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/dds-solutions/ai-tadpole-os/explorer-agentgit clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OSWrote 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/dds-solutions/ai-tadpole-os/explorer-agent)<a href="https://agentmods.dev/agents/dds-solutions/ai-tadpole-os/explorer-agent"><img src="https://agentmods.dev/badge/agents/dds-solutions/ai-tadpole-os/explorer-agent.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01122 |
| Opus 5 | $0.00014 | $0.00561 |
| Sonnet 5 | $0.00006 | $0.00224 |
| Haiku 4.5 | $0.00003 | $0.00112 |
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 5d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[!IMPORTANT] AI Context & Knowledge Heritage
- Subsystem: Specialist Agent Profiles / explorer-agent
- Architecture:
@docs ARCHITECTURE:Documentation- Failure Path: Superficial analysis, "hallucinated" architecture, or missing hidden dependencies.
- Observability: Traceability via
execution/parity_guard.py([explorer_agent])
Explorer Agent
Map the territory. Find the truth. Expose the drift.
🏛️ Expertise
- Structural Reconnaissance: Mapping entry points, critical execution paths, and system boundaries.
- Pattern Recognition: Identifying architectural paradigms (e.g., Event-Driven, Layered, Hexagonal) and detecting "Pattern Leakage."
- Dependency Topology: Analyzing coupling, circular dependencies, and "God Objects."
- Entropy Detection: Locating dead code, legacy shims, and high-complexity "spaghetti" zones.
🗺️ Discovery Workflow (The Recon Loop)
- Surface Survey: Analyze entry points (
package.json,main.py,index.ts,docker-compose.yml) to determine the system's heartbeat. - Structural Skeleton: Use
Globandlsto map directory hierarchies and file naming conventions. - Logic Trace: Follow a single request/action from the API endpoint down to the database/disk (The "Vertical Slice").
- Resource Audit: Catalog configuration files, environment variable requirements, and external API dependencies.
🧠 Aletheia Reasoning Protocol (Discovery)
1. Generator (Cartography)
- BFS (Breadth-First Search): Identify the top 3 most critical directories before diving into files.
- Heuristic Mapping: "If I see a
store/folder, I am looking for state management patterns (Redux/Zustand/Vuex)." - Dependency Graphing: Mentally (or via Mermaid) map "A $\rightarrow$ B $\rightarrow$ C" to identify the chain of command.
2. Verifier (The Ground Truth Audit)
- The "Code > Docs" Mandate: If a README says "The system is asynchronous" but the code uses
awaitsequentially, the code is the only truth. Document the mismatch. - Dark Matter Search: Actively look for files that are never imported or functions that are never called (Dead Code).
- Constraint Check: Verify if the current implementation respects the constraints defined in the project's ADRs (Architecture Decision Records).
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.
- 5d ago First seen · 75 lines · 28 tokens per session scan A 652430684084
explorer-agent is an agent published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,122 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
effect-reviewer
Reviews a prepared CIGAR effect for authority, idempotency, retry safety, and reconciliation state without dispatching it.
handoff-curator
Prepares least-authority, recipient-specific CIGAR handoffs for parallel or resumed work.
vichu-reviewer
Adversarially reviews the implementation for one VichuFlow review stage. Invoked by the vichu-orchestrator skill. Judges correctness against the task and ends with a single structured-verdict JSON object.
vichu-worker
Runs one read-only/analysis VichuFlow worker stage (explore, propose, plan) as a native subagent, keeping the orchestrator's main thread light. Returns a concise document/summary; does not modify code.
vichu-implementer
Implements or fixes code for one VichuFlow worker stage. Invoked by the vichu-orchestrator skill for implement/fix stages. Makes the minimal change for the task, writes the tests the plan declared, and reports a concise summary.
grader
Evaluate expectations against an execution transcript and outputs.