ai-shakespii: Instructions file for Codex

AGENTS.md

ai-shakespii AGENTS.md is an instructions file for Codex, OpenCode from ai-creed/ai-shakespii. It costs 2,002 tokens per session, scanned A, original, MIT.

A project instruction document for ai-shakespii, a tool that creates and validates agent skills as software components. It records the project's architecture, fixed decisions, source of truth, and repository layout.

In plain words
What is it for?
Use it when working on ai-shakespii to understand its Bun and TypeScript structure, command-line boundaries, standard SKILL.md format, and required development order.
Why use it?
It gives coding agents the context needed to follow the repository's conventions instead of guessing how the project is organized or what format its skills should use.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions subagents.

This is ai-creed/ai-shakespii's own configuration. It tells Codex and OpenCode how to work on ai-shakespii 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 ai-shakespii configures →

Reuse

Borrowing it

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

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 ai-shakespii AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ai-creed/ai-shakespii/agents-md"><img src="https://agentmods.dev/badge/instructions/ai-creed/ai-shakespii/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,002 This file is loaded in full into every session.
When invoked 2,002 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 $0.02002 $0.02002
Opus 5 $0.01001 $0.01001
Sonnet 5 $0.00400 $0.00400
Haiku 4.5 $0.00200 $0.00200

Measured 10d ago against content hash 602f039935b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ai-shakespii 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 10d 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 · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

Project Summary

  • shakespii (repo ai-shakespii) is a workbench for Agent Skills — init / lint / test / bench / gate-checked install. Skills are treated as software components with explicit contracts, not prompt folders.
  • Architecture is lib-first thin CLI: src/lib is pure (rules never touch disk — sibling file content rides on FileEntry.text), src/cli does all I/O. TypeScript on Bun; published to npm as shakespii with no build step — the tarball ships src/ verbatim, so the tarball layout must equal the repo layout (packageRoot resolution depends on it).
  • Build order (decided): linter → test harness → writer-as-skill → library. The writer (skills/authoring-skills) is a skill, not app code.

Non-Negotiable Decisions

See docs/STRATEGY.md for rationale.

  1. Standard format only. Skills produced or validated by this tool use the standard Agent Skills format (SKILL.md, YAML frontmatter with name + description, spec at agentskills.io). Never invent a parallel format. The shakespii skill anatomy (Intent / Inputs / Preconditions / Procedure / Output / Examples / Anti-patterns) is enforced as a content contract inside standard SKILL.md bodies.
  2. Reuse skill-creator eval schemas (evals.json / grading.json / benchmark.json + the trigger-accuracy eval design). Wrap and enforce; do not reinvent.
  3. TDD for all code. Every lint rule is a pure function over a parsed skill with fixture tests written first; the same discipline applies to harness and CLI code.
  4. Agent-first interface. The CLI is the deterministic substrate (--json, exit codes, rule IDs); the bundled companion skills are the interface agents drive it through.

Source Of Truth

  • Tracked specs live in docs/specs/. Implementation plans (docs/superpowers/plans/) and calibration docs (docs/CALIBRATION-*.md) are git-ignored local working copies — kept in the repo tree for the workflow but never committed; their canonical copies live only in the ai-pref-nsync root below. Citations to docs/CALIBRATION-*.md inside tracked docs therefore resolve locally, not on GitHub.
  • Dual-location rule: canonical doc copies live in ~/.ai-pref-nsync/local-docs/ai-shakespii/ (subdirs specs/, plans/, brainstorm/, knowledge-references/; ROADMAP canonical at plans/ROADMAP.md). The in-repo docs/ files are synced mirrors — update both, verify with cp + cmp. README.md is repo-only.
  • docs/ROADMAP.md lists open decisions — they are the user's to make; never pick one silently.
  • Lint rules cite their evidence (audit doc reference) in docs/LINT-RULES.md before implementation. The dogfood corpus is the user's installed skills at ~/.claude/skills/ plus the superpowers plugin — calibrate against it; synthetic fixtures are never enough.

Read the full file on GitHub · 84 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. 10d ago First seen · 84 lines · 2,002 tokens per session scan A 602f039935b7

Subscribe to this mod's changes

ai-shakespii AGENTS.md is an instructions file published in the GitHub repository ai-creed/ai-shakespii (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,002 tokens to every session, about $0.0100 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens