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/a5c-ai/babysitter/ampgit clone --depth 1 https://github.com/a5c-ai/babysitterWrote 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/a5c-ai/babysitter/amp)<a href="https://agentmods.dev/agents/a5c-ai/babysitter/amp"><img src="https://agentmods.dev/badge/agents/a5c-ai/babysitter/amp.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 | $0.00000 | $0.01960 |
| Opus 5 | $0.00000 | $0.00980 |
| Sonnet 5 | $0.00000 | $0.00392 |
| Haiku 4.5 | $0.00000 | $0.00196 |
Grade C, and why
amp scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://get.sourcegraph.com/amp | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### curl (Universal) How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amp
Sourcegraph's agentic coding assistant with multi-model support and specialized subagents for advanced code understanding.
Overview
Sourcegraph Amp is an intelligent coding agent that combines multiple AI models with specialized subagents to deliver superior code understanding and generation. Features include the Oracle multi-model routing system, Librarian code search capabilities, and deep integration with Sourcegraph's code intelligence platform.
Installation
NPM (Recommended)
npm install -g @ampcode/cli
curl (Universal)
curl -fsSL https://get.sourcegraph.com/amp | bash
Binary Download
Download from GitHub Releases for your platform.
Authentication
Sourcegraph Account Setup
- Sign up at sourcegraph.com/sign-up
- Install Amp CLI (see Installation above)
- Generate an access token:
open https://sourcegraph.com/users/settings/tokens - Authenticate with Sourcegraph:
amp auth login - Verify authentication:
amp --version
Environment Variables
export SOURCEGRAPH_ACCESS_TOKEN=your_sourcegraph_token
Usage with adapters
Basic Chat
adapters run amp --prompt "Explain this codebase architecture"
Resume Session
adapters run amp --session-id def456 --prompt "Continue the code review"
Model Selection
# Oracle multi-model routing (default)
adapters run amp --model oracle --prompt "Optimize this algorithm"
# Specific model selection
adapters run amp --model claude-sonnet --prompt "Review for security vulnerabilities"
adapters run amp --model gpt-4o --prompt "Generate comprehensive tests"
adapters run amp --model gemini-pro --prompt "Refactor for better maintainability"
Auto-approve Tools (Yolo Mode)
adapters run amp --tool-approval-mode yolo --prompt "Fix all ESLint warnings"
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.
- 4d ago First seen · 314 lines · 0 tokens per session scan C 28ed45f36119
amp is an agent published in the GitHub repository a5c-ai/babysitter (1,762 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,960 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
experiment-coder
Implement, deploy, monitor, sync, and debug experiments from the STATE.md Runs table.
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
implementer
Use when the implementation plan needs to be executed slice by slice. A seasoned coding expert that reads the plan, follows TDD discipline, executes one vertical slice at a time, and commits each slice atomically when its tests pass. Dispatched during the Implement phase.
default-workflow
The order of work for any task: what to read first, how to scope a change, how to verify, and how to commit and open pull requests. Topic-specific rules live in the pages linked under References.
progressive-disclosure-source
This file is the source of truth for the structure and maintenance approach.