An integration for the Pi coding agent that creates project-local configuration and instructions for using kcp-harness. Pi is a coding agent, while an MCP client is an extension that lets it connect to external tools.

Use it to generate Pi configuration and skills for kcp-harness, optionally specifying a knowledge manifest and allowed paths. It can preview the changes first and does not install Pi or change global Pi settings.

Pi does not include an MCP client by default, so the generated configuration alone cannot connect to those tools. The integration documents this requirement and keeps the setup limited to the project rather than global settings.

pi — Agent for coding agents by Cantara: An integration for the Pi coding agent that creates…

Install

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.

agentmods

npx agentmods add agents/cantara/kcp-harness/pi

Clone the repo

git clone --depth 1 https://github.com/Cantara/kcp-harness

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/cantara/kcp-harness/pi.svg)](https://agentmods.dev/agents/cantara/kcp-harness/pi)

Your own site

<a href="https://agentmods.dev/agents/cantara/kcp-harness/pi"><img src="https://agentmods.dev/badge/agents/cantara/kcp-harness/pi.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 328 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00328
Opus 5	$0.00000	$0.00164
Sonnet 5	$0.00000	$0.00066
Haiku 4.5	$0.00000	$0.00033

Measured 3d ago against content hash d6011f1225ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pi 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.

docs/agents/pi.md · 39 lines

What it actually says

Pi integration

kcp-harness integrate pi generates project-local Pi configuration:

.pi/mcp.json with a lazy kcp-harness MCP server and directTools: false;
.pi/skills/kcp-harness/SKILL.md teaching the agent to use kcp_plan, kcp_load, and harness diagnostics.

Prerequisite: an MCP client extension

Stock Pi ships without an MCP client ("No MCP" is a stated Pi design choice), so .pi/mcp.json on its own does nothing. Install an MCP client extension first, for example:

pi install npm:pi-mcp-adapter

The generated .pi/mcp.json uses that adapter's format (settings.toolPrefix, settings.directTools, per-server lifecycle: lazy). The generated skill loads independently of MCP — Pi discovers .pi/skills/ once the project is trusted — and tells the agent to ask the operator for the adapter rather than bypass governance when the kcp_plan/kcp_load tools are missing.

Preview before writing:

kcp-harness integrate pi --dry-run

Generate with a custom manifest and governed paths:

kcp-harness integrate pi \
  --manifest ./knowledge.yaml \
  --paths "docs/,src/"

The integration does not install Pi, modify global Pi settings, or reimplement governance. Review the generated files before committing them. Re-running the command is idempotent for the generated files.

Changes

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 · 39 lines · 0 tokens per session scan A d6011f1225ed

Subscribe to this mod's changes

pi is an agent published in the GitHub repository Cantara/kcp-harness (0 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 328 tokens. 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 2026-08-31.

Building agents

pi

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Pi integration

Prerequisite: an MCP client extension

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

.NET-Notebook-Migration-Agent