pi-continue: Instructions file for Codex

AGENTS.md

pi-continue AGENTS.md is an instructions file for Codex, OpenCode from Tiziano-AI/pi-continue. It costs 6,873 tokens per session, scanned A, original, MIT.

A project instruction file for pi-continue, an extension that lets a long Pi coding session continue after its context is summarized. It describes the product rules, documentation locations, and code ownership.

In plain words
What is it for?
Use it when developing or reviewing the pi-continue extension, its documentation, changelog, or source files.
Why use it?
It gives coding agents the project boundaries and release expectations needed to change the extension without breaking its stated behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is Tiziano-AI/pi-continue's own configuration. It tells Codex and OpenCode how to work on pi-continue itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pi-continue configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Tiziano-AI/pi-continue. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Tiziano-AI/pi-continue/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Tiziano-AI/pi-continue

Made for: Codex, OpenCode.

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.

agentmods badge for pi-continue AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tiziano-ai/pi-continue/agents-md/github.svg)](https://agentmods.dev/instructions/tiziano-ai/pi-continue/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tiziano-ai/pi-continue/agents-md"><img src="https://agentmods.dev/badge/instructions/tiziano-ai/pi-continue/agents-md/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.

agentmods 80×15 button for pi-continue AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tiziano-ai/pi-continue/agents-md"><img src="https://agentmods.dev/badge/instructions/tiziano-ai/pi-continue/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,873 This file is loaded in full into every session.
When invoked 6,873 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06873 $0.06873
Opus 5.5 $0.02749 $0.02749
Sonnet 5.5 $0.01375 $0.01375
Haiku 4.5 $0.00687 $0.00687

Measured 21d ago against content hash 105a8dc93955, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pi-continue 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 21d 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.

AGENTS.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

pi-continue is a Pi extension package with one product promise: when context fills during a long Pi run, Pi compacts at a safe checkpoint and the same task continues in the same session from the new summary. It is published on npm and in the pi.dev package gallery and accepts outside contributions, so it has real users. Breaking changes are announced under Breaking changes and Migration in CHANGELOG.md; the product still keeps no aliases or compatibility shims (see the product contract).

This guide is for agents working in this checkout. It is tracked in Git and deliberately excluded from the npm package, where README.md is the operator guide. Paths written src/... are under extensions/continue/src/.

Where things live

The tracked documentation is intentionally small:

  • README.md is the npm-package guide: install, /continue, configuration, prompt customization, boundaries and a compact product explanation.
  • CHANGELOG.md holds the release notes. Keep it concise, complete and tied to validated shipped behavior.
  • AGENTS.md (this file) holds the product invariants, the Pi runtime boundary, code ownership, checks and the release invariants. It is tracked for everyone who works on the repository and excluded from the npm package by the package.json files allowlist; tracking it does not bring the ignored local notes below back into the documentation.

Everything else explains itself through source and tests. extensions/continue/index.ts is the entry point and registers the Pi hooks; the ownership map below says which src/ module owns each behavior; assets/ holds the customizable system/user prompt corpus; examples/ holds the public config and output examples; tests/ is the executable contract, including the no-network host-loop fixture in tests/mid-run-host-integration.test.ts, which drives a real Pi agent session with a faux provider.

PLAN.md, ARCH.md and VISION.md are ignored local notes, not documentation, and MAINTAINER.md is the maintainer's ignored local release runbook (see Releasing). Do not re-track them or grow a larger documentation set unless the maintainer explicitly restores one. CONTINUE.md is retired local state: pi-continue neither writes nor reads it, and if it exists, leave it alone unless the task is about continuation-document behavior. .pi/continue/*.md is package-owned runtime output (the per-session continuation artifacts). None of these belong in the package.

Read the full file on GitHub · 242 lines

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.

  1. 21d ago Changed · +2 lines · +160 tokens per session 105a8dc93955
  2. 1mo ago First seen · 240 lines · 6,713 tokens per session scan A 7eecf0fc12c3

Subscribe to this mod's changes

pi-continue AGENTS.md is an instructions file published in the GitHub repository Tiziano-AI/pi-continue (20 stars, last pushed 21d ago), licensed MIT. It adds 6,873 tokens to every session, about $0.0275 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 2026-09-24.

Related

pi-continue AGENTS.md compared with instructions from other repositories

pi-continue AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pi-continue AGENTS.mdTiziano-AI/pi-continueInstructions file2021d agoMITA6,873Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode