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 rules/angrysky56/local-repl-mcp/codegraphgit clone --depth 1 https://github.com/angrysky56/local-repl-mcpWhat 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 | $0.00654 | $0.00654 |
| Opus 5 | $0.00327 | $0.00327 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
codegraph 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.
This is a copy
100% identical to codegraph — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeGraph
This project has a CodeGraph MCP server (codegraph_* tools) configured. CodeGraph is a tree-sitter-parsed knowledge graph of every symbol, edge, and file. Reads are sub-millisecond and return structural information grep cannot.
When to prefer codegraph over native search
Use codegraph for structural questions — what calls what, what would break, where is X defined, what is X's signature. Use native grep/read only for literal text queries (string contents, comments, log messages) or after you already have a specific file open.
| Question | Tool |
|---|---|
| "Where is X defined?" / "Find symbol named X" | codegraph_search |
| "What calls function Y?" | codegraph_callers |
| "What does Y call?" | codegraph_callees |
| "What would break if I changed Z?" | codegraph_impact |
| "Show me Y's signature / source / docstring" | codegraph_node |
| "Give me focused context for a task/area" | codegraph_context |
| "See several related symbols' source at once" | codegraph_explore |
| "What files exist under path/" | codegraph_files |
| "Is the index healthy?" | codegraph_status |
Rules of thumb
- Answer directly — don't delegate exploration. For "how does X work" / architecture / trace questions, answer with 2-3 codegraph calls:
codegraph_contextfirst, then ONEcodegraph_explorefor the source of the symbols it surfaces. Codegraph IS the pre-built index, so spawning a separate file-reading sub-task/agent — or running a grep + read loop — repeats work codegraph already did and costs more for the same answer. - Trust codegraph results. They come from a full AST parse. Do NOT re-verify them with grep — that's slower, less accurate, and wastes context.
- Don't grep first when looking up a symbol by name.
codegraph_searchis faster and returns kind + location + signature in one call. - Don't chain
codegraph_search+codegraph_nodewhen you just want context —codegraph_contextis one call. - Don't loop
codegraph_nodeover many symbols — onecodegraph_explorecall returns several symbols' source grouped in a single capped call, while each separate node/Read call re-reads the whole context and costs far more. - Index lag: the file watcher debounces ~500ms behind writes; don't re-query immediately after editing a file in the same turn.
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 · 39 lines · 654 tokens per session scan A f60cde20259d
codegraph is a cursor rule published in the GitHub repository angrysky56/local-repl-mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 654 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to codegraph, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
java-import-fqn
Java 禁止不必要的全限定类名，必须 import（类名冲突除外）.
debugging
Debugging guidance for the Lineai MCP Server.
diagram
Generate or update a mermaid diagram with the .mmd text as source of truth — defaults to a lightweight zero-dependency Node live-preview server that watches the .mmd and hot-reloads a browser tab (pan/zoom), with a self-hosted mermaid.live editor via Docker, system-viewer SVG, VS Code live preview, or a public…
council
Run a high-stakes decision through a council of five persona-diverse advisors (Contrarian, First-Principles, Expansionist, Outsider, Executor) in parallel, then anonymized peer review, then a chairman synthesis of where they agree, clash, and what to do. Use for real tradeoffs ("council this", "pressure-test this"…
statusline
Turn the usage statusLine on or off (model + context% + 5-hour usage% in every project) without editing config by hand. Runs bin/install-statusline.sh, which installs the script to /.claude and merges the setting without clobbering other keys. Opt-in, global, run once per machine; /statusline off disables it.
add-linter
Add linter configs and GitHub Actions workflows for languages detected in the current repo. Use when the user wants to add linters, set up code quality checks, or after sync-scaffold suggests running /add-linter.