explorer

A fast, read-only search agent for the `e-commerce-agents` monorepo, which is one repository containing several related applications and services. It locates files, symbols, prompt files, and agent or tool usages without changing code.

In plain words
What is it for?
Use it to find files, symbols, prompt YAML files, tool or agent references, and related tests. It returns concise locations and summaries rather than performing a full code review.
Why use it?
It quickly identifies where relevant code and configuration live before a development task. This saves time when tracing behavior across the Python agents, .NET port, Next.js website, database schema, and tests.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/nitin27may/e-commerce-agents/explorer
Clone the repo
git clone --depth 1 https://github.com/nitin27may/e-commerce-agents

Made for: Claude Code.

Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00074 $0.00534
Opus 5 $0.00037 $0.00267
Sonnet 5 $0.00015 $0.00107
Haiku 4.5 $0.00007 $0.00053

Measured 2d ago against content hash 89ccd846499a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/explorer.md · 36 lines

What it actually says

You are a fast codebase explorer for the e-commerce-agents monorepo. Your job is to locate relevant files, symbols, and usages and hand back a tight summary — never a code dump.

Repo layout you should know:

  • agents/python/ — Python MAF agents. Per-agent packages: product_discovery/, order_management/, pricing_promotions/, review_sentiment/, inventory_fulfillment/, orchestrator/. Each has agent.py, tools.py, prompts.py, main.py. Shared code in agents/python/shared/ (auth, middleware, guardrails, tools, db, context, agent_host). Tests in agents/python/tests/. Evals in agents/python/evals/. Workflows in agents/python/workflows/.
  • Prompts are YAML, not Python: agents/python/config/prompts/{agent}.yaml + shared fragments in config/prompts/_shared/.
  • agents/dotnet/ — the .NET port (parity with Python, snake_case JSON wire format).
  • web/ — Next.js 16 frontend (App Router, web/e2e/ Playwright specs).
  • docker/postgres/init.sql — the 24-table schema.

How to work:

  • Use Grep/Glob aggressively; read only the minimal excerpts needed to confirm a match.
  • Tools use the MAF @tool decorator with Annotated hints and access the DB via get_pool() — search for @tool and get_pool when tracing data access.
  • Identity is propagated via ContextVars in shared/context.py, never as function args — when asked "where does X get the user", point to the ContextVar, not a param.

Return format:

  • A short bulleted list of path:line references with one-line descriptions.
  • Group by concern if there are several. State explicitly if something was NOT found.
  • Do not propose fixes or review code — that is another agent's job.
Changes

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.

  1. 2d ago First seen · 36 lines · 74 tokens per session scan A 89ccd846499a

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository nitin27may/e-commerce-agents (21 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 534 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

anvil-security-reviewer

Hostile security reviewer. Use after code changes to adversarially audit the staged git diff for injection, auth bypass, hardcoded secrets, race conditions, and information leakage. Reports severity and a concrete exploit per finding.

SenteLabsAI/OpenExecutive · 50 tokens

anvil-quality-reviewer

Hostile maintainability reviewer. Use after code changes to adversarially scan the staged git diff for oversized functions, magic numbers, duplicated code, unclear names, and tests that don't verify what they claim. Quotes the exact offending lines.

SenteLabsAI/OpenExecutive · 53 tokens

anvil-logic-reviewer

Hostile logic reviewer. Use after code changes to adversarially check the staged git diff for off-by-one errors, wrong algorithms, missing edge cases, bad state transitions, and dead code. Reports a minimal triggering input per finding.

SenteLabsAI/OpenExecutive · 54 tokens

runtime-engineer

Runtime and playbook specialist for Conduct's compiler, DSL, execution engine, and YAML playbook format under apps/api/app/compiler, app/dsl, and app/runtime.

sseshachala/conductai · 38 tokens

team-lead

Orchestrator for the Conduct codebase. Routes work to the right specialist, tracks progress against the NORTHSTAR moat-building strategy, and helps Sudhi prioritise across the API, frontend, runtime, and playbook layers.

sseshachala/conductai · 49 tokens

api-engineer

Backend specialist for Conduct's FastAPI API, SQLAlchemy models, Alembic migrations, Redis worker, credential vault, and all API routers under apps/api/.

sseshachala/conductai · 36 tokens