code-search skills

220 tagged code-search, measured the same way as everything else here.

Browse within: code-intelligence 62embeddings 56agent-memory 47call-graph 34ai-skills 27bi-temporal-graph 27ai-coding-assistant 16llm-tools 13cocoindex 12code-explorer 12hybrid-search 12grep 11coding-agents 10code-documentation 9

opengrok

73

IcyHot09/opengrok-mcp-server

Skill Claude CodeCodex

Use this skill whenever the user wants to search, navigate, or understand source code in a large codebase — even when they don't say "OpenGrok". Trigger for: finding where a function or class is defined, tracking where something is called or referenced, reading a remote source file, checking who last changed a line…

6 4mo ago A 158 tokens

jarvis-issues

74

jarvis-intelligence/jarvis-index

Skill Claude CodeCodex

Part of jarvis

Report bugs and request features for the jarvis MCP server via GitHub issues. Use when jarvis errors, an index fails, a limitation bites, or to request an improvement.

4 11d ago A 41 tokens

jarvis-setup

75

jarvis-intelligence/jarvis-index

Skill Claude CodeCodex

Part of jarvis

Install and configure jarvis, the local-first structural code intelligence. Use when onboarding, running setup.sh, registering the MCP server, or indexing a repo for the first time.

4 11d ago C 40 tokens

jarvis-use

76

jarvis-intelligence/jarvis-index

Skill Claude CodeCodex

Part of jarvis

Use jarvis structural code intelligence for code structure queries: finding references, go-to-definition, call/type hierarchy, who calls a function, where a symbol is defined, document symbols, natural-language semantic search. Prefer over grep.

4 11d ago A 49 tokens

Driftya/code-meridian

Skill Claude CodeCodex

Plan safer refactors with CodeMeridian by checking graph freshness, exact symbols, impact, tests, duplication, and architecture risk before editing.

4 5d ago A 34 tokens original MIT

Driftya/code-meridian

Skill Claude CodeCodex

Plan focused tests with CodeMeridian by finding relevant test shields, coverage gaps, impacted behavior, and the smallest useful test set before implementation.

4 5d ago A 35 tokens original MIT

Driftya/code-meridian

Skill Claude CodeCodex

Preserve and strengthen the user's independent reasoning during design, strategy, learning, interpretation, hypothesis work, and consequential decisions, and preserve justified durable context with explicit provenance when supported. Use when a task benefits from human-led judgment, model-building, productive…

4 5d ago A 99 tokens original MIT

droste-code-memory

80

lorismascio17/droste-memory

Skill Claude CodeCodex

Use when Claude needs project-aware code memory, MCP context retrieval, repository indexing, causal code search, or Droste CLI workflows. Triggers include requests to index a repo with Droste, configure droste mcp, retrieve graph-aware context, inspect caller/callee relationships, avoid blind file reads, or keep…

3 1mo ago A 75 tokens original MIT

droste-memory

81

lorismascio17/droste-memory

Skill Claude CodeCodex

Use when the chat should save durable knowledge into Droste-Memory, retrieve spatial memory context, pan or zoom the Droste camera, reveal hidden detail layers, or synchronize with the local FastAPI visualizer.

3 1mo ago A 46 tokens original MIT

querying-gdl-data

82

greppable/greppable-cc-plugin

Skill Claude CodeCodex

Part of greppable

Use when working with structured business data records — orders, invoices, products, or any @type records in .gdl files. Covers: filtering records by field values, aggregating data by region/status/category, cross-referencing between record types, extracting specific fields, or converting GDL data to CSV/JSON.…

3 4mo ago A 123 tokens original MIT

greppable/greppable-cc-plugin

Skill Claude CodeCodex

Part of greppable

Use when creating, modifying, or querying .gdld diagram files — architecture flows, sequence diagrams, service topology, and gotcha/anti-pattern records. Also triggers when: investigating how services connect, understanding request flows or data pipelines, assessing blast radius of a change, "how does X connect to Y"…

