to jonnyzzz/mcp-steroid#253. The suite is structurally tied to a real Windows/Linux agent (it downloads + runs the OS Claude build). Per the root CLAUDE.md rule, it is gated at the task level: build.gradle.kts → tasks.test…
823mo agoReviewMountCreate a free account to mount
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
AnthropicCLAUDE.md
