By ccimen
Hook-enforced standards for Eneo: TDD phase gate (RED/GREEN/REFACTOR), bash firewall against test-edit bypass, wave barrier for parallel subagent coordination, coverage + mutation ratchets, trivial-assertion detector, PR metadata validator, protected-file gates, and pyright typecheck (ported from the legacy checker plugin).
Claude Code marketplace for the Eneo workflow.
eneo-core and eneo-standards/eneo-core:eneo-new "<change>"/eneo-core:eneo-commit "<message>"/eneo-core:eneo-doctor when the environment feels wrongeneo-standards enforce TDD, audit, tenancy, and quality gates| Plugin | Purpose |
|---|---|
eneo-core | Main /eneo-* workflow, subagents, and implementation skills |
eneo-standards | Hooks, validators, helper binaries, and status line |
eneo-findings | Findings workflow and learning extraction |
eneo-review | On-demand /eneo-peer-review plus trigger-gated external review agents |
/plugin marketplace add CCimen/eneoplugin
/plugin install eneo-core@eneoplugin
/plugin install eneo-standards@eneoplugin
/plugin install eneo-findings@eneoplugin
/plugin install eneo-review@eneoplugin # optional
/reload-plugins
Then run:
/eneo-core:eneo-doctor
/eneo-new → edit → /eneo-verify → /eneo-commit → /eneo-ship/eneo-new → /eneo-start → /eneo-verify → /eneo-commit → /eneo-ship/eneo-new → /eneo-discuss → /eneo-plan → /eneo-start → /eneo-verify → /eneo-commit → /eneo-ship → /eneo-recapCommand discovery note: /help mostly shows built-ins. For plugin commands, type / and filter by eneo, or inspect the plugin in /plugin.
/eneo-peer-review/eneo-peer-review is on-demand peer review — invoke it whenever you want a skeptical second pair of eyes on the current diff or task. It is not a hook and never auto-runs.
/eneo-peer-review # review the current diff
/eneo-peer-review "Is this the right ownership boundary?" # plain-language question
/eneo-peer-review plan "Should I implement this slice?"
/eneo-peer-review ready # gates: exits non-zero unless cleared
/eneo-peer-review deep "Challenge tests, API shape, slop." # stronger advisory review
/eneo-peer-review show # last review, reviewer output only
The runner uses Codex if installed, falls back to a fresh-context Claude session, and skips loudly with install hints when neither is available. Iterations are stored under .claude/peer-reviews/<slug>/, and iteration N+1 resumes the reviewer's prior critique by captured session id (never --last). green and ready are aliases that gate the exit code; deep is advisory only — asking for a deeper review never punishes you. See plugins/eneo-review/ for full options and tuning env vars.
/eneo-commit does/eneo-commit is the commit-time review step between technical verification and PR creation.
It keeps the workflow split clean:
/eneo-verify proves the change works/eneo-commit reviews the staged commit/eneo-ship opens the PR with the required metadata and evidenceUnder the hood, /eneo-commit combines:
security-reviewer pass only on risky diffsgit commit, so the repo's own hooks still remain the source of truthThis improves AI-assisted workflows in particular because it separates deterministic enforcement from advisory review instead of mixing both concerns into a single late-stage step.
The harness is intentionally split:
eneo-core owns workflow and subagentseneo-standards owns runtime enforcementeneo-findings owns backlog capture outside the current taskeneo-review stays quiet until /eneo-verify decides a change is risky enough to justify extra review, or until you run /eneo-peer-review for an on-demand architecture/code reviewbrThe harness already has:
.claude/state/current-task.json.claude/phases/ and .claude/recaps/Adding beads/br to the core flow would introduce another state system to reconcile. If the team later wants it, it should be an optional companion workflow, not a required harness dependency.
MIT
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.
npx claudepluginhub ccimen/eneoplugin --plugin eneo-standardsOptional adversarial review: Codex + Gemini reviewer subagents. Trigger-gated — only invoked by /gsd-verify-work when change is tagged audit:schema, tenancy:cross, authz, or LOC > 800. Output compatible with the A/B/AB autoreason tournament.
GitHub Projects findings tracker: /finding to create, list, or grab issues on the eneo project board, plus /finding-teach which extracts session learnings into candidate skills. Reads configurable board IDs and labels from .claude/config/findings.json so municipalities can override without forking the plugin.
Eneo slash commands (/gsd-*, /eneo-env-check, /finding-teach), subagents (tdd-pair, domain specialists, reviewers, learning-extractor, autoreason-judge), and skills (PRD/plan/issues, FastAPI/Pydantic/SvelteKit/audit-log, frontend-design).
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.
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.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use