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 agents/elara-labs/code-context-engine/cursorgit clone --depth 1 https://github.com/elara-labs/code-context-engineWhat 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 | $0.00008 | $0.00578 |
| Opus 5 | $0.00004 | $0.00289 |
| Sonnet 5 | $0.00002 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
cursor 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor has built-in codebase indexing, but CCE adds compressed retrieval, cross-session memory, and token savings tracking on top.
Quick setup
cce init # Auto-detects Cursor if .cursor/ exists
cce init --agent all # Explicitly includes Cursor
Files created
.cursor/mcp.json
Registers the CCE MCP server for Cursor's agent mode.
{
"mcpServers": {
"context-engine": {
"command": "cce",
"args": ["serve", "--project-dir", "/path/to/your/project"]
}
}
}
.cursorrules
Contains instructions for Cursor's AI to prefer context_search over raw file reads. The CCE block is wrapped in markers so your own rules are preserved.
Working with Cursor's built-in indexing
Cursor indexes your codebase for its own retrieval. CCE complements this by:
- Compressed context that uses fewer tokens per query (Cursor's index returns full file content, CCE returns relevant chunks with signature compression)
- Token savings tracking so you can measure the cost difference
- Graph-aware retrieval that follows code relationships (imports, calls)
- Cross-session memory that persists decisions across restarts
Both systems run side by side without conflict. Cursor's indexing handles in-editor completions, CCE handles chat/agent queries.
Verify it's working
- Restart Cursor after running
cce init - Open the Composer or Chat panel
- Ask a code question:
Where is the database connection configured?
- Check the tool call output. If Cursor used
context_search, CCE is active - Run
cce savingsin your terminal to see token savings
Troubleshooting
Cursor ignores CCE and reads files directly
Cursor may prefer its built-in indexing for some queries. Check that .cursorrules contains the CCE instructions block. The instructions tell Cursor to prefer context_search, but Cursor's own heuristics may override this for simple lookups.
"cce: command not found"
Cursor inherits PATH from how it was launched. Ensure ~/.local/bin (or wherever cce is installed) is in your shell profile, then launch Cursor from a terminal with cursor .
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 · 77 lines · 8 tokens per session scan A 887c479beb19
cursor is an agent published in the GitHub repository elara-labs/code-context-engine (407 stars, last pushed 8d ago), licensed MIT. It adds 8 tokens to every session and 578 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
meta-warden
Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.
nopua-mentor-ja
Agent Team メンター役 — 他のチームメイトの実行状況を観察し、恐怖ではなく知恵で導く。行き詰まり、放棄、受け身に陥ったときは道徳経の知恵で啓発。5人以上のチーム推奨。.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.