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 agentlas-ai/agentlas-desktop --skill pi-agentgit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/pi-agent)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/pi-agent"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/pi-agent/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/agentlas-ai/agentlas-desktop/pi-agent"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/pi-agent.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 | $0.00118 | $0.01715 |
| Opus 5.5 | $0.00047 | $0.00686 |
| Sonnet 5.5 | $0.00024 | $0.00343 |
| Haiku 4.5 | $0.00012 | $0.00171 |
Grade A, and why
pi-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 1mo 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.
This is a copy
100% identical to pi-agent — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pi Agent
Use this skill when the user wants to operate Pi or build on top of Pi. Pi is a minimal terminal coding harness extended through TypeScript extensions, skills, prompt templates, themes, packages, custom models/providers, SDK integrations, RPC mode, JSON event streams, and TUI components.
First Decision
Pick the reference before answering or coding:
| User intent | Read |
|---|---|
| What Pi is, docs map, install methods | references/overview.md |
| Install, authenticate, first run | references/quickstart.md |
| Day-to-day CLI usage, commands, modes, flags, project trust | references/usage.md |
| Provider auth, API keys, cloud provider setup | references/providers.md |
| Custom model entries, local models, proxies, compat flags | references/models.md |
Local llama.cpp router, /llama, model download/load |
references/llama-cpp.md |
| Settings keys and defaults | references/settings.md |
PI_* and other environment variables |
references/environment-variables.md |
| Extension development, custom tools, events, commands | references/extensions.md |
| Custom provider implementation, OAuth, custom streaming | references/custom-provider.md |
| Embed Pi in Node/TypeScript | references/sdk.md |
| Integrate from another process/language | references/rpc.md |
| Consume JSONL event output | references/json.md |
| Build terminal UI components | references/tui.md |
| Package extensions/skills/prompts/themes | references/packages.md |
| Delegate to subagents, chains, parallel runs, orchestration | references/pi-subagents.md |
| Connect MCP servers, MCP tool discovery/config | references/pi-mcp-adapter.md |
| Interactive interview forms, structured user input | references/pi-interview.md |
| Web search, URL/PDF/repo fetching, video understanding | references/pi-web-access.md |
| Author Pi skills | references/skills.md |
| Prompt templates or themes | references/prompt-templates.md, references/themes.md |
| Sessions, branching, compaction, parsing JSONL | references/sessions.md, references/compaction.md, references/session-format.md |
| Security, sandboxing, trust | references/security.md, references/containerization.md |
| Keyboard or terminal issues | references/keybindings.md, references/terminal-setup.md, references/tmux.md, references/windows.md, references/termux.md, references/shell-aliases.md |
| Working on Pi itself | references/development.md |
What ships with it
34 files 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.
- references/compaction.md 5.3 KB
- references/containerization.md 3.5 KB
- references/custom-provider.md 8.2 KB
- references/development.md 1.2 KB
- references/environment-variables.md 3.6 KB
- references/extensions.md 18 KB
- references/json.md 2.8 KB
- references/keybindings.md 5.4 KB
- references/llama-cpp.md 3.0 KB
- references/models.md 8.5 KB
- references/overview.md 2.0 KB
- references/packages.md 5.9 KB
- references/pi-interview.md 7.4 KB
- references/pi-mcp-adapter.md 21 KB
- references/pi-subagents.md 41 KB
- references/pi-web-access.md 27 KB
- references/prompt-templates.md 1.7 KB
- references/providers.md 7.9 KB
- references/quickstart.md 2.5 KB
- references/rpc.md 8.9 KB
- references/sdk.md 11 KB
- references/security.md 4.6 KB
- references/session-format.md 6.1 KB
- references/sessions.md 2.9 KB
- references/settings.md 6.8 KB
- references/shell-aliases.md 606 B
- references/skills.md 3.7 KB
- references/terminal-setup.md 4.2 KB
- references/termux.md 1.1 KB
- references/themes.md 4.1 KB
- references/tmux.md 1.6 KB
- references/tui.md 7.5 KB
- references/usage.md 8.0 KB
- references/windows.md 745 B
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.
- 1mo ago First seen · 101 lines · 118 tokens per session scan A 51221e4d9040
pi-agent is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 118 tokens to every session and 1,715 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to pi-agent, differing in 20 lines, and is treated as a copy.
Other skills, from other repositories
typescript-eval
Test TypeScript code snippets before persisting as skills.
javascript-sandbox
Best practices for using the clodex built-in JavaScript sandbox for browser debugging, fetched-data processing, attachments, and mini-app orchestration within its bundled capability boundary.
openmanus
Use OpenManus as an external autonomous Python agent for long-running research, browser-style exploration, data analysis, or multi-step execution tasks from inside a mounted workspace.
node
Node.js runtime and npm package manager.
effect
Work with Effect v4 / effect-smol TypeScript code in this repo.
typescript
Use when creating or refactoring TypeScript code to strict standards; enforces type-first modeling, T-prefixed aliases, explicit return types, safe generics, discriminated unions, and maintainable module-level typings.