developer-tools agents

vericontext/vibeframe

Agent Claude Code

Checks version, generated references, public docs, and metadata sync. Use proactively after version bumps, releases, CLI changes, or doc changes.

anton-abyzov/specweave

Agent

Part of specweave

System Architect for writing plan.md with architecture decisions and component design. Use for increment technical planning during sw:increment orchestration.

anton-abyzov/specweave

Agent

Part of specweave

Increment closer that runs the full sw:done closure pipeline (code-review, simplify, grill, judge-llm, PM validation, sync) in a fresh context. Use when closing increments after task completion to avoid context overflow.

anton-abyzov/specweave

Agent

Part of specweave

Test-Aware Planner for generating tasks.md with BDD test plans. Reads spec.md and plan.md to produce implementation tasks with Given/When/Then scenarios. Use during sw:increment orchestration.

crisnahine/rails-ai-context

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

crisnahine/rails-ai-context

Agent

Issues and specs for this repo live as GitHub issues. Use the gh CLI for all operations.

crisnahine/rails-ai-context

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

pandazki/pneuma-skills

Agent Claude Code

Pneuma Skills amendment specialist — HEAVYWEIGHT Fable-5 engine. Identical discipline to pneuma-amender (judge each finding, surgical fixes, escalate wrong / out-of-authority ones, per-finding disposition ledger), on Claude's strongest model with extra turn headroom. Pick this over pneuma-amender for an amendment…

pandazki/pneuma-skills

Agent Claude Code

Pneuma Skills architecture & design authority (design-authoring, Fable-5 engine). Use proactively for design-level work on any Pneuma layer / contract / mode / backend, present or future — TWO modes: DESIGN (architect a new or extended capability end to end — contracts, layer placement, cross-layer integration…

pandazki/pneuma-skills

Agent Claude Code

Pneuma Skills codebase reconnaissance specialist. Use proactively for any research, investigation, or architecture-understanding task scoped to the pneuma-skills repository. Internalizes the project map and design philosophy (auto-loaded via AGENTS.md and the docs/reference/ chain), so it locates code by layer +…

NEWBIE0413/gemini-gpt-hybrid

Agent

AGGRESSIVE hybrid agent that delegates code generation and modification directly to Gemini and GPT for rapid development and automation.

NEWBIE0413/gemini-gpt-hybrid

Agent

Intelligent hybrid agent that uses Gemini and GPT for analysis and problem identification, then returns insights to Claude for safe code implementation.

azalio/map-framework

Agent Claude Code

Part of map-framework

Evaluates solution quality and completeness (MAP).

azalio/map-framework

Agent Claude Code

Part of map-framework

Reviews code for correctness, standards, security, and testability (MAP).

azalio/map-framework

Agent Claude Code

Part of map-framework

Predicts consequences and dependency impact of changes (MAP).

devcodex-labs/devcodex

Agent

An AI development-rules assistant with an automatic mode that can be enabled explicitly or through configured aliases. It keeps that mode active during a conversation and can proceed automatically in approved paths while enforcing safety rules.

devcodex-labs/devcodex

Agent

An AI assistant for software development that identifies the kind of help needed and routes the request to a matching workflow.

Larens94/codedna

Agent Claude Code

Use this agent when writing new Python files, editing existing Python files, or reviewing recently written code to ensure full compliance with the CodeDNA v0.9 annotation standard. This includes enforcing module docstrings, export contracts, semantic variable naming, function-level Rules docstrings, message…

Larens94/codedna

Agent

Part of codedna-plugin

CodeDNA compliance reviewer. Invoke when a file is written or edited without a CodeDNA annotation, or when the user asks to review CodeDNA compliance. Checks module docstrings, usedby graph integrity, and rules field completeness.

dceoy/speckit-agent-skills

Agent

Generate a custom checklist for the current feature based on user requirements.

dceoy/speckit-agent-skills

Agent

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

dceoy/speckit-agent-skills

Agent

Create or update the feature specification from a natural language feature description.

juspay/neurolink

Agent

Delegation through registerAgentTool is synchronous: the supervising agent's loop blocks on each worker, so four investigations cost four times one investigation and the supervisor sits idle while each runs.

juspay/neurolink

Agent

A long-running agent has to run real commands — a build, a test suite, a linter whose output is the evidence for a finding. The two obvious shapes both fail: bashTool blocks the loop, hands the model a shell, and truncates its own output at 100 KB; a childprocess call with a command string is a shell injection with…