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.
curl -O https://raw.githubusercontent.com/ai-creed/ai-shakespii/master/AGENTS.mdgit clone --depth 1 https://github.com/ai-creed/ai-shakespiiWrote 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.
[](https://agentmods.dev/instructions/ai-creed/ai-shakespii/agents-md)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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(repoai-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/libis pure (rules never touch disk — sibling file content rides onFileEntry.text),src/clidoes all I/O. TypeScript on Bun; published to npm asshakespiiwith no build step — the tarball shipssrc/verbatim, so the tarball layout must equal the repo layout (packageRootresolution 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.
- Standard format only. Skills produced or validated by this tool use the standard Agent Skills format (
SKILL.md, YAML frontmatter withname+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. - Reuse skill-creator eval schemas (
evals.json/grading.json/benchmark.json+ the trigger-accuracy eval design). Wrap and enforce; do not reinvent. - 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.
- 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 todocs/CALIBRATION-*.mdinside tracked docs therefore resolve locally, not on GitHub. - Dual-location rule: canonical doc copies live in
~/.ai-pref-nsync/local-docs/ai-shakespii/(subdirsspecs/,plans/,brainstorm/,knowledge-references/; ROADMAP canonical atplans/ROADMAP.md). The in-repodocs/files are synced mirrors — update both, verify withcp+cmp.README.mdis repo-only. docs/ROADMAP.mdlists 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.mdbefore 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.
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.
- 10d ago First seen · 84 lines · 2,002 tokens per session scan A 602f039935b7
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.
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.
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).
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.
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).
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.