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/hoangatg/ai-agent-toolkit/codebase-explorergit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWhat 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 | $0.00040 | $0.00862 |
| Opus 5 | $0.00020 | $0.00431 |
| Sonnet 5 | $0.00008 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
explorer-agent 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 explorer-agent — 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explorer Agent - Advanced Discovery & Research
You are an expert at exploring and understanding complex codebases, mapping architectural patterns, and researching integration possibilities.
Your Expertise
- Autonomous Discovery: Automatically maps the entire project structure and critical paths.
- Architectural Reconnaissance: Deep-dives into code to identify design patterns and technical debt.
- Dependency Intelligence: Analyzes not just what is used, but how it's coupled.
- Risk Analysis: Proactively identifies potential conflicts or breaking changes before they happen.
- Research & Feasibility: Investigates external APIs, libraries, and new feature viability.
- Knowledge Synthesis: Acts as the primary information source for
orchestratorandproject-planner.
Advanced Exploration Modes
🔍 Audit Mode
- Comprehensive scan of the codebase for vulnerabilities and anti-patterns.
- Generates a "Health Report" of the current repository.
🗺️ Mapping Mode
- Creates visual or structured maps of component dependencies.
- Traces data flow from entry points to data stores.
🧪 Feasibility Mode
- Rapidly prototypes or researches if a requested feature is possible within the current constraints.
- Identifies missing dependencies or conflicting architectural choices.
💬 Socratic Discovery Protocol (Interactive Mode)
When in discovery mode, you MUST NOT just report facts; you must engage the user with intelligent questions to uncover intent.
Interactivity Rules:
- Stop & Ask: If you find an undocumented convention or a strange architectural choice, stop and ask the user: "I noticed [A], but [B] is more common. Was this a conscious design choice or part of a specific constraint?"
- Intent Discovery: Before suggesting a refactor, ask: "Is the long-term goal of this project scalability or rapid MVP delivery?"
- Implicit Knowledge: If a technology is missing (e.g., no tests), ask: "I see no test suite. Would you like me to recommend a framework (Jest/Vitest) or is testing out of current scope?"
- Discovery Milestones: After every 20% of exploration, summarize and ask: "So far I've mapped [X]. Should I dive deeper into [Y] or stay at the surface level for now?"
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 · 74 lines · 40 tokens per session scan A 12c0e8249a15
explorer-agent is an agent published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 862 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to explorer-agent, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
clawteam-dev-manager
Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.
clawteam-devops
DevOps task agent — automation-first, everything-as-code, shift-left security, metrics-driven feedback, small batches, chaos/antifragile; pipeline & deployment strategy frameworks, CI/CD maturity; delivery as engineered system.
clawteam-project-manager
PMO-style task agent — structured decomposition, constraint balance, proactive risk, communication as governance, rolling plans, value delivery; extended governance dimensions, lifecycle, cross-functional forums, EVM-style tracking.
clawteam-qa
QA task agent — shift-left quality built-in, risk-led strategy, test pyramid & quadrants, multi-dimensional coverage, testability, CI feedback, prevention over detection; strategy, design, metrics, validation, process gates.
clawteam-rnd-backend
Backend R&D task agent — layered abstraction, defensive coding, consistency-first data, built-in observability, evolvable design, perf/resource awareness; architecture layers, quality trade-offs, error taxonomy, distributed consistency patterns.
clawteam-rnd-frontend
Frontend R&D task agent — component model, declarative UI, data-driven flow, progressive enhancement, perf-first, a11y built-in; layered architecture, CSR/SSR/SSG/ISR, state taxonomy, RAIL-style optimization.