pi-rules AGENTS.md

Repository instructions for pi-rules, a TypeScript extension that manages coding rules, including its code style, tests, architecture, and process for adding rule sources.

In plain words
What is it for?
Use them when modifying pi-rules, writing its Vitest tests, or adding a new place from which rules are loaded.
Why use it?
They reduce inconsistent changes by defining formatting, type-safety, testing, filesystem, and network restrictions.

Instructions file for CodexOpenCode

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 instructions/code-yeongyu/pi-rules/agents-md
Clone the repo
git clone --depth 1 https://github.com/code-yeongyu/pi-rules

Made for: Codex, OpenCode.

Per session 670 This file is loaded in full into every session.
When invoked 670 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00670 $0.00670
Opus 5 $0.00335 $0.00335
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured yesterday against content hash 9faaacc38082, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pi-rules 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 yesterday.

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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project rules for pi-rules itself.

Code style

  • TypeScript strict mode (noUncheckedIndexedAccess, strict: true).
  • NO any in src/ (production). Use unknown and narrowing.
  • Imports use .js extension for project files (Node16 module resolution).
  • Tabs (indentWidth: 3), 120-char line width, biome-formatted.
  • ESM only ("type": "module").

Test conventions

  • Vitest, real temp filesystem via test/helpers/temp-fs.ts for fs-touching tests.
  • Naming: it("#given X #when Y #then Z") with // given / // when / // then body comments.
  • NO test deletion or skipping.
  • NO writes to real ~/.pi. Use injectable home dir.
  • NO network access.

Architecture

  • src/rules/ — pure logic units (parser, matcher, scanner, finder, ordering, cache, formatter, truncator, project-root, tool-paths) and orchestrating engine.ts (uses dependency injection).
  • src/ui/ — TUI components (rules-banner, dynamic-border).
  • src/commands.ts — slash command handlers.
  • src/index.tsdefault function piRulesExtension(pi: ExtensionAPI): void factory; registers flags + hooks + commands.

When adding a new rule source

  1. Add the path/extension to src/rules/constants.ts (PROJECT_RULE_SUBDIRS or PROJECT_SINGLE_FILES or USER_HOME_RULE_SUBDIRS).
  2. Update RuleSource union in src/rules/types.ts.
  3. Add SOURCE_PRIORITY entry.
  4. Update findRuleCandidates in src/rules/finder.ts if discovery semantics differ.
  5. Add tests covering the new source in test/finder.test.ts and the integration tests.
  6. Update README.md "What gets loaded" section.

Hook contract reminders

  • before_agent_start: return { systemPrompt: event.systemPrompt + block }. NEVER mutate event.systemPrompt in place. Use event.systemPromptOptions.contextFiles to dedup against pi's native loader.
  • tool_result: return { content: [...event.content, { type: "text", text: block }] }. NEVER mutate event.content in place.
  • session_start: reset state, but never throw.
  • All hooks are idempotent: dedup via cache keys (cwd+realPath+hash for static, toolCallId+realPath+hash for dynamic).

Read the full file on GitHub · 55 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. yesterday First seen · 55 lines · 670 tokens per session scan A 9faaacc38082

Subscribe to this mod's changes

pi-rules AGENTS.md is an instructions file published in the GitHub repository code-yeongyu/pi-rules (10 stars, last pushed 5d ago), licensed MIT. It adds 670 tokens to every session, about $0.0034 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 2026-08-31.