3 4mo ago A 107 tokens original MIT

greppable/greppable-cc-plugin

Skill Claude CodeCodex

Part of greppable

Use when agent memory from prior sessions could inform current work — choosing between alternatives when past decisions exist, investigating why something was built a certain way, or checking if a problem was already solved. Triggers on: "what did we decide about X", "why did we choose Y", "what do we know about Z"…

3 4mo ago A 145 tokens original MIT

rk-pull

88

Sixz-AI/repo-knowledge

Skill Claude CodeCodex

Part of repo-knowledge

Pull knowledge base from remote and merge into local. Fetches remote state, Agent compares diffs and merges (alias LRU merge for index.md, union dedup for registry.md, newer-cached-date wins for docs). Does NOT push — local only. Use when user says 'pull knowledge', 'sync from remote', 'rk-pull', or on a new machine…

2 3mo ago A 90 tokens original MIT

rk-push

89

Sixz-AI/repo-knowledge

Skill Claude CodeCodex

Part of repo-knowledge

Push local knowledge base to the remote repository. Always fetches remote first, Agent compares diffs and merges (alias LRU merge for index.md, union dedup for registry.md, newer-cached-date wins for docs), then commits and pushes. Retries once on push rejection. Use when user says 'push knowledge', 'sync to remote'…

2 3mo ago A 87 tokens original MIT

rk-search

90

Sixz-AI/repo-knowledge

Skill Claude CodeCodex

Part of repo-knowledge

Search the codebase knowledge base with breadth-first scan and progressive alias learning. Scans ALL project indexes in parallel (including personal), scores candidates by alias/semantic match, then deep-verifies the best match. Use when user asks to find code, understand how something works, or get usage examples.

2 3mo ago A 64 tokens original MIT

root-cause-debugger

91

beingmartinbmc/jambavan

Skill Claude CodeCodex

Part of jambavan

Use when investigating a bug, test failure, or unexpected behavior — before proposing any fix. Enforces observe/compare/hypothesize/fix phases to prevent guess-and-check thrashing. Escalates after 3+ failed fix attempts.

2 27d ago A 55 tokens original MIT

using-jambavan

92

beingmartinbmc/jambavan

Skill Claude CodeCodex

Part of jambavan

Use when Jambavan MCP tools (jambavanindex, jambavancontext, jambavanmemory) are available in the current session, or when you see .jambavan/ in the project root.

2 27d ago A 47 tokens original MIT

vibhishana-niti

93

beingmartinbmc/jambavan

Skill Claude CodeCodex

Part of jambavan

Activate Vibhishana Niti — a severe senior-engineer discipline for shipping the minimum correct change. Use when the user asks for the smallest/simplest fix, a minimal diff, root-cause (not symptom) fixes, when a request seems larger than needed, or when they say "vibhishana niti". Deactivate when they say "normal…

2 27d ago A 82 tokens original MIT

repo-index

94

WangChangxin0809/repo-agent-harness

Skill Claude CodeCodex

Part of repo-agent-harness

Give a repository a code-and-docs graph an agent can query — tree-sitter symbols, import and call edges, doc-to-code edges, ranked by personalized PageRank from whatever the current task touches. Use this when an agent cannot find the relevant code in a large repo, when grep returns hundreds of hits or none, when…

2 3d ago A 108 tokens original MIT

writing-checks

95

WangChangxin0809/repo-agent-harness

Skill Claude CodeCodex

Part of repo-agent-harness

Build the machinery that enforces a convention instead of documenting it — PreToolUse guards that block an action before it runs, CI gates that judge the worktree, selftests that prove a check can turn red, and structural tests that enforce layering. Use this whenever a rule keeps getting violated despite being…

2 3d ago A 105 tokens original MIT

writing-docs

96

WangChangxin0809/repo-agent-harness

Skill Claude CodeCodex

Part of repo-agent-harness

Write or restructure documentation that agents and people actually read — choosing which of the four directories it belongs in (how-to, reference, decisions, exec-plans), knowing what belongs in a failure message instead of a file, and keeping the routing table honest. Use this whenever writing a doc, a runbook, a…

2 3d ago A 141 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: