pi-subagents is a pi extension that runs specialized AI sub-agents in separate sessions and coordinates them through parallel or sequential workflows. It is for developers who want autonomous agents with independent tools, prompts, models, and controllable execution. The catalogue agents and instruction define additional agent types and orchestration workflows for pi.
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/tintinweb/pi-subagents/lazy-ext-selectedgit clone --depth 1 https://github.com/tintinweb/pi-subagentsWrote 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/tintinweb/pi-subagents/lazy-ext-selected)<a href="https://agentmods.dev/agents/tintinweb/pi-subagents/lazy-ext-selected"><img src="https://agentmods.dev/badge/agents/tintinweb/pi-subagents/lazy-ext-selected.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 | $0.00012 | $0.00118 |
| Opus 5 | $0.00006 | $0.00059 |
| Sonnet 5 | $0.00002 | $0.00024 |
| Haiku 4.5 | $0.00001 | $0.00012 |
Grade B, and why
lazy-ext-selected scanned grade B with 1 finding 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 5d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: "*, ext:ext-lazy.mjs" What it actually says
e2e template: the case a static allowlist can never express. lazy_tool does not
exist when the session is constructed, so it cannot be listed up front — scope
has to be re-derived once the extension registers it.
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.
- 5d ago First seen · 11 lines · 12 tokens per session scan B cb0416fc88fb
lazy-ext-selected is an agent published in the GitHub repository tintinweb/pi-subagents (1,075 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 118 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
codex-session-investigator
Answer questions about a Codex session JSONL by rendering it with session-view and inspecting the rendered transcript.
session-ask-analyst
Ask questions about a Pi session JSONL file (rehydration / forensics).
implementer
Implement tasks via TDD and commit small changes.
worker
General-purpose worker for isolated tasks.
code-reviewer
Production readiness review: quality, security, testing (read-only).
spec-reviewer
Verify implementation matches the plan/spec (read-only).