developer-tools agents

lgbarn/shipyard

Agent

Part of shipyard

Use this agent when performing brownfield analysis on an existing codebase, onboarding to a new project, generating codebase documentation, or understanding legacy code. Examples: Context: The user wants to understand an existing codebase they are joining or inheriting. user: "I need to understand this existing…

luna-prompts/skillnote

Agent

Part of plugin

Create, refine, and push reusable skills to the SkillNote registry. Use when repeated instructions are detected, user says "create a skill", "save this pattern", "turn this into a skill", or during session retrospective.

BinaryHB0916/iSparto

Agent

Product-technical alignment reviewer. Spawned in a tmux pane via OpenAI Codex CLI with zero inherited context. Cross-provider isolation (GPT-5.5 vs Lead's Claude) layered on top of zero context inheritance. Reads product-spec and tech-spec independently to verify the technical approach actually implements what the…

BinaryHB0916/iSparto

Agent

Compliance audit sub-agent. Reviews session against CLAUDE.md behavioral guidelines — branching conventions, Codex review triggers, Doc Engineer execution, PR workflow, unauthorized operations, plan.md accuracy. Outputs deviation report.

subicura/purplemux

Agent Claude Code

Use this agent when you need to verify code quality after writing or modifying code. This includes running TypeScript type checking to catch type errors before committing. The agent should be called after completing a logical chunk of code implementation.\n\nExamples:\n\n \nContext: User has just finished implementing…

subicura/purplemux

Agent Claude Code

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

AgriciDaniel/claude-code-essentials-vs-code

Agent

Research codebase thoroughly.

AgriciDaniel/claude-code-essentials-vs-code

Agent

Security-focused code analysis.

AgriciDaniel/claude-code-essentials-vs-code

Agent

Generate comprehensive tests.

0xmariowu/AgentLint

Agent

Part of agent-lint

Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…

LeeJuOh/claude-code-zero

Agent

Part of notebooklm-connector

Queries NotebookLM notebooks in Chrome to extract responses. Use when the orchestrating skill provides a NotebookLM URL and question. The notebooklm-manager skill resolves notebook names to URLs before invoking this agent.

LeeJuOh/claude-code-zero

Agent

Part of vision-powers

Review a generated report for narrative coherence, internal contradictions, and unsupported assumptions — with no access to source data or analysis context. Delegated by the report generation workflow as an optional quality gate.

LeeJuOh/claude-code-zero

Agent

Part of vision-powers

Analyze functionality, architecture, dependencies, and quality of agent plugin components (Claude Code). Delegated by the plugin-visual skill.

Obedience-Corp/festival

Agent

Festival task execution specialist. Use when working through festival tasks, marking completion, committing with traceability, managing task state (completed/blocked/reset), and advancing through sequences. Follows the fest next → work → complete → commit loop.

Obedience-Corp/festival

Agent

Festival planning specialist. Use when creating new festivals, designing phase/sequence/task structure, choosing festival and phase types, scaffolding from plans, and validating festival structure. Expert in the Festival Methodology hierarchy and naming conventions.

Obedience-Corp/festival

Agent

Festival is files and two CLIs the agent loop actually touches: fest and camp, installed and kept current by a third tool, festival. It works with any agent that can run shell commands and read files, which is nearly all of them. There is no plugin to install for the core loop: the agent runs fest next, reads the task…

blas0/UnseveredMemory

Agent Claude Code

Part of unsevered-memory

Meta-agent that decomposes tasks, delegates to specialized agents, and maximizes parallel execution. Use for complex multi-step tasks requiring coordination.

primeline-ai/evolving-lite

Agent

Part of evolving-lite

Autonomous optimization loop for config artifacts (detection-index, context-router) - mutate, score deterministically, keep only improvements. Two code-enforced safety gates wrap the loop.

primeline-ai/evolving-lite

Agent

Part of evolving-lite

Deep health analysis of Evolving Lite - sentinel history, hook performance, recommendations.

primeline-ai/evolving-lite

Agent

Part of evolving-lite

Checks Evolving Lite data consistency - memory structure, experience index, config validity.

get-tmonier/argot

Agent

Part of argot

Status: binding (era-13.5 gate G7) Code: crates/argot-core/src/scoring/calibration.rs — runcalibrate (multi-seed median threshold).

get-tmonier/argot

Agent

Part of argot

If any of these files don't exist, proceed silently. Don't flag their absence upfront.

get-tmonier/argot

Agent

Part of argot

Companion to calibration-contract.md, which governs the base statistical scorer. The semantic layer (feature semantic, crate crates/argot-rules-semantic/) calibrates itself separately at fit time; this file records the invariants a contributor must not break.

congmnguyen/claude-code-wsl2-setup

Agent

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences.