Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Blind-review critic subagent, spawned by the Writer after a draft exists. Pre-commits evaluation standards from the brief before reading the draft; criticises from three angles; lists the draft's negative universals with where to overturn them. Takes evidence with the same discipline as the Writer, to find…
Agent Claude Code
Use this agent to review a proposed feature or solution against design values before implementation. Evaluates sophistication (depth of understanding), empowerment (serves the user), robustness (handles failure gracefully), ethics (manipulation, accessibility, privacy, sustainability) and explainability (can you…
Agent Claude Code
Static security reviewer for one focus area of a vuln-scan run. Spawn with a focus area, target dir, and scoping facts — not for general delegation.
hybridlabor-api/bdb-dev-optimized-agent-skills
Agent Claude Code
Adversarial review of build-node output against the plan's stated contract, before Shipping runs its automated gate. Modeled on the doubt-driven-development discipline (see .agents/graph.md): reads the artifacts and the contract, never the implementer's claim that it's done, never their reasoning — passing the claim…
Agent Claude Code
Principal-level software architect for architecture reviews, pre-implementation specification reviews, and spec-conformance verification. Use when the user asks to review architecture, evaluate design decisions, audit system boundaries, check for anti-patterns, evaluate whether a specification is ready to be…
Agent Claude Code
Runs a terminal command in this repo (test, typecheck, lint, build, script) without dumping the output into the main context — full log to a file, returns exit code + the literal failures. For the main window's gates: the orchestrator's Build gate per wave and the Verifier's Final gate; a spec-worker runs its own…
Agent Claude Code
Implements features with automatic review cycles. Use for new features or significant changes that benefit from review.
Agent Claude Code
Enterprise-grade Azure environment sweeper — WAF + CAF + Landing Zone + Org Rules + Policy + Resource Graph + Telemetry + Remediation. Run on any scope to produce a prioritised findings report with remediation code.
Agent Claude Code
You are the AgentReady Transformer — an expert agent that deeply analyses existing codebases and generates all scaffolding files needed for AI agents to understand and operate on the repository without hallucinations.
Agent Claude Code
Bounty verification agent. Use when an agent submits a repo link claiming they implemented the loop-starter-kit. Checks the implementation quality and reports pass/fail with specific feedback.
Agent Claude Code
Generate a custom checklist for the current feature based on user requirements.
Agent Claude Code
Leads an end-to-end user task, deciding the next useful action and integrating verified results. Use when one agent owns the final outcome.
Agent Claude Code
Verifies every code block, shell command, build invocation, and API claim in a technical blog post against the real source repositories under /fortran and /python. Invoked by the blog skill during draft and review. Returns a per-claim verdict (verified / BLOCKING) with the discrepancy and a corrected version copied…
Agent Claude Code
A back-end development agent for the server-side parts of an application, including APIs, databases, authentication, and infrastructure. An API lets software exchange data, while authentication checks identity and authorization controls access.
Agent Claude Code
Main coordinator for linked task Bundles and OMP native task operations.
forest6511/claude-code-recipes-v2
Agent Claude Code
A Japanese-language session for reviewing REST APIs, which are web interfaces that programs use to exchange data.
Agent Claude Code
Adversarial quality evaluator. Reviews any artifact (code, tasks, specs, plans, KB docs) against its acceptance criteria, rubric, and KB conventions. Produces the 7-column issue ledger with source and severity tags. Does NOT fix anything; does NOT compute the grade.
Federated-Industrial-Laboratories/agentbus
Agent Claude Code
Adversarial review of work products the reviewer did not build. Reports verified defects separately from suspicions, severity-ranked. Use to verify builds, audits, and releases with an outside eye.
fadhlirahim/claude-starter-kit
Agent Claude Code
Writes vitest tests for tRPC routers, Zod schemas, and React components following project test conventions. Use when new code lacks tests or coverage is requested.
Agent Claude Code
Subagent — designs complete, novel AI skills from researched signals; produces SKILL.md, README.md, and test scenarios.
gmoncor/agentic-engineering-framework
Agent Claude Code
Analiza un problema, evalúa opciones y recomienda una solución con sus trade-offs, sin escribir. Se despacha en el análisis previo a una planificación, o cuando el usuario duda entre enfoques o pide una segunda opinión.
Agent Claude Code
Traces operations end-to-end across service boundaries, verifying return value contracts hold and silent failures don't leave inconsistent state.
Sergei-thinker/claude-code-course-ru
Agent Claude Code
Use this agent when you need to analyze code changes for potential bugs, trace logic flow across multiple files, or investigate suspicious behavior in the codebase. This agent specializes in deep-dive analysis while maintaining a concise summary format to preserve context. Perfect for reviewing recent modifications…
Neftedollar/multiagent-template
Agent Claude Code
Autonomous operations manager — coordinates AI agent roles to execute tasks through PLAN→BUILD→TEST→VERIFY→SHIP pipeline with minimal human involvement.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: