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/eko24ive/pi-ask/agents-mdgit clone --depth 1 https://github.com/eko24ive/pi-askWrote 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/instructions/eko24ive/pi-ask/agents-md)<a href="https://agentmods.dev/instructions/eko24ive/pi-ask/agents-md"><img src="https://agentmods.dev/badge/instructions/eko24ive/pi-ask/agents-md.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 | $0.00824 | $0.00824 |
| Opus 5 | $0.00412 | $0.00412 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
pi-ask AGENTS.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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for agents working in this repository.
Project scope
This repo builds a pi.dev extension that adds an ask / interview-style user question flow.
Primary deliverables:
src/— implementationtests/— behavior coveragedocs/— contract and architecture
Project goals
Optimize for:
-
pi-native design
- prefer
pi.registerTool() - prefer
ctx.ui.custom()for complex flows - keep results compatible with normal pi tool results
- prefer
-
testable architecture
- keep state logic in plain TypeScript modules
- keep pi/TUI wiring thin
- prefer testing transitions and serialization over terminal rendering details
-
small docs, clear code
- keep implementation consistent with
docs/contract.md - update docs when behavior changes materially
- keep docs focused on contracts and boundaries, not line-by-line explanations
- keep implementation consistent with
Tech stack
- TypeScript
- pnpm
- Biome
- pi extension APIs from
@mariozechner/pi-coding-agent - TUI components from
@mariozechner/pi-tui - TypeBox for tool schemas
Commands
Use these project commands:
pnpm install
pnpm test
pnpm typecheck
pnpm format
pnpm lint
pnpm check
Notes:
pnpm checkruns Biome write/check flow for this repo.pnpm testruns the Node test runner againsttests/*.test.ts.- the extension is intended to be loaded dynamically with:
pi -e ./src/index.ts
File-specific guidance
src/
- keep implementation in TypeScript only
- preserve the separation between:
- schema/types
- state logic
- UI component logic
- tool registration
- avoid introducing unnecessary framework abstractions
- prefer small pure helper functions where possible
tests/
- add or update tests when changing state behavior
- prefer focused tests for:
- question normalization
- selection behavior
- tab movement
- custom answer submission
- result summarization
- cancellation behavior
docs
Keep docs short and synced with the implementation.
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 · 135 lines · 824 tokens per session scan A a017b8da4349
pi-ask AGENTS.md is an instructions file published in the GitHub repository eko24ive/pi-ask (48 stars, last pushed 18d ago), licensed MIT. It adds 824 tokens to every session, about $0.0041 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
pi-fabric AGENTS.md
Instructions for monotykamary/pi-fabric, covering agents.md, golden rule: build when done, before committing and commits.
TelePi AGENTS.md
Instructions for benedict2310/TelePi, covering repository guidelines, project structure & module organization, build, test, and development commands, operational commands and coding style & naming conventions.
my-pi AGENTS.md
Instructions for spences10/my-pi, covering agents.md, orientation, repository-specific skills, source of truth order and commit and changeset ownership.
LaPis AGENTS.md
Instructions for GeneGulanesJr/LaPis, covering protocols, 1. code & doc retrieval — use memory-code / memory-doc, 2. persistent memory — automatic, when to use the tools and content format.
pi-server AGENTS.md
Instructions for tryingET/pi-server, covering agents.md — crystallized learnings for pi-server, canonical references, architecture principles, adr-0001: atomic outcome storage and the invariant.
compound-engineering-pi CLAUDE.md
Instructions for gvkhosla/compound-engineering-pi, covering every marketplace - claude code plugin marketplace, repository structure, philosophy: compounding engineering, working with this repository and adding a new plugin.