Indium-AI-Labs/indium-agentkit

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Reviews a diff, branch, or pull request for correctness, security, error handling, performance, and test coverage, verifying each finding before reporting it. Use proactively after code changes and before merging. Read-only.

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Drafts an operational runbook for one service and failure mode from repository evidence: detection, diagnosis, mitigation, recovery, escalation, and rollback limits, with every step labeled by verification status. Use when a service, alert, or procedure lacks a runbook or an existing one no longer matches the code.…

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Reviews a bounded change, endpoint, or integration for exploitable security flaws in authentication, authorization, input handling, secrets, tenant isolation, and LLM or agent features such as prompt injection and over-broad tool permissions. Use proactively before merging security-sensitive changes or to confirm a…

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Designs referentially intact, PII-free, reproducible synthetic data plans from a schema: insertion order over the foreign-key graph with cycle handling, volumes and skewed distributions, constraint-safe field rules, and seeding determinism. Use when seed, fixture, or load-test data is needed, or when an existing seed…

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Verifies completed work against its acceptance criteria by running each of the project's declared lint, type-check, build, and test commands separately and tracing every criterion to evidence. Use after implementation and before reporting a task done, committing, or merging. Read-only.

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Investigates a bug, failing test, or regression by reproducing it, tracing the divergence, and testing competing hypotheses, then returns the root cause with evidence and no fix. Use when the cause of wrong behavior is unknown and evidence gathering can run in parallel with other work. Read-only.

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Researches authoritative external documentation for the exact library, framework, SDK, or API versions a project uses, and returns version-tagged, cited facts to prevent hallucinated APIs. Use when code depends on an API whose signature, behavior, configuration, or version differences are uncertain, or before an…

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Reviews frontend components, state management, rendering boundaries, styling tokens, and bundle impact for correctness and performance risks. Use proactively after UI changes or before merging frontend work. Not for accessibility audits (use the accessibility-checker subagent). Read-only.

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Reviews Dockerfiles, Terraform and other infrastructure-as-code, Kubernetes and Helm manifests, and cloud configuration for security, reliability, and cost risks. Use proactively before merging infrastructure changes or when an environment's posture is in question. Read-only.

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Critiques an implementation plan against the actual codebase for missing steps, wrong assumptions, unhandled risks, scope creep, and unverifiable acceptance criteria, and proposes concrete amendments. Use before executing a non-trivial plan, or when a plan touches unfamiliar code, public contracts, data, or…

Indium-AI-Labs/indium-agentkit

Agent Claude Code

Adds or repairs automated tests at public behavior seams for assigned behavior, including characterization tests before a refactor and regression tests for a fixed bug, and proves they fail and pass for the right reasons. Use when test coverage is missing or a change needs red-green evidence. Edits only assigned paths.