By zreed3
Deterministic ADG governance for Claude Code: deny-by-default tool gating via a PreToolUse hook, bounded-context discipline, and the ADG lane / backlog / audit workflow as slash commands and skills.
Classify the work into a Proofline lane before spending tokens on context or gates.
Get a bounded ADG context packet for a feature instead of reading files blind.
Record verification of a backlog item with explicit, tier-appropriate evidence.
Guide an agent through bounded feature-slice delivery. Use before implementation work that needs reduced rework, scoped context, stop conditions, evidence, and targeted checks.
Validate requirements-to-UX-as-code lineage. Use when features, user stories, use cases, requirements, scenarios, journeys, surface states, RBAC roles, or UX contracts are added or changed.
Maintain standards-linked governance evidence. Use when controls, evidence, maturity scores, security practices, AI governance, privacy, or deliverable auditability changes.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Deterministic, deny-by-default governance for agent-assisted development: a PreToolUse guardrail hook that hard-blocks destructive commands and raw context-hazard reads (and asks on secrets / production / migration), bounded-context discipline, and the ADG lane / backlog / audit workflow exposed as slash commands and skills.
This repository is a lean plugin marketplace — it ships only the installable
plugin. The full Agentic Development Governance platform (the SQL-first backlog, the
scripts/ the workflow commands invoke, AI-security evals, DORA metrics, and the
governance dashboard) lives at
zreed3/agentic-development-platform.
/plugin marketplace add zreed3/adg-governance-plugin
/plugin install adg-governance
hooks/adg-guardrail-hook.mjs) — deterministic, fails closed
for mutating tools and open for reads./adg-classify, /adg-context, /adg-verify.adg-bounded-delivery, adg-requirements-to-ux,
adg-standards-evidence..codex-plugin/) — the same policy and rulebook for Codex.The workflow slash commands shell out to the ADG platform's
scripts/(e.g.scripts/adg-context.mjs). Install this plugin into a repo that has adopted ADG (npm run adg:install) for the full command set; the guardrail hook itself is self-contained.
Author: Zach Reeder (@zreed3), OtterBlock Pty Ltd
Source-available under the PolyForm Noncommercial License 1.0.0.
© 2026 OtterBlock Pty Ltd (ABN 91 614 672 794) — all rights reserved; commercial use
requires a separate license. See LICENSE.
Deterministic ADG governance for Claude Code: deny-by-default tool gating via a PreToolUse hook, bounded-context discipline, and the ADG lane / backlog / audit workflow as slash commands and skills.
npx claudepluginhub zreed3/adg-governance-plugin --plugin adg-governanceHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.