Search everything...

Stats

Actions

Available In

ai-coding-model-guidance

Cross-tool AI-coding model guidance — three strategist agents that help you reason about model selection in the non-Claude coding ecosystems: GitHub Copilot's model picker (completions / chat / coding agent / cloud agent + org model rules), OpenAI Codex (CLI + cloud model lineup, reasoning levels, /model), and xAI Grok (Grok 4.x lineup + the coding-tool surface). Teaches the DURABLE reasoning — task-complexity → reasoning-level → cost-tier → surface — over a single citation-grounded, dated lineup that is the marketplace's freshness anchor for non-Claude model facts. Volatile specifics (prices, context windows, picker availability) carry retrieval dates + a re-verify-at-use rider, and the agents fetch live before quoting. Seam: when the answer is a CLAUDE model or a Claude-app build, escalate to claude-app-engineering/claude-solution-architect — this plugin owns the non-Claude tools. Requires ravenclaude-core@>=0.7.0.

Publisher marketplaceai-coding-model-guidance@ravenclaude · marketplace and plugin share one repository (mcorbett51090/ravenclaude)

npx claudepluginhub mcorbett51090/ravenclaude --plugin ai-coding-model-guidance

Popularity

Stars

Above avg

Med: 0·Avg: 860

Copy clicks

Med: 0·Avg: 2

What's Inside

Agents3

codex-model-strategist

/codex-model-strategist

Use for choosing a model AND reasoning level in OpenAI Codex (CLI + cloud) — GPT-5.5 default, GPT-5.5-Pro for the hard 1%, GPT-5.3/GPT-5-Codex for long autonomous runs, Codex-Spark for inline edits. Reasons complexity → reasoning-level → cost before a SKU. Claude → claude-app-engineering.

copilot-model-strategist

/copilot-model-strategist

Use for choosing a model in GitHub Copilot's picker across surfaces (completion, Chat, coding agent, cloud, mobile), plus org rules and plan-gated availability. Reasons complexity → reasoning → cost → surface, scopes each claim to surface + date. 'Use/build Claude' → claude-app-engineering.

grok-model-strategist

/grok-model-strategist

Use for choosing an xAI Grok model for coding work — Grok 4.3 flagship/default, Grok 4.1 Fast / Grok 4.20 for very-long-context or multi-agent runs — plus the warning that grok-code-fast-1 was RETIRED 2026-05-15 and silently rebills at 4.3 pricing. Seams to claude-app-engineering for a Claude build.

Skills8

lineup-freshness-sweep

/lineup-freshness-sweep

Check the ai-coding-model-guidance knowledge bank for stale entries and produce a prioritized refresh list. Reach for this skill when the knowledge bank's retrieval date is more than 4 weeks old, when a consumer reports a model discrepancy, or on the monthly researcher-reminder cadence.

codex-reasoning-level-calibration

/codex-reasoning-level-calibration

Calibrate the OpenAI Codex reasoning-level dial before recommending a model upgrade. Maps task type, failure mode, and budget to the right reasoning effort level — ensuring developers exhaust the reasoning dial on the current model before paying for a bigger SKU. Domain-specific to the Codex reasoning API.

coding-agent-task-scoping

/coding-agent-task-scoping

Scope an autonomous AI coding agent task so it is well-bounded, recoverable, and matched to the right model tier before it runs. Reach for this skill before any long, unsupervised, or multi-step agentic run — a poorly scoped task on a frontier model is both expensive and hard to debug.

context-window-planning

/context-window-planning

Estimate a coding task's context demand and match it to a model tier whose window is sufficient, without quoting specific token counts that churn monthly. Reach for this skill when the task involves large codebases, long conversation histories, or multi-file agentic runs where context overflow would produce silent truncation errors.

copilot-surface-audit

/copilot-surface-audit

Audit a developer's GitHub Copilot configuration across all surfaces (completions, chat IDE, coding agent, cloud agent, mobile) to identify model gaps, plan mismatches, and org-policy constraints. Reach for this skill before recommending a Copilot model — surface and plan scope the answer, not just the model name.

Stats

Version0.3.12

LanguageHTML

Stars4

Forks1

MaintenanceExcellent

LicenseMIT

Last CommitJul 14, 2026

AddedJul 19, 2026

Actions

View on GitHub View README Plugin Marketplace JSON Homepage

Own this plugin?

Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).

Available In

ravenclaude4

README

🐦‍⬛ RavenClaude

A private Claude Code plugin marketplace — bundled team rules, specialist agents, dispatch playbooks, and templates that travel with you across projects.

🚀 ▶ See what RavenClaude is (pitch.html) — the one-page pitch: the value prop, the proof, and the plugin catalog at a glance. Start here. (Or view the raw HTML source, or download and open locally — no server, no build step.)

