ai-coding-assistant agents

shipfast-ai/shipfast

Agent

Planning agent. Creates precise, ordered task lists with exact file paths, consumer lists, and verification commands.

shipfast-ai/shipfast

Agent

Execution agent. Checks consumers before changing. Builds and verifies per task. Follows existing patterns exactly.

shipfast-ai/shipfast

Agent

Reconnaissance agent. Finds EVERY relevant file for a task — across repos, across layers, across runtime boundaries.

QBall-Inc/clear

Agent

Part of clear

Architect sub-agent for plan-management Track B. Reads requirements and designs phase/workpackage decomposition with dependencies, confidence levels, and milestone checkpoints.

QBall-Inc/clear

Agent

Part of clear

Detail Engineer sub-agent for plan-management Track B. Reads architect output and enriches each workpackage with acceptance criteria, deliverables, verification steps, and notes.

QBall-Inc/clear

Agent

Part of clear

Requirements analyst sub-agent for plan-management Track B. Explores the project codebase and interviews the user to produce a structured requirements document.

Oreo-Mcflurry/claude-gate

Agent

Code reviewer - evaluates code quality, security issues, test coverage, and performance patterns.

Oreo-Mcflurry/claude-gate

Agent

Gate System orchestrator - analyzes project state, determines current phase, and coordinates gate reviews.

Oreo-Mcflurry/claude-gate

Agent

Spec Gate reviewer - evaluates requirements clarity, acceptance criteria, and scope definition.

parasxos/cpp26-adapter

Agent

Part of cpp26-adapter

Reviews a C++ file or diff for C++26 standard compliance. Two-pass: (1) regex anti-pattern check against tools/cpp26lint/patterns.yaml and (2) clang -std=c++2c -fsyntax-only compile check whose diagnostics are classified informationally as bug-vs-compiler-lag using mcpcpp26-refcompilerstatus. Returns a YAML report…

Institut-du-Numerique-Responsable/skill-nr

Agent

Revue accessibilité d'un diff selon le RGAA 4 / WCAG 2.1 AA.

Institut-du-Numerique-Responsable/skill-nr

Agent

Revue écoconception d'un diff selon le RGESN v2 et le GR491.

mryll/skills

Agent

Runs the ste skill's draft-check-fix loop (Steps 3-5) on a cheaper model tier when the ste skill delegates in economy mode. Receives the source text or request, the target language, and the compliance level already chosen by the user; returns the final STE deliverable, the checker report summary, and the TN/TV…

onesimplecode/agent-engineering-standards

Agent

Use this role for implementation work: code, tests, documentation, and ADRs.

onesimplecode/agent-engineering-standards

Agent

Use this role for analysis that may involve sensitive or private data. The role is intentionally constrained.

onesimplecode/agent-engineering-standards

Agent

Use this role after a developer or implementation agent completes a bounded change. The reviewer is a fresh-context quality gate, not a second implementer.

airmcp-com/mcp-standards

Agent Claude Code

Matrix of agent capabilities and their specializations.

airmcp-com/mcp-standards

Agent Claude Code

Guide to spawning agents with Claude Code's Task tool.

airmcp-com/mcp-standards

Agent Claude Code

Complete guide to all 54 available agent types in Claude Flow.

zahardev/aicontext

Agent Claude Code

Generates project documentation from code and AIContext artifacts. Reads the codebase, produces a structured document, writes it to disk.

zahardev/aicontext

Agent Claude Code

Explores the codebase and returns concise summaries of code structure, relationships, and patterns. Use for understanding existing code before making changes.

zahardev/aicontext

Agent Claude Code

Runs backend and frontend tests, analyzes output, and returns only failures and relevant diagnostics. Use after writing or modifying code.

AcKeskin/contexture

Agent

Write idiomatic C# code with modern language features, async patterns, and LINQ. Masters .NET ecosystem, Entity Framework Core, and ASP.NET Core. Use for C# optimization, refactoring, or complex .NET solutions.

AcKeskin/contexture

Agent

Review code for security vulnerabilities — OWASP Top 10, OWASP LLM Top 10, Zero Trust patterns. Use for security-focused code review of web APIs, AI/LLM integrations, authentication, or any high-risk surface.