By dmltdev
Additive Claude Code skills, agents, and rules: session journaling, learned-correction persistence, prompt expansion, context discipline, and TypeScript/web rule baselines
Evidence-gated QA verifier. Proves a change works by RUNNING it (tests, app/CLI, lint, typecheck) and citing the output — never by reading code and judging. Use to catch incorrect work that passes ordinary review. Read-only; reports a verdict, does not fix.
Runs as a context/session babysitter for persistent orchestrators. Watches phase drift, context decay, verifier failures, prompt quality, and continuity handoffs; launches or recommends fresh-session prompts and phase-gate verification to steer work away from slop. Use for long-lived orchestration, multi-agent runs, validator tuning, or session continuity management.
Concilium reviewer — the maintainability lens. Reviews readability, type design, documentation, and project code-standards (one folded lens). Read-only; reports findings, does not edit.
Concilium reviewer — the scalability lens. Reviews performance hot paths, data-access patterns, resource/cost growth, and concurrency/scaling. Read-only; reports findings, does not edit.
Concilium reviewer — the security lens. Reviews secrets, injection, authz/authn, unsafe sinks, data exposure, and dependency risk (OWASP-class). Read-only; reports findings, does not edit.
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
Use when designing or running long-lived multi-agent orchestration, babysitter/subconscious agents, phase-gate verification agents, context compaction, session handoff, validator tuning, or systems meant to steer AI work away from unusable slop toward a tiny desirable output subset. Authoritative playbook for the babysitter-orchestrator agent and babysat orchestrate-chaos mode.
Commit changes, push to GitHub, and open a PR. Includes quality checks (security, patterns, simplification). Use --quick to skip checks.
Use when you want a multi-lens quality review of a change — convenes four specialized reviewer agents in parallel and returns one merged, severity-ranked, non-blocking report
Use when opening a pull/merge request on GitHub, Bitbucket, or any other remote. Enforces a concise, reviewer-respecting PR shape — body detail scales with change risk, not change size. No "Affected files", no "How to test", no AI boilerplate.
Uses power tools
Uses Bash, Write, or Edit tools
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.

An additive Claude Code library — skills, agents, and rules. Covers what generic workflows don't: session journaling, learned-correction persistence, prompt expansion, context discipline (token budgets, strategic /compact), TypeScript/web rule baselines, plus a handful of safety and lookup helpers.
This is not a workflow framework. It does not enforce phases, gate your work, or auto-inject context. Skills load on demand via the Skill tool. Use what you need, ignore the rest.
/plugin install void-grimoire@claude-plugins-official
/plugin marketplace add dmltdev/void-grimoire
/plugin install void-grimoire@dmltdev
33 skills across 8 domains, plus a 9-agent toolkit and a plugin-local rules/ reference tree. Pick by name:
| Domain | Skills | Description |
|---|---|---|
| void-grimoire | expand-prompt, learn-correction, autoresearch, strategic-compact, orchestrate-chaos, orchestrate-subagents, mission-control, babysitter-orchestrator, unslop, unslop-design | Prompt expansion, self-learning, skill optimization, context discipline, CHAOS multi-agent dispatch (plain + babysat mode), minimal in-session subagent orchestration, mission-control coordination, babysitter playbook, inline slop classifier, product UI unslopping |
| tools | using-herdr, using-codex, using-omp, using-adhd, using-agent-browser, using-chrome-devtools-mcp | External CLI/MCP wrappers — preflight, invocation, fallbacks for herdr, Codex, oh-my-pi, adhd, agent-browser, chrome-devtools-mcp |
| qa | test-with-browser | Evidence-based UI verification — drive a browser against acceptance criteria, capture screenshots/console/network, write a report under .test-results/ |
| workflow | verify-requirements, session-summary, session-usage-summary, session-friction, grill-me, grill-me-fast, grill-with-docs, docs-source-of-truth | Requirements validation, session journaling, AI-usage feedback, append-only friction log for correction events, plan-grilling, fast batched plan-grilling, DDD-shaped docs-as-source-of-truth workflow (replaces OpenSpec-style flows) |
| docs | lookup-docs, index-docs | Documentation search via qmd, with first-class openspec/specs awareness |
| git | enforce-git-safety, commit-push-pr, create-pr | Block destructive git ops; commit/push/PR helper; concise risk-sized PR body rubric |
| npm | enforce-release-safety | Pre-publish safety checks |
| concilium | convene-concilium, verify-and-correct | Multi-lens parallel code review (correctness, security, maintainability, scalability) plus evidence-gated self-correction. Pragmatic, non-blocking. |
Read-on-demand subagents under agents/:
silent-failure-hunter — zero-tolerance review for swallowed errors, empty catch blocks, dangerous fallbacks, broken error propagation.type-design-analyzer — evaluates type design across encapsulation, invariant expression, usefulness, and enforcement.herdr-orchestrator — coordinator for multi-pane parallel work in a herdr workspace. Decomposes goals, spawns worker Claude / omp / adhd instances in sibling panes, monitors, aggregates. Driven by orchestrate-chaos.babysitter-orchestrator — context/session babysitter for persistent orchestrators. Watches phase drift, context decay, verifier failures, and prompt quality; writes verifier/relaunch prompts into a .chaos/interventions.md audit trail. Spawned as a sibling pane by babysat orchestrate-chaos.The concilium — four pragmatic, read-only reviewer lenses dispatched in parallel by convene-concilium, each citing the shared quality-dimensions.md bar:
dev-in-test — correctness, edge cases, silent failures, test presence/quality.dev-in-security — secrets, injection, authz, unsafe sinks, dependency risk (OWASP-class).dev-in-maintainability — readability, type design, documentation, code-standards (one folded lens).dev-in-scalability — performance hot paths, data-access patterns, resource/cost, concurrency.And the verifier that proves work instead of judging it:
adversarial-verifier — evidence-gated QA. Proves a change works by running it (tests, app/CLI, lint) and citing the output; refuses to PASS without execution. Driven by verify-and-correct in a bounded verify → fix → re-verify → escalate cycle.Plugin-local rules/ reference tree under three buckets: common/ (language-agnostic baselines), typescript/ (TS/JS-specific guidance with the matching common baseline inlined), and web/ (frontend/web-specific guidance with the same flattening). Read on demand; never auto-injected.
npx claudepluginhub dmltdev/void-grimoire --plugin void-grimoireUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
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.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.