Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/lucassantana-dev/sharekit/codebase-memorynpx skills add LucasSantana-Dev/sharekit --skill codebase-memorygit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00098 | $0.00933 |
| Opus 5 | $0.00049 | $0.00466 |
| Sonnet 5 | $0.00020 | $0.00187 |
| Haiku 4.5 | $0.00010 | $0.00093 |
Grade A, and why
codebase-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Memory — Knowledge Graph Tools
Backed by the codebase-memory MCP server (~/.local/bin/codebase-memory-mcp, stdio). The server indexes codebases into a persistent tree-sitter AST knowledge graph (158 languages, sub-ms queries). Index a project before querying — see Workflow below.
Graph tools return precise structural results in ~500 tokens vs ~80K for grep.
Quick Decision Matrix
| Question | Tool call |
|---|---|
| Who calls X? | trace_path(direction="inbound") |
| What does X call? | trace_path(direction="outbound") |
| Full call context | trace_path(direction="both") |
| Find by name pattern | search_graph(name_pattern="...") |
| Dead code | search_graph(max_degree=0, exclude_entry_points=true) |
| Cross-service edges | query_graph with Cypher |
| Impact of local changes | detect_changes() |
| Risk-classified trace | trace_path(risk_labels=true) |
| Text search | search_code or Grep |
Exploration Workflow
list_projects— check if project is indexed- If not indexed:
index_repository(path="<repo>")thenindex_status— one-time, milliseconds for average repos get_graph_schema— understand node/edge typessearch_graph(label="Function", name_pattern=".*Pattern.*")— find codeget_code_snippet(qualified_name="project.path.FuncName")— read source
Tracing Workflow
search_graph(name_pattern=".*FuncName.*")— discover exact nametrace_path(function_name="FuncName", direction="both", depth=3)— tracedetect_changes()— map git diff to affected symbols
Quality Analysis
- Dead code:
search_graph(max_degree=0, exclude_entry_points=true) - High fan-out:
search_graph(min_degree=10, relationship="CALLS", direction="outbound") - High fan-in:
search_graph(min_degree=10, relationship="CALLS", direction="inbound")
14 MCP Tools
index_repository, index_status, list_projects, delete_project,
search_graph, search_code, trace_path, detect_changes,
query_graph, get_graph_schema, get_code_snippet, get_architecture,
manage_adr, ingest_traces
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 73 lines · 98 tokens per session scan A e23868ccc441
codebase-memory is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 933 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
adding-new-ai-format
Step-by-step guide for adding support for a new AI editor format to PRPM - covers types, converters, schemas, CLI, webapp, and testing.
agent-builder
Use when creating, improving, or troubleshooting Claude Code subagents. Expert guidance on agent design, system prompts, tool access, model selection, and best practices for building specialized AI assistants.
creating-claude-commands
Expert guidance for creating Claude Code slash commands with correct frontmatter, structure, and best practices.
creating-claude-hooks
Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security requirements, and PRPM package structure.
creating-cursor-rules-skill
Expert guidance for creating effective Cursor IDE rules with best practices, patterns, and examples.
creating-opencode-plugins
Use when creating OpenCode plugins that hook into command, file, LSP, message, permission, server, session, todo, tool, or TUI events - provides plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript event-driven modules.