postindustria-tech

postindustria-tech/agentic-toolkit

Plugin Claude Code

Complete toolkit for building agentic systems with LangGraph, DSPy, and modern AI workflows.

postindustria-tech/agentic-toolkit

Plugin Claude Code

Development practices and workflows for quality-driven software engineering. Provides TDD, session completion, molecular task execution with formula-based atom graphs, multi-agent code review, entity test remediation, obligation-driven test derivation, test source-of-truth auditing, and obligation reclassification.…

postindustria-tech/agentic-toolkit

Agent

Researches how a task should be implemented in THIS codebase for the dev-practices execute skill's research atom. Surfaces the existing primitives/components to reuse, the CURRENT (not deprecated) pattern to follow, and the Core Invariant -- recording findings into the beads task. Spawned by the execute skill in a…

postindustria-tech/agentic-toolkit

Agent

Independent adversarial reviewer for the dev-practices execute skill's review atom. Reads a beads task's research findings and implementation plan, rates findings LOW/MEDIUM/HIGH against a fixed rubric, and returns a verdict (ALLLOW / NEEDSREFINEMENT / NEEDSUSERINPUT) that routes the next atom. Spawned by the execute…

postindustria-tech/agentic-toolkit

Agent

Writes the failing regression test (TDD red) for the dev-practices execute skill's write-test atom. Designs the test at the right level -- integration/ E2E through the outer surface by default -- from the plan stored in a beads task. Spawned by the execute skill in a fresh context -- NOT for direct or proactive…

postindustria-tech/agentic-toolkit

Agent

Reviews naming conventions, error message formats, API response shapes, logging patterns, and config access for cross-module consistency. Read-only.

postindustria-tech/agentic-toolkit

Agent

Single-disease, whole-tree codebase scanner for the in-loop targeted review (code-review --targeted). Given ONE disease-pattern spec and ONE lens (dedup | consistency | layering), finds every instance of that ONE pattern across the whole source tree and emits a disposition table (MIGRATE / ALLOWLIST / DEFER).…

postindustria-tech/agentic-toolkit

Agent

Reviews code for logic duplication -- not just textual copy-paste but semantically equivalent code expressed differently. Especially important in AI-assisted codebases where generated code varies syntactically. Read-only.

postindustria-tech/agentic-toolkit

Agent

Reviews whether logic lives in the correct architectural layer: transport wrappers vs business logic vs repositories vs adapters vs services. Read-only.

postindustria-tech/agentic-toolkit

Agent

Reviews code for Pythonic idioms, Pydantic best practices, SQLAlchemy 2.0 patterns, and async correctness. Read-only -- writes findings to output file.

postindustria-tech/agentic-toolkit

Agent

Reviews test quality: are tests testing behavior or just mocking everything? Are assertions meaningful? Is coverage real or illusory? Do mocks verify the right things? Read-only -- writes findings to output file.

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

Launch multi-agent code review covering architecture, security, testing, and consistency. Use when asked to "code review", "review code", "audit code", "multi-agent review", "architecture review", "security review", "testing review", "DRY review", "consistency review", "layering review", "launch review agents"…

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

Execute beads tasks through the full lifecycle using molecular workflow. Use when asked to "execute tasks", "mol-execute", "run molecular workflow", "cook formula", "execute beads tasks", "task execution", "bug triage", "run task pipeline", "walk the molecule", "atom-based execution". Auto-selects formula based on…

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

Write per-obligation behavioral tests with hard quality enforcement. Use when asked to "obligation test", "write obligation tests", "cover obligations", "obligation coverage", "behavioral test derivation", "per-obligation tests", "test from obligations", "fill obligation allowlist", "reduce obligation allowlist"…

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

Reclassify obligation layers (behavioral vs schema) to shrink the test obligation allowlist without writing integration tests. Use when asked to "reclassify obligations", "shrink allowlist", "reclassify schema obligations", "obligation layer reclassification", "reduce obligation allowlist", "move obligations to schema…

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

Fill test stubs in entity test suites systematically. Use when asked to "remediate tests", "fill test stubs", "convert stubs to tests", "entity remediation", "TDD batch", "implement test stubs", "fix entity test suite", "stub remediation", "batch test implementation". Works batch-by-batch with TDD: write failing tests…

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

Merge, consolidate, or integrate branches with per-file semantic conflict resolution and a behavior-level coherence gate. Use when asked to "semantic merge", "merge branches", "merge two branches", "consolidate branches", "integrate branches", "merge these PRs", "combine branches", "resolve merge conflicts"…

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

This skill should be used when the user asks to "end session", "complete work", "landing the plane", "finish session", "git push workflow", "session checklist", "push to remote", "how do I finish my work", "commit and push workflow", "finish coding session", "save my work", "end my work session", or needs to properly…

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

This skill should be used when the user asks to "use TDD", "test-driven development", "write tests first", "red green refactor", "never adjust tests to match code", "fix a bug with TDD", "refactor with tests", "how should I write tests", "test first development", "testing workflow", "write code with tests", "tests…

postindustria-tech/agentic-toolkit

Skill Claude CodeCodex

Audit non-obligation tests to classify each assertion's source of truth. Use when asked to "audit tests", "test audit", "classify test assertions", "test source of truth", "how do we know tests are correct", "test authority audit", "characterization test check", "verify test correctness", "audit test quality source".…

postindustria-tech/agentic-toolkit

Plugin Claude Code

Comprehensive toolkit for building agentic systems using LangGraph and LangChain, with tutorial-grounded patterns and best practices.

postindustria-tech/agentic-toolkit

Agent

Use this agent when LangGraph workflow files are created or modified to validate structure and detect anti-patterns. Examples.

postindustria-tech/agentic-toolkit

Command

Generate a ReAct agent with ToolNode integration and tool calling.

postindustria-tech/agentic-toolkit

Command

Generate FastAPI deployment code for LangGraph workflow with async execution.