🏠 ▶ Open the landing page (index.html) rendered in your browser — the front door: a navigable home with the plugin catalog, the specialist roster, and a comfort-posture starter. Regenerated from the manifests on every release.

(Or view the raw HTML source, or download and open locally — no server, no build step.)

🎛 ▶ Open the RavenClaude dashboard — point-and-click editor for your .ravenclaude/comfort-posture.yaml: set per-tool file, network, shell, and package autonomy across three levels (deny → ask → allow) — per layer (user / local / project) and per individual permission — without editing YAML by hand. (That link is the published, read-only preview; to use it for real — where Save & apply writes your repo's config — run rc dashboard from your project, the one canonical launcher across Claude Code, Copilot CLI, and a bare terminal.)

🖥 Working on this repo? Launch the functional local dashboard (where Save & apply actually writes this repo's config) with one command: bash scripts/open-dashboard.sh. It kills any running dashboard server, starts a fresh one, and opens it in your browser automatically. (VS Code users: a .vscode/tasks.json wired as the default build task — Ctrl/Cmd+Shift+B — runs the same script; .vscode/ is gitignored, so add it locally if you want the keybinding.)

📖 ▶ Open the RavenClaude portal — one self-contained page: browse every plugin, agent, skill, hook, rule, and template in the Marketplace section (with an “I want to…” use-case lookup), tune the comfort-posture Dashboard, and more. Regenerated from the manifests on every release.

(Or view the raw HTML source, or download and open locally — no server, no build step.)

🚀 ▶ First Workflow in 10 Minutes — install → dashboard → one governed multi-agent dispatch → /wrap. The canonical onboarding walkthrough. Start here if you've never used RavenClaude before.

🌐 ▶ Raven Power ↗ — the consulting front door behind RavenClaude. This marketplace is the proof-of-craft; the website is where the engagements live.

Today this marketplace ships 164 plugins:

ravenclaude-core — domain-neutral Team Lead + 14 specialists (architect, coders, reviewers, designer, documentarian, deep-researcher, project-manager, partner-success-manager, prompt-engineer, data-engineer, etc.), plus dispatch playbooks (with a Cross-plugin dispatch section), gates, 43 skills, 16 hooks, templates, and the cross-project contribution-staging loop.
power-platform — 11 Microsoft Power Platform specialists (Power Fx, flows, Power BI, Dataverse, model-driven, PCF, Copilot Studio, Power Pages, admin, ALM, tester), 21 skills, an advisory house-opinions hook covering 8 checks, and the bundled pbix-mcp MCP server.
finance — 7 corporate-finance & FP&A specialists (FP&A analyst, financial modeler, controller, treasury, valuation, audit-prep, board-pack composer), 9 skills, templates, advisory anti-pattern hook.
regulatory-compliance — 12 financial-regulatory specialists (6 function: AML/KYC, regulatory reporting, risk-and-controls, policy & procedure writer, examination prep, Bermuda-insurance; plus 6 jurisdiction: BMA, CIMA Cayman, Bahamas, Channel Islands, UK PRA, US), 10 skills, templates, defensive PII-scrub hook.
web-design — 7 web specialists (web architect, UX, visual, frontend implementer, content strategist, accessibility auditor, performance engineer) with WCAG 2.2 AA/AAA, Core Web Vitals, SEO/AEO, and Fluent + React discipline. 11 skills, templates, advisory web anti-pattern hook.
edtech-partner-success — 6 K-12 EdTech partner-success specialists (partner-success manager, success-playbook designer, learning-analytics analyst, QBR composer, partner-profile curator, FERPA comms translator) with 16 skills and a knowledge bank of operating cadences.

View full README on GitHub

More by mcorbett51090

generative-web-media

4·

AI multimedia for brand & winery sites: a creative brief -> on-brand, web-optimized, license-clean images/video/3D/audio behind a mandatory human curation gate. 4 agents (generation-strategist, web-asset-pipeline-engineer, asset-provenance-guardian, brand-and-accessibility-reviewer) route a brief to the right generator (provider-neutral, Grok-lean for images where competitive; inpaint/outpaint/bg-removal/upscale first-class), turn raw output into AVIF/WebP responsive <picture> markup with LCP/CLS-safe embeds, pin commercial-use licenses (flags the FLUX-dev non-commercial trap; C2PA + a provenance ledger; EU AI Act Art.50 disclosure), and gate every asset on brand-hex/style conformance + WCAG alt text before ship. 6 skills, 4 knowledge docs (Mermaid decision trees; all prices [unverified]), 6 best-practices, 4 commands, 5 templates, 4 scripts. The shared foundation the brand-identity-studio plugin consumes. Declarative fal MCP binding (set FAL_KEY). Requires ravenclaude-core@>=0.7.0.

v0.1.1

mcorbett51090

finance

4·

Corporate finance & FP&A specialist team — FP&A analyst, financial modeler, controller, treasury analyst, valuation analyst, audit-prep specialist, and board-pack composer. Ships 23 skills including the controller-autopilot: a governed close-to-report cycle (GAAP statements, COA mapping, reconciliation auto-match, review→approve→lock workflow, ELT staging, consolidation, per-entity dashboard, close schedules) plus its live-integration tier (multi-currency remeasurement + CTA, OAuth GL connectors + drill-through lineage, warehouse/RLS dashboard, IdP-backed segregation of duties) and a gold-standard NetSuite close (OAuth2 M2M + SuiteQL BS/IS trial balance, COA-draft, tie-out doctor, changed-after-sign-off drift, layperson runbook). 10 templates, a knowledge bank, and 2 advisory hooks (anti-patterns + secrets/PII scan). Inherits ravenclaude-core protocols (Grounding, Structured Output, Cited-Adjudicator).

v0.18.3

mcorbett51090

power-platform

4·1·

Power Platform specialist team — 11 agents (incl. power-platform-tester, power-bi-engineer) and 23 skills, with strong ALM/git coverage for solutions, flows, and PBIP. A house-opinions hook flags 8 §3/§4 violations; the knowledge bank carries production decision trees (PA-flow recovery, Dataverse token-acquisition, PCF React surface, PBI deploy/refresh, custom-connector build-path, PBIR Enhanced infinite-spinner debug + full build reference, DAX silent-zero scoring via the `Domain` pattern, sempy.fabric notebook reference, Power BI Copilot report-readiness, Code Apps connector gotchas, PBIP deployment variables + #839, PBIR reference enrichment, PBIP report fast-solve triage router [MCP-optional]) plus a real-engagement scenarios bank. Bundles the community pbix-mcp server (d0nk3yhm/pbix-mcp, MIT) for .pbix/.pbit read/write/DAX-eval (`pip install pbix-mcp`); documents (not bundles) the official Microsoft Dataverse MCP (CLAUDE.md §9a). Extends ravenclaude-core.

v0.44.7

mcorbett51090

project-management

4·

Project & delivery management team — four specialists across the predictive (PMBOK/PMP) and agile (Scrum/Kanban) tracks and the hybrid between: delivery-lead (charter, schedule, scope/change control, earned value), scrum-master (backlog, sprints, ceremonies, velocity, impediments), risk-and-raid-analyst (scored qual+quant risk, RAID depth, mitigation/contingency, issue triage), and stakeholder-comms-lead (stakeholder register, comms plan, status/exec reporting, escalation memos, steering packs). Deepens — does NOT replace — ravenclaude-core's domain-neutral project-manager (the lightweight RAID/status-hygiene default every plugin routes to); this is the deep PM craft layer. Knowledge: a predictive-vs-agile-vs-hybrid decision tree + a best-practices library. Seams: prose polish → ravenclaude-core/documentarian; system design → architect. Requires ravenclaude-core@>=0.7.0.

v0.4.1

mcorbett51090

ai-red-teaming

4·

AI/LLM red-teaming team — 2 agents (ai-redteam-lead, adversarial-testing-engineer) for the layer answering 'can this AI system be made to do harm, leak data, or exceed its authority — and how do we harden it?': threat modeling + rules of engagement, the attack taxonomy (OWASP LLM Top 10 2025 + MITRE ATLAS), direct vs indirect prompt injection, jailbreaks (roleplay/encoding/many-shot/crescendo), data exfiltration & training-data extraction, agentic tool-abuse / excessive agency, multimodal attacks, and defense-in-depth remediation. Fluent in automated red-team harnesses (PyRIT, Garak, Promptfoo red-team, Giskard) and likelihood×impact severity. 3 skills, a 2-doc knowledge bank (attack-taxonomy decision tree + 2026 patterns), and 2 templates. Distinct from llm-evaluation-engineering (quality-regression eval), trust-and-safety (content-moderation / T&S policy), and security-engineering (app/infra pentest) — the adversarial AI-security layer over model- and agent-based systems. Requires ravenclaude-core@>=0.7.0.

v0.2.0

mcorbett51090

ai-coding-model-guidance

Popularity

What's Inside

Confidence

README

🐦‍⬛ RavenClaude

Similar Plugins

claude-council

fullstack-dev-skills

godot-skills

nature-skills

mattpocock-skills

ecc

More by mcorbett51090

generative-web-media

finance

power-platform

project-management

ai-red-teaming

🐦‍⬛ RavenClaude

More by mcorbett51090

generative-web-media

finance

power-platform

project-management

ai-red-teaming

Popularity

Health & Quality

Similar Plugins

claude-council

fullstack-dev-skills

godot-skills

nature-skills

mattpocock-skills

ecc