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 skills add paulinevos/claude-stuff --skill amp-cligit clone --depth 1 https://github.com/paulinevos/claude-stuffWrote 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/skills/paulinevos/claude-stuff/amp-cli)<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/amp-cli"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/amp-cli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/amp-cli"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/amp-cli.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00040 | $0.01021 |
| Opus 5.5 | $0.00016 | $0.00408 |
| Sonnet 5.5 | $0.00008 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
amp-cli 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amp CLI
When asked to start an orb, start a thread on Amp, or hand work to Amp, actually launch it through the CLI and return its URL. Writing this skill does not itself authorize launching an Amp task.
Check availability
Run command -v amp, amp version, and amp --help. If PATH misses it, check ~/.local/bin/amp and ~/.amp/bin/amp. Read relevant subcommand help for unfamiliar operations: Amp changes quickly.
If missing, report it. When installation is requested, download and inspect https://ampcode.com/install.sh, run the official installer with required permissions, and verify help/version. Existing shells may need the absolute executable path after the installer updates PATH.
Check amp account list. An existing AMP_API_KEY can authenticate too; check presence without revealing its value. If needed, use amp login when authorized and leave browser sign-in to the user. Successful help output does not establish authentication.
Prepare context
Write a self-contained summary to a temporary UTF-8 file using a file-writing tool. Include the outcome and acceptance criteria, repository/project and branch or commit, relevant files and links, decisions and constraints, findings, completed work, next steps, reproduction/tests and known failures, and the scope of authorized actions. Distinguish facts from hypotheses. Omit unrelated history and credentials. Feed this file through stdin rather than interpolating conversation text into a shell command.
Run in the relevant checkout. For repository work, check amp projects status --json or select a known project explicitly; resolve a missing project before launching. No-project orbs are appropriate for tasks needing no repository. Orbs cannot assume access to local paths, uncommitted changes, or unpublished commits. Supply necessary diffs/files through prompt context or --attach and explain their use. Do not push merely to facilitate a handoff without authorization.
Launch and follow up
For an orb or a generic remote handoff to a thread on Amp, use:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 66 lines · 40 tokens per session scan A c84f2e9e6436
amp-cli is a skill published in the GitHub repository paulinevos/claude-stuff (64 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 1,021 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…