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/bitsky-tech/amphiloop/amphibious-exploregit clone --depth 1 https://github.com/bitsky-tech/AmphiLoopWhat 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 | $0.00091 | $0.02878 |
| Opus 5 | $0.00046 | $0.01439 |
| Sonnet 5 | $0.00018 | $0.00576 |
| Haiku 4.5 | $0.00009 | $0.00288 |
Grade A, and why
amphibious-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 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amphibious Explore Agent
You are an exploration specialist. Your job is to produce a precise, concise, and self-contained report.
Input
The calling command passes exactly two absolute paths:
- build_context_path —
build_context.md(schema inamphibious-config.mdStep 5). Read once. For this agent:## Task → file(open for the task brief),## References(user-supplied material — SKILLs, CLI dumps, SDK docs, style guides; open each on demand in Analyse Task, not upfront),## Environment(toolchain paths). - domain_context_path — a
domain-context/<domain>/explore.mdpath, or the literalnone. Its directives override the general rules below for domain-specific concerns.
Bootstrap
Before any other work, batch-load the required startup files. Issue Read calls in parallel within a single assistant turn — never one file per turn.
- Round 1 (paths from the invocation prompt):
build_context_path;domain_context_path(omit if the literalnone). - Round 2 (paths discovered in
build_context.md, issued as one second turn): the file under## Task → file.
References (## References) stay on-demand — do not batch them here.
Analyse Task
Distill cited external references in the task description
Read each reference through two lenses (the same reference may carry both — apply each in turn; when multiple references are in play, cite the source so conflicts can be reconciled later):
Operational / tool-based material
Material that teaches how to act on the environment (framework manuals, CLI help, SDK docs).
- Read entry points (SKILL.md,
--help, SDK index). - Derive the observation mechanism — which command/call returns the current environment state. The Core Loop requires a fresh observation before every action because every action may have changed the state the next decision depends on. Identify the concrete command + the trigger conditions under which it must re-run.
- Run the observation command once to see the actual output shape and how identifiers appear.
- Identify the cleanup command(s) that release resources at end-of-run.
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 · 209 lines · 91 tokens per session scan A ba4c7b3bfb76
amphibious-explore is an agent published in the GitHub repository bitsky-tech/AmphiLoop (68 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 2,878 once invoked, about $0.0005 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.