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/boozedog/pi-codemode/agents-mdgit clone --depth 1 https://github.com/boozedog/pi-codemodeWhat 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 | $0.00762 | $0.00762 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
pi-codemode 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-codemode Agent Instructions
Development approach: TDD first
All new behavior must be developed test-first.
- Write or update a focused failing test that describes the desired behavior.
- Run the relevant test command and confirm it fails for the expected reason.
- Implement the smallest change that can make the test pass.
- Run the test again and confirm it passes.
- Refactor only after tests are green.
- Repeat in small slices.
Do not add broad implementation before there is a failing test covering the behavior.
Test expectations
- Prefer small unit tests for executor, type generation, command quoting, config merging, and bridge behavior.
- Add integration tests for cross-component workflows only after the involved units are covered.
- For bug fixes, first add a regression test that fails on the current code.
- Tests should assert observable behavior, not implementation details, unless the detail is a security/resource-safety requirement.
Current MVP priority
The main MVP path is the QuickJS executor:
- QuickJS is the default executor target.
- Deno is optional/future and should stay behind the executor interface.
- Do not add a Node VM executor for MVP.
- Generated code should only access explicit globals:
codemode,$,shell,print, andπ. - Host tool calls must support async success, async failure, concurrency, timeout/cancellation, and clean runtime/context disposal.
Required QuickJS executor test slices
Before expanding executor features, keep these behaviors covered by tests:
- returns primitive and object values
- captures
print/ console output - injects
πstring constants - awaits one async host tool call
- resolves many concurrent host tool calls via
Promise.all - propagates rejected host calls to the guest promise
- supports nested MCP-style namespaces, e.g.
mcp.github.search_issues(...) - times out runaway code
- does not expose Node or host globals such as
process,require, filesystem, environment, network, or subprocess APIs - releases QuickJS runtime/context memory cleanly after execution
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.
- 2d ago First seen · 80 lines · 762 tokens per session scan A e648cd6cc285
pi-codemode AGENTS.md is an instructions file published in the GitHub repository boozedog/pi-codemode (24 stars, last pushed 19d ago), licensed MIT. It adds 762 tokens to every session, about $0.0038 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.