MCP server Claude CodeCodexCursor +2
MCP server "rag-anything-mcp" as configured in jesse-merhi/rag-anything-mcp. Runs locally from the rag-anything-mcp Python package.
35 1y ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
Instructions for jesse-merhi/skills, covering global agent instructions, communication, implementation design, dependency-first implementation and model turns.
2 yesterday A 1,839 tokens
original MIT
Instructions file
Instructions for jesse-merhi/skills, covering claude global instructions and browser work.
2 yesterday A 146 tokens
original MIT
Agent
Runs a code-centric review in GPT-5.6 Sol High for an explicitly selected dirty tree, branch diff, commit, or PR. Use when review is requested or an active workflow needs a reviewer; do not use merely because code changed or for high-level product and architecture judgment.
2 yesterday A 62 tokens
original MIT
Agent
Top-level Fable coordinator for repository work. Owns product and architecture judgment, routes settled implementation to Opus 5, and routes code-centric review to GPT-5.6 Sol High.
2 yesterday A 45 tokens
original MIT
opus-worker
06Agent
Implements settled, bounded repository changes and production UI. Use proactively after Fable has decided the behavior and direction; do not use for code review or unresolved product and architecture decisions.
2 yesterday A 39 tokens
original MIT
ask-claude
07Skill Claude CodeCodex
Ask Claude from a non-Claude harness through a full ACP session for an independent answer or explicitly scoped implementation.
2 yesterday A 26 tokens
original MIT
ask-codex
08Skill Claude CodeCodex
Ask Codex from a non-Codex harness through a full ACP session for an independent answer or explicitly scoped implementation.
2 yesterday A 29 tokens
original MIT
Skill Claude CodeCodex
Query Jira, JPD, and Confluence through local Rovo Dev MCP, including site IDs, JQL, CQL, and boards.
2 yesterday A 37 tokens
original MIT
cleanup
10Skill Claude CodeCodex
Discover and remove local development artifacts that belong to finished or abandoned work, including worktrees, branches, stashes, processes, watchers, containers, volumes, build outputs, and simulator state. Use when asked to clean up after a task, PR, branch, worktree, or dev environment; not for source-code…
2 yesterday A 72 tokens
original MIT
code-review
11Skill Claude CodeCodex
Run authorized native and independent fix-and-rerun reviews for a PR, branch, commit, or diff.
2 yesterday A 25 tokens
original MIT
Skill Claude CodeCodex
Repeat fresh cold reviews and fixes until the configured clean stop condition.
2 yesterday A 20 tokens
original MIT
Skill Claude CodeCodex
Cold-review a PR, branch, or feature with neutral context, changed-flow coverage, and actionable findings.
2 yesterday A 25 tokens
original MIT
Skill Claude CodeCodex
Create or refine architecture, lifecycle, sequence, trust-boundary, decision, threat-model, SVG, or HTML diagrams that explain system relationships. Do not use technical diagrams as product runtime or UI proof.
2 yesterday A 46 tokens
original MIT
design
15Skill Claude CodeCodex
Route UI design work among production visual design, interaction and motion implementation, read-only motion review, and explicit multi-variant prototyping.
2 yesterday A 29 tokens
original MIT
diagnose
16Skill Claude CodeCodex
Debug bugs, failing tests, regressions, flakiness, or unexpected behavior with reproducible evidence.
2 yesterday A 24 tokens
original MIT
Skill Claude CodeCodex
Confirm actionable review findings, deduplicate root causes, and exclude nits, vague risks, and style notes.
2 yesterday A 26 tokens
original MIT
Skill Claude CodeCodex
Validate web UI with Playwright screenshots, layout checks, responsive states, and reference comparisons.
2 yesterday A 22 tokens
original MIT
Skill Claude CodeCodex
Ground a plan in repo docs, code, Obsidian notes, ADRs, specs, and tickets, then grill its decisions.
2 yesterday A 33 tokens
original MIT
grilling
20Skill Claude CodeCodex
Stress-test a plan, decision, or idea through relentless questions and explicit grill requests.
2 yesterday A 20 tokens
original MIT
handoff
21Skill Claude CodeCodex
Transfer the current work to a fresh full agent session, placing related work beside the current session and unrelated asides separately.
2 yesterday A 27 tokens
original MIT
Skill Claude CodeCodex
Create standalone HTML for complex explanations, code walkthroughs, plans, reports, diagrams, or research.
2 yesterday A 25 tokens
original MIT
Skill Claude CodeCodex
Review architecture for module depth, interfaces, locality, dependencies, and testability.
2 yesterday A 23 tokens
original MIT
just-do-it
24Skill Claude CodeCodex
Take one well-defined, cohesive change from its current implementation or delivery checkpoint through exact-head code review, proof, CI, and a reviewer-ready PR. Use only when the user explicitly invokes this skill.
2 yesterday A 44 tokens
original MIT