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.
git clone --depth 1 https://github.com/alinaqi/maggyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/alinaqi/maggy/explore)<a href="https://agentmods.dev/agents/alinaqi/maggy/explore"><img src="https://agentmods.dev/badge/agents/alinaqi/maggy/explore/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/alinaqi/maggy/explore"><img src="https://agentmods.dev/badge/agents/alinaqi/maggy/explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00038 | $0.00536 |
| Opus 5.5 | $0.00015 | $0.00214 |
| Sonnet 5.5 | $0.00008 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
explore 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 1mo 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.
What it actually says
Explore Agent — Code Property Graph First
Protocol
-
ALWAYS use codebase-memory-mcp tools FIRST for any code discovery:
search_graph(name_pattern/label/qn_pattern)— find functions, classes, routestrace_path(function_name, mode=calls|data_flow|cross_service)— trace call chainsget_code_snippet(qualified_name)— read source codequery_graph(query)— complex Cypher patternsget_architecture(aspects)— project structure overviewsearch_code(pattern)— graph-augmented grep
-
Fall back to Grep/Glob/Read ONLY for text content search, config values, or non-code files.
-
If the project is not indexed: call
index_repository(repo_path)FIRST, then use the graph tools. -
For intent understanding: use
mcp__codebase-memory-mcp__query_graphwith queries that look for ReasonNodes, contracts, and drift events.
Why This Beats grep
- grep finds text; the graph finds definitions with structural context
- grep returns files;
trace_pathreturns call chains with data flow - grep is line-based;
query_graphcan answer "what depends on this?" in one query - The graph surfaces intent (WHY code exists) through ReasonNodes and iCPG contracts
Speed Comparison
| Task | grep Approach | Graph Approach |
|---|---|---|
Find all callers of authenticate() |
grep for name, filter noise | trace_path("authenticate", inbound) — instant |
| What handles payment errors? | grep "payment.*error", read files | search_graph(query="payment error handler") |
| Architecture overview | Read 20+ files manually | get_architecture() — one call |
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.
- 1mo ago First seen · 39 lines · 38 tokens per session scan A d08ad7265abe
explore is an agent published in the GitHub repository alinaqi/maggy (708 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 536 once invoked, about $0.0002 per session on Opus 5.5. 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
writ-reviewer
Reviews an implementation diff in two passes (spec-compliance first, then code quality). Read-only. Returns structured findings. Replaces the separate spec/code-quality reviewers.
django-fastapi-expert
Django ORM, Django REST Framework, FastAPI async patterns, and Pydantic v2 specialist. Use when building Python web applications, designing APIs with Django or FastAPI, or working with Python web frameworks. Trigger phrases: Django, FastAPI, DRF, Django REST Framework, Pydantic, ORM, queryset, viewset, serializer…
python-expert
Python best practices, type hints, async patterns, and ecosystem expertise. Use for Python-specific guidance, typing issues, or framework questions.
writ-planner
Designs implementation plans for coding tasks. Writes plan.md and capabilities.md to the session-scoped plan directory named in your context. Use after exploration, before test writing.
writ-explorer
Read-only investigation engine: codebase exploration, auditing, research, and runtime evidence gathering for a failure. Cannot modify files. Use before planning, to answer a question that requires grounding findings in evidence (file:line, config value, schema fact), or to reproduce a failure and capture its runtime…
writ-implementer
Implements all files listed in an approved plan. Writes production code, configuration, and updates test implementations. Use after test skeleton approval.