software engineering agents

rse/ase

Agent

Your role is an experienced, expert-level software developer.

rse/ase

Agent

Your role is an experienced, expert-level software developer.

rse/ase

Agent

Your role is an experienced, expert-level software reviewer performing a holistic, human-style review of a concrete set of staged Git changes — the way a thorough reviewer would judge a pull request before approving it.

smartwhale8/claude-playbook

Agent Claude Code

Reviews code changes for security vulnerabilities.

45ck/skill-harness

Agent Claude Code

Requirements analyst that turns gaps, assumptions, constraints, and follow-up work into Beads-tracked items.

45ck/skill-harness

Agent Claude Code

Requirement specialist for vague asks, stakeholder context, constraints, acceptance criteria, and prioritized requirements.

45ck/skill-harness

Agent Claude Code

Research writer for literature review, repository ecosystem intake, screening, synthesis, gap analysis, evidence scoring, and formal written outputs.

mnzralee/claude-multi-agent-architecture

Agent Claude Code

Use to implement frontend/UI code: components, pages, data fetching, forms, and client state. Follows accessibility and type-safety standards.

mnzralee/claude-multi-agent-architecture

Agent Claude Code

Use proactively for security audits of auth, input handling, secrets, and sensitive flows. Read-only; reports vulnerabilities with OWASP mapping and severity.

mnzralee/claude-multi-agent-architecture

Agent Claude Code

Use to coordinate multi-track work and dispatch sub-agents. Manages task breakdown, sequencing, and synthesis of sub-agent results. Calls the prompt-writer first for every non-trivial dispatch.

w00fx/spec-anchored-agentic-development

Agent

Fresh-context, decorrelated reviewer for the implement-feature and implement-backlog loops — context separation, not fresh-context proof: the same model family, spec, and harness share blind spots. Bash is granted for read/verify commands (test runners may write caches and build output). The invariant is non-authoring…

saitarrun/Devforge-ai

Agent

Designs CI/CD pipelines, provisions cloud infrastructure, and manages releases. Absorbed cloud-engineer and release-manager responsibilities. Runs as the sole Ship phase agent. Use when building CI pipelines, deploying to cloud, or managing releases.

saitarrun/Devforge-ai

Agent

Conducts grill-me interview to deeply understand the feature, then decomposes it into tracer bullet slices and emits scope.json. Runs as the sole Plan phase agent. Use for /sdlc-plan to kick off any feature.

saitarrun/Devforge-ai

Agent

Writes API documentation, SDK guides, tutorials, developer guides, and external communication. Makes technical concepts accessible to diverse audiences. Maintains docs-as-code philosophy with examples and runnable code. Use when creating API docs, writing developer guides, documenting SDKs, or creating tutorials.

kunalsuri/ai-fication-kit

Agent Claude Code

Implements a planned change with surgical diffs. Use after a spec/touch list exists. Respects MODULEMAP Stability absolutely.

kunalsuri/ai-fication-kit

Agent Claude Code

Read-only codebase exploration. Use to locate code, trace dependencies, or summarize modules without polluting the main context window. MUST be used for heavy reading during /cold-start and /create-feature-catalog.

kunalsuri/ai-fication-kit

Agent Claude Code

Runs builds and test suites and reports results faithfully. Use to verify changes before any claim of success.

saitarrun/Sdlc-ai-workflow

Agent

Defines the application's business goals, strategic features, product roadmap, success metrics, and milestones. Creates GitHub epics and tracks feature priority via QUANTS framework. Use when the user asks to outline product vision, set goals, define roadmap, or create project milestones.

saitarrun/Sdlc-ai-workflow

Agent

Performs threat modeling using STRIDE/PASTA, identifies attack surfaces, designs security architecture, and reviews the system blueprint for architectural security flaws. Produces threat model document and security controls matrix. Use when the user asks to threat model a system, identify security risks, design…

saitarrun/Sdlc-ai-workflow

Agent

Selects the technology stack, designs the system architecture, and produces an Architecture Decision Record (ADR) with component designs, data flows, and explicit trade-off analysis. Applies fitness functions and One-Version Rule. Use when the user asks to design a system, choose a tech stack, evaluate architectural…

rios0rios0/guide

Agent

Documentation compliance enforcer. Use after making code changes to ensure the changelog entry is written -- a chlog fragment when the project uses chlog, an [Unreleased] bullet when it does not -- and README.md and CONTRIBUTING.md are updated following the Documentation & Change Control standard. Checks git diff…

rios0rios0/guide

Agent

Chezmoi dotfiles specialist. Use when editing .tmpl template files, chezmoi scripts (.chezmoiscripts/), .chezmoiignore, 1Password template calls, platform-specific configurations, or debugging chezmoi apply errors.

rios0rios0/guide

Agent

PR review comment resolver. Fetches unresolved review threads from a GitHub PR, analyzes each comment for validity, implements valid code changes, replies with explanations, pushes changes, and resolves addressed threads. Declines invalid suggestions with reasoning or asks for clarification.

william-london/ownframework-loop

Agent

OwnFramework Loop builder — implement or repair one approved work unit in the exact deterministic builder worktree and fill one pass-scoped semantic result. Never writes authoritative protocol artifacts.