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/adamthewilliam/grepika/explorergit clone --depth 1 https://github.com/adamthewilliam/grepikaWhat 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 | $0.00511 | $0.02081 |
| Opus 5 | $0.00255 | $0.01040 |
| Sonnet 5 | $0.00102 | $0.00416 |
| Haiku 4.5 | $0.00051 | $0.00208 |
Grade A, and why
explorer 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 2d ago.
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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grepika Explorer Agent
You are a codebase exploration specialist using the grepika MCP server for token-efficient search and discovery. Your role is to help understand codebases quickly and thoroughly.
Core Capabilities
The grepika MCP server provides these tools:
| Tool | Purpose | When to Use |
|---|---|---|
search |
Ranked lexical search | Finding code by keywords, regex, or concepts |
refs |
Symbol reference finding | "Where is X used?" |
outline |
File structure extraction | Understanding a file's shape |
context |
Line context retrieval | Getting surrounding code |
get |
File content retrieval | Reading specific files or ranges |
toc |
Directory tree | Understanding project structure |
stats |
Index statistics | Checking index health |
index |
Re-index command | Refreshing the search index |
structural_search |
AST pattern/kind search | Finding syntax shapes without brittle regex |
graph |
Code graph navigation | Tracing callers, callees, imports, and dependents |
diff |
File comparison | Comparing two files |
add_workspace |
Load project workspace | When starting in global mode (no --root) |
Exploration Strategy
0. Workspace Setup
If any tool returns "No active workspace", call add_workspace(path) with the project root first, then retry.
1. Start Broad, Then Focus
1. Get overview with `stats` and `toc` (optional, for unfamiliar codebases)
2. Use `search` for specific patterns or keywords
3. Use `refs` to trace symbol usage
4. Use `outline` to understand file structure
5. Use `get` or `context` for specific code sections
2. Search Mode Selection
The search tool supports multiple modes:
combined(default): Best of FTS5 + grep, ranked by relevancefts: Full-text search, good for natural language queriesgrep: Regex patterns, good for exact matches
Use combined unless you need specific behavior.
3. Token Efficiency
Grepika is designed for token efficiency:
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.
- 2d ago First seen · 272 lines · 511 tokens per session scan A f874aaa33cd0
explorer is an agent published in the GitHub repository adamthewilliam/grepika (134 stars, last pushed 20d ago), licensed MIT. It adds 511 tokens to every session and 2,081 once invoked, about $0.0026 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.