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 instructions/bitsky-tech/amphiloop/claude-mdgit 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 | $0.01194 | $0.01194 |
| Opus 5 | $0.00597 | $0.00597 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
AmphiLoop CLAUDE.md 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 3d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AmphiLoop
Agent skill & knowledge corpus for the Bridgic ecosystem — providing skills, agents, and commands for building high-quality bridgic projects. Skills cover the foundational specs; commands and agents orchestrate them into end-to-end workflows.
Architecture
AmphiLoop/
├── CLAUDE.md ← this file
├── .claude-plugin/
│ ├── plugin.json ← Claude Code plugin registration
│ └── marketplace.json ← marketplace metadata
├── skills/ ← domain knowledge: "what it is, how to use it"
│ ├── manifest.ini ← skill source registry (repo, ref, paths)
│ ├── README.md ← manifest docs + auto-generated skill table
│ ├── bridgic-browser/ ← browser automation CLI + SDK
│ ├── bridgic-amphibious/ ← dual-mode agent framework
│ └── bridgic-llms/ ← LLM providers and initialization
├── agents/ ← execution methodology: "how to do it well"
│ ├── amphibious-config.md ← inline-loaded by /build Phase 2 (interactive; NOT a subagent)
│ ├── amphibious-explore.md ← abstract exploration methodology
│ ├── amphibious-code.md ← code generation expertise
│ └── amphibious-verify.md ← project verification expertise
├── commands/ ← user-invocable workflows (thin orchestrators)
│ └── build.md ← /build pipeline (domain-agnostic; accepts --<domain>)
├── domain-context/ ← pre-distilled per-domain context injected by /build
│ └── browser/ ← intent.md, config.md, explore.md, code.md, verify.md
│ └── script/ ← domain-only helpers (e.g. browser-observe.sh)
├── templates/ ← static templates read by commands (not auto-scanned by Claude Code)
│ └── build-task-template.md ← unified TASK.md template (used by /build Phase 1)
├── hooks/ ← auto-loaded by Claude Code
│ └── hooks.json ← hook definitions
└── scripts/
├── hook/ ← hook script implementations
│ └── inject-command-paths.sh ← injects PLUGIN_ROOT + PROJECT_ROOT when a bridgic command loads
├── run/ ← runtime scripts used by agents
│ ├── setup-env.sh ← verify uv toolchain (auto-installs if missing) and run `uv init --bare` in PROJECT_ROOT
│ ├── check-dotenv.sh ← .env LLM configuration validation
│ └── monitor.sh ← run-and-monitor for amphibious-verify agent
└── maintenance/ ← plugin maintenance scripts (manual)
└── sync-skills.sh ← sync skills from source repos via manifest.ini
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.
- 3d ago First seen · 82 lines · 1,194 tokens per session scan A 9fcfc84ffe22
AmphiLoop CLAUDE.md is an instructions file published in the GitHub repository bitsky-tech/AmphiLoop (68 stars, last pushed 3mo ago), licensed MIT. It adds 1,194 tokens to every session, about $0.0060 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.