pokayokay: Instructions file for Claude Code

AGENTS.md

pokayokay AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from srstomp/pokayokay. It costs 1,756 tokens per session, scanned B, original, MIT.

Repository-specific instructions for working on pokayokay, a development-orchestration plugin that coordinates coding workflows and task management through ohno.

In plain words
What is it for?
Use them when changing pokayokay, validating its plugin setup, running its command-line setup, or executing its tests.
Why use it?
They explain the project structure, the difference between its Codex and Claude Code support, and the commands needed to develop and test it.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: SessionStart hook event, but also the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions subagents; mentions Claude Code.

This is srstomp/pokayokay's own configuration. It tells Claude Code, Codex and OpenCode how to work on pokayokay 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 pokayokay configures →

Reuse

Borrowing it

Nothing to install: this file belongs to srstomp/pokayokay. 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/srstomp/pokayokay/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/srstomp/pokayokay

Made for: Claude Code, 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 pokayokay AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/srstomp/pokayokay/agents-md"><img src="https://agentmods.dev/badge/instructions/srstomp/pokayokay/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,756 This file is loaded in full into every session.
When invoked 1,756 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01756 $0.01756
Opus 5.5 $0.00702 $0.00702
Sonnet 5.5 $0.00351 $0.00351
Haiku 4.5 $0.00176 $0.00176

Measured 2mo ago against content hash a476f31bc729, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

pokayokay AGENTS.md scanned grade B with 1 finding 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Note: Codex installs in two steps — `codex plugin marketplace add` registers the source under `[marketplaces.pokayokay]` in `~/.codex/config.toml`, and `codex plugin add pokayokay@pokayokay` installs the plugin (recorded
AGENTS.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex when working with code in this repository.

Project Overview

pokayokay is a development-orchestration plugin built primarily for Claude Code, with additive Codex support. It integrates with ohno (task management via MCP) to provide structured workflows with configurable human oversight.

Important: the Codex and Claude Code surfaces differ. On Codex, the plugin provides skills, the ohno MCP server, and lifecycle hooks. The commands/ and agents/ directories are Claude Code-only — Codex has no Task-tool subagent dispatch, and the .codex-plugin/plugin.json manifest exposes only skills/ and .mcp.json. When a skill references dispatching a yokay-* agent, execute that agent's role inline instead: read the corresponding plugins/pokayokay/agents/yokay-<name>.md and follow its checklist and output contract directly.

Development Commands

# Register this checkout as a Codex plugin marketplace, then install the
# plugin from it (run from repo root)
codex plugin marketplace add .
codex plugin add pokayokay@pokayokay

# Run the CLI setup wizard locally (wires ohno MCP + Codex hooks)
npm --prefix cli install
node cli/bin/cli.js

# Run specific shell tests
bash plugins/pokayokay/tests/<test-name>.test.sh

# Run the full test suite (shell + node, per-test PASS/FAIL, non-zero exit on failure)
npm test
# or directly:
bash plugins/pokayokay/tests/run-tests.sh

# Codex-specific test suites
bash plugins/pokayokay/tests/codex-compatibility.test.sh
node --test plugins/pokayokay/tests/cli-dual-runtime.test.mjs

Note: Codex installs in two steps — codex plugin marketplace add registers the source under [marketplaces.pokayokay] in ~/.codex/config.toml, and codex plugin add pokayokay@pokayokay installs the plugin (recorded under [plugins."pokayokay@pokayokay"]). The marketplace step alone does not install anything. The command is add, not install, and there is no codex plugin validate.

Architecture

Read the full file on GitHub · 130 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. 2mo ago First seen · 130 lines · 1,756 tokens per session scan B a476f31bc729

Subscribe to this mod's changes

pokayokay AGENTS.md is an instructions file published in the GitHub repository srstomp/pokayokay (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,756 tokens to every session, about $0.0070 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

pokayokay AGENTS.md compared with instructions from other repositories

pokayokay AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pokayokay AGENTS.mdsrstomp/pokayokayInstructions file91mo agoMITB1,756Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode