Compressed GitNexus playbook for local/Ollama models in Zed — graph-first with minimal context overhead. Use when running qwen/deepseek/llama via Ollama.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add ReidenXerx/bearing --skill bearing-local --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Bearing Local?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/reidenxerx-bearing-local)More formats (shields.io, HTML) on the badges page.
---
name: bearing-local
description: >-
Compressed GitNexus playbook for local/Ollama models in Zed — graph-first with
minimal context overhead. Use when running qwen/deepseek/llama via Ollama.
disable-model-invocation: false
---
# GitNexus — local model playbook
## Rules (short)
1. **Orient:** `query({ search_query, task_context, goal, repo: "__GITNEXUS_REPO__", limit: 3, max_symbols: 8 })`
2. **Symbol:** `context({ name, repo: "__GITNEXUS_REPO__", include_content: false })`
3. **Before edit:** `impact({ target, direction: "upstream", repo: "__GITNEXUS_REPO__", summaryOnly: true })`
4. **Path:** `trace({from, to})` when both endpoints are known
5. **Control/data:** `pdg_query({mode: "controls"|"flows"})` when relevant
6. **Structural:** READ schema → `cypher` (field ACCESSES, overrides, process steps)
7. **Security:** `explain({target})` for taint findings; absence is not proof of safety
8. **Stale:** `npm run bearing:agent-refresh` — never grep instead of refresh
## Zed profile
Use agent profile **Zed + GitNexus** (grep off, gitnexus MCP on). Do not fall back to project-wide grep when profile disables it — use MCP.
## Anti-patterns
- Full-file reads of large sources — Read offset/limit only for edit lines
- Skipping `impact` on "small" edits
- Symbol rename via search-replace — use `rename` dry_run
